Recent Releases of https://github.com/bytedance/ui-tars-desktop

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.11

What's Changed

From v0.3.0-beta.11, we have mainly introduced the Real-time Thinking Duration Protocol, introduced the MongoDB Provider to Agent Server, supported Tarko Agent UI Builder and CLI, and optimized a lot of Web UI experience.

Here is a simple demo of Thinking Duration:

https://github.com/user-attachments/assets/ee2e2883-4bf5-4558-a1a6-eff34916fb68

New Features πŸŽ‰

  • feat(tarko): implement MongoDB provider for agent server (#1450) by @cjraft in b69aa5a
  • feat(tarko): agui cli for agent ui builder, see @tarko/agent-ui-cli (#1446) by @ulivz in 7bb9184
  • feat(o-agent): update sandbox sdk and gui-agent operator (#1437) by @cjraft in 8e2d7bb
  • feat(mcp-servers): support mcp offical registry (#1447) by @ycjcl868 in 5d773cf
  • feat(tarko): add navbar logo display options (#1443) by @ulivz in 4b1ed1f
  • feat(tarko): init @tarko/agent-ui-builder (#1436) by @ulivz in a99ac0c
  • feat(tarko): move workspace navItems from header to navbar (#1441) by @ulivz in 73fa2dc
  • feat(tarko): add tabbed file viewer for read_multiple_files tool (#1438) by @ulivz in 88f3568
  • feat(gui-agent): improve page visibility detection in AIOBrowser (#1431) by @ZhaoHeh in 230853e
  • feat(tarko-agent): thinking duration protocol and modernize thinking ui (#1423) by @ulivz in 094d40e
  • feat(tarko): refine collected files (#1422) by @ulivz in 95b1bfb
  • feat(tarko): add guiAgent.renderBrowserShell option (#1421) by @ulivz in 5a9d8e4

Bug Fixes πŸ›

  • fix(tarko): fetch actual remote config instead of local file (#1449) by @ryanroe in 083f842
  • fix(tarko): external @tarko/agent-ui-builder in agent-cli build (#1445) by @ulivz in fe579ae
  • fix(tarko): improve markdown inline code wrapping (#1439) by @ulivz in df9f553
  • fix(tarko): resolve react key spread warning and hooks render issue (#1435) by @ulivz in f3f4bf6
  • fix(tarko): make thinking toggle default expanded without initial animation (#1432) by @ulivz in ce0947d
  • fix(tarko): prevent frequent api/v1/models calls by memoizing callbacks (#1378) by @ulivz in e07ec41
  • fix(tarko): improve scroll-to-bottom indicator edge case handling (#1429) by @ulivz in 50eb9f2
  • fix(tarko): prevent duplicate session loading in SessionRouter (#1427) by @ulivz in f96d4ff
  • fix(tarko-agent): improve JSON parsing in PromptEngineeringToolCallEngine (close: #1360) (#1361) by @ulivz in b2d5817

Other Changes

  • refactor(tarko): rename SessionItemInfo to SessionInfo (#1440) by @ulivz in d1b4d97
  • refactor(tarko): rename agent-web-ui to agent-ui (#1434) by @ulivz in 9a4e8f5
  • refactor(tarko): simplify code editor components (#1425) by @ulivz in 8b46f6f
  • chore(tars-stack): release 0.3.0-beta.11 by @ulivz in be3cfab
  • chore(all): fix changelog generation (#1420) by @ulivz in e53360b
  • ci: remove tag prefix from release scripts (#1451) by @ulivz in 12ebdba
  • ci(ptk): github release (#1428) by @ulivz in cbe3894

Full Changelog: @agent-tars@0.3.0-beta.10...v0.3.0-beta.11

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.10

What's Changed

News ✨

We are excited to announce that this version officially introduces support for UI-TARS-2!

  • Paper: https://arxiv.org/abs/2509.02544
  • Demo: https://seed-tars.com/showcase/ui-tars-2
  • X: https://x.com/TsingYoga/status/1963629621326614940

New Features πŸŽ‰

  • feat(tarko): limit welcome prompts to 3 with shuffle (#1416) by @ulivz in c6d6791
  • feat(tarko): refine all empty state (#1408) by @ulivz in 18dc008
  • feat(tarko): add user message auto-scroll in normal mode (#1412) by @ulivz in 2c7f55d
  • feat(tarko): enhance slug generation with multilingual support (#1410) by @ulivz in 915c7c5
  • feat(tarko): auto-scroll for replay (#1407) by @ulivz in da22a39
  • feat(tarko): improve ChatInput UX with conditional help text and home variant (#1406) by @ulivz in 8c38bfc
  • feat(tarko): refine thinking animation (#1404) by @ulivz in bae4951
  • feat(tarko): refine scroll-to-bottom indicator (#1402) by @ulivz in 3a7d239
  • feat(tarko): defaults background to white for html renderer (#1397) by @ulivz in c583e7e

Bug Fixes πŸ›

  • fix(tarko): prevent auto-scroll on refresh for historical user messages (#1415) by @ulivz in 62df723
  • fix(tarko): improve scroll-to-bottom indicator detection (#1411) by @ulivz in 556e3a0
  • fix(tarko): improve session UI state management (#1409) by @ulivz in 0391c11
  • fix(tarko): scroll-to-bottom indicator session switching and edge cases (#1405) by @ulivz in 442dab8
  • fix(tarko): improve markdown link parsing edge cases (#1398) by @ulivz in 24fdf31

Other Changes

  • refactor(tarko): remove excessive dots from empty states (#1414) by @ulivz in 074559e
  • chore(tars-stack): release 0.3.0-beta.10 by @ulivz in 59b59ef
  • chore: fix changelog filter scopes and restore missing entries (#1418) by @ulivz in b3fe00d
  • chore(o-agent): update example prompts (#1417) by @ulivz in 3b28c9b
  • chore(tarko): enhance code block spacing (#1400) by @ulivz in 1752459
  • chore(tars-stack): release 0.3.0-beta.9 (#1396) by @ulivz in da0e22b

Full Changelog: v0.3.0-beta.9...v0.3.0-beta.10

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.9

What's Changed

News ✨

We are excited to announce that this version officially introduces support for UI-TARS-2!

  • Paper: https://arxiv.org/abs/2509.02544
  • Demo: https://seed-tars.com/showcase/ui-tars-2
  • X: https://x.com/TsingYoga/status/1963629621326614940

New Features πŸŽ‰

  • feat(tarko): refine LinkReaderRenderer (#1393) by @ulivz in c985542
  • feat(o-agent): temp hack for model thinking (#1395) by @cjraft in 605bf84
  • feat(tarko): auto-append replay=1 to share URLs (#1394) by @ulivz in 6a85332
  • feat(o-agent): system prompt update (#1392) by @cjraft in b19f9ef
  • feat(tarko): disable html rendering in markdown renderer (#1391) by @ulivz in 057a466
  • feat(gui-agent): delay 1s before screenshot on aio hybried operator (#1388) by @heh in 79e835a
  • feat(o-gui-agent): support ChromeUI gui operation on AIO sandbox (#1383) by @heh in a034369
  • feat(tarko): refine behavior of guiAgent.renderGUIAction (#1386) by @ulivz in 94b4c32
  • feat(o-agent): update time and proxy instruction in sp (#1384) by @cjraft in 1906ec6
  • feat(tarko): add multimodal clipboard paste support (#1379) by @ulivz in 2b40a7c
  • feat(tarko): refactor chat panel ui (#1375) by @ulivz in 70c28fa
  • feat(tarko): reuse chat input in home page (#1313) by @ulivz in 350364d
  • feat(tarko): add model id tooltip to navbar (#1370) by @ulivz in 4da9abb
  • feat(o-agent): native think (#1371) by @cjraft in 195c875

Bug Fixes πŸ›

  • fix(tarko): correct isProcessing state management during agent execution (#1387) by @ulivz in 9d0df70
  • fix(tarko): fix markdown link parsing with chinese text (#1358) by @ulivz in 73ca0ca
  • fix(tarko): image data missing in workspace (#1373) by @ulivz in 2a79e1d

Other Changes

  • refactor(tarko): simplify screenshot display state management (#1390) by @ulivz in d3710ad
  • refactor(tarko): remove unnecessary abstraction and redundant state updates (#1380) by @ulivz in dfee2b3
  • chore(tars-stack): release 0.3.0-beta.9 by @ulivz in 81a1cfa
  • chore(o-agent): disable gui agent screenshot switch and render (#1385) by @ulivz in 2a92348
  • chore(ptk): add --no-verify to release commits (#1369) by @ulivz in e19a0f2
  • chore(ptk): update release commit scope from agent-tars to tars-stack (#1368) by @ulivz in 25001c7
  • chore(all): fix grammar typo (#1367) by @ulivz in 48e40ab
  • ci(ptk): handle missing git tags in changelog generation (#1372) by @ulivz in d9eb138

Full Changelog: v0.3.0-beta.8...v0.3.0-beta.9

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.3

What's Changed

New Features πŸŽ‰

  • feat(tarko): add built-in agents support (#1208) by @ulivz in 2ee2848
  • feat(tarko): add webui workspace panels support (#1206) by @ulivz in 04db315
  • feat(tarko): add webUIConfig support to AgentConstructor (#1207) by @ulivz in b968bb5
  • feat(tarko): add intelligent auto-scroll to chat UI (#1203) by @ulivz in 85b6dd4
  • feat(ui-tars): sunset UI-TARS-desktop remote operator (#1135) by @skychx in 21c3910
  • feat(tarko): decouple file renderers from GenericResultRenderer (#1201) by @ulivz in 9f586e4
  • feat(omni-gui-agent): migrate from local browser to AIO sandbox browser (#1205) by @heh in 3f204bb
  • feat(omni-agent): enable gui in omni agent (#1197) by @heh in b564062
  • feat(omni-gui-agent): execute screenshot on demand on EachLoopEnd hook (#1195) by @heh in e17643b
  • feat(tarko): fully compatible with str_replace_editor (#1189) by @ulivz in 7a4ff74
  • feat: upgrade @agent-infra/sandbox package and add health check (#1188) by @小ε₯ in 65b806a
  • feat: enhance o-agent with session state management and Jupyter CI support (#1186) by @小ε₯ in fea1084
  • feat(tarko): initial support model.displayName (#1163) by @ulivz in 6239834
  • feat(tarko): add workspace raw mode display (#1167) by @ulivz in 29826ae
  • feat(tarko): add loading states for session creation and switching (#1168) by @ulivz in f551d4c
  • feat(tarko): improve JupyterCI tool rendering ui (#1166) by @ulivz in 4d43191
  • feat(tarko-cli): load env file baesd on the workspace (#1170) by @小ε₯ in 9482717
  • feat(tarko): refine run command semantics (#1158) by @ulivz in 73a79a9
  • feat(tarko): add .env file support (#1156) by @小ε₯ in 2279ad9
  • feat(mcp-client): add tools and prompts filtering with comprehensive tests (#1155) by @charles in 896274f
  • feat(tarko): add agent config viewer (#1153) by @ulivz in 971360b
  • feat(agent-tars): support flexible system prompt override (#1151) by @ulivz in d975c30
  • feat(tarko): add agent server exclusive mode support (#1149) by @ulivz in acfae7c
  • feat(tarko): add workspace config support for instructions.md (#1145) by @ulivz in 1357e48
  • feat(agent-cli): auto-detect available port to prevent conflicts (close: #1141) (#1142) by @ulivz in ce9e10b
  • feat(mcp): increase default timeout from 10s to 60s (#1139) by @ulivz in 64095e5
  • feat(gui-agent): support remote browser operator and update web-ui feature for o-tars gui agent (#1136) by @heh in 2249b98
  • feat(o-agent): migrate from omni-tars core to agent-infra sandbox (#1137) by @小ε₯ in cda0a13
  • feat(gui-agent): construct operator on demand (#1133) by @heh in b29c1d2
  • feat(o-agent): improve configuration and performance optimization (#1131) by @小ε₯ in 61f2b8a
  • feat(tarko): o tars adaptation (#1127) by @ulivz in 3ea3053
  • feat(tarko): refactor event processor architecture (#1119) by @ulivz in 732aead
  • feat(tarko): add raw events state (#1118) by @ulivz in 78c1366
  • feat(tarko): display workspace path in workspace header (#1117) by @ulivz in 0b83eee
  • feat(navbar): improve width control and model display (#1116) by @ulivz in 4d0b34e
  • feat(agent): move aio client to core package, add unit test for parser (#1113) by @小ε₯ in cb7d1f2
  • feat(tarko): move model selector from chat input to navbar (#1089) by @ulivz in 28ff271
  • feat(tarko): edit_file renderer (#1107) by @ulivz in 855a2da
  • feat: enhance code agent and model output adaptation (#1108) by @小ε₯ in d40aa0d
  • feat(tarko-agent): add onEachAgentLoopEnd hook (#1111) by @ulivz in 6521137
  • feat: add gui agent powered by tarko (#1031) by @heh in c135aa5
  • feat(tarko): add LinkReader renderer support (#1099) by @ulivz in 38b9c44
  • feat(tarko): optimize time to first token experience (close: #1052) (#1082) by @ulivz in 2faa945
  • feat(tarko): support switching model at runtime (close: #1057) (#1058) by @ulivz in 4dcc321
  • feat(tarko): add workspace display in navbar (close: #1039) (#1081) by @ulivz in c5a3f9c
  • feat(tarko): improve search result relevance scoring (#1079) by @ulivz in 59e8e99
  • feat(tarko): optimize navbar space for agent and model display (close: #1076) (#1078) by @ulivz in cb067fd
  • feat(tarko-cli): add config logging reminders (close: #1063) by @ulivz in 7fabccf
  • feat(omni-tars): migrate gui agent into omni tars (#1071) by @heh in 05bf32b
  • feat(gui-agent): add action parser for omni (#1065) by @heh in 153fea9
  • feat(omni-tars): refactor AgentPlugin architecture and enhance API integration (#1056) by @小ε₯ in 5805005
  • feat(tarko): remove auto scroll behavior from ChatPanel (#1049) by @ulivz in 9887239
  • feat(tarko): enhance thinking message ui (#1048) by @ulivz in f40a996
  • feat(tarko): mcpServer filter (close: #1045) (#1046) by @ulivz in 77a7fc3
  • feat(omni-tars): implement omni-tars multi-agent system (#1047) by @小ε₯ in 1b0c93d
  • feat(tarko): tools filter (close: #1041) (#1042) by @ulivz in 1040760
  • feat(tarko): experimental contextual selector (#1032) by @ulivz in 478b9a1
  • feat(agent-server): handle old workspace schema migration (#1030) by @ulivz in 1057f1b
  • feat: seed mcp agent (#1023) by @小ε₯ in 58e599b
  • feat(tarko): add @tarko/interface and defineConfig function (#1022) by @ulivz in dc3d2f7
  • feat(tarko): agent resolver should respect workspace (#1021) by @ulivz in 52a9fbf
  • feat(tarko): webui config and render dynamic ui metadata (#1017) by @ulivz in f794270
  • feat(tarko): refine agent module path resolution (#1016) by @ulivz in 03e7a26
  • feat(tarko): display agent name in web ui (#1015) by @ulivz in 9cc804c
  • feat(tarko): refine package scope (#1013) by @ulivz in 2474789
  • feat(tarko): refine workspace resolution (#1011) by @ulivz in 9a7af10
  • feat(tarko): refine workspace design (#1008) by @ulivz in 674d67a
  • feat(tarko): global directories (#1007) by @ulivz in de40626
  • feat(agent-tars): custom agent by @ulivz in 6799ebd
  • feat(agent): add dispose api and onDispose hook (#997) by @ulivz in ce2df9e
  • feat(agent): add getTools type (#996) by @ulivz in af981e1
  • feat(agent-tars-web-ui): simplify replay state (#989) by @ulivz in f865c6d
  • feat(agent-tars-server): session read optimization (close: #750) (#974) by @小ε₯ in 68f9805

Bug Fixes πŸ›

  • fix(tarko): allow workspace panel updates in replay mode (#1202) by @ulivz in 898914f
  • fix(tarko): replace hardcoded texts with configurable title (#1174) by @ulivz in 5bd7e26
  • fix(tarko): display "Unknown Agent" at initial rendering (#1184) by @ulivz in 6d3b0ca
  • fix(tarko): persist agent name in session metadata (#1175) by @ulivz in 436da04
  • fix(tarko): handle CLI parameter order for agent argument (#1169) by @ulivz in 2acb378
  • fix(tarko): add rollback error handling in sqlite migration (#1147) by @ulivz in 9a49826
  • fix(tarko): inline code dark mode text color (#1143) by @ulivz in b37ec25
  • fix(tarko): preserve events data during database migration (#1121) by @ulivz in d00fede
  • fix(tarko): use plain text rendering for user messages (closes #1103) (#1104) by @ulivz in db45a12
  • fix(tarko): improve omni tars search result rendering (close: #1094) (#1096) by @ulivz in ca7bfb5
  • fix(tarko): enhance contextual selector with path support and validation (#1077) by @ulivz in fd89a01
  • fix(tarko): validate session consistency before panel updates (#1072) by @ulivz in b9cbbd7
  • fix(mcp-search): replace node-fetch with native fetch for Node.js 22 (#1069) by @ulivz in e69521d
  • fix(omni-tars): add missing super.onAgentLoopEnd() call (#1066) by @ulivz in 9d71442
  • fix(agent-tars): directory_tree causes context overflow (close: #969) (#1055) by @ulivz in 9220b25
  • fix(agent-tars-cli): sqlite should consider backward compatibility (#1029) by @ulivz in 62f5e05
  • fix(tarko): agent cli should pass directories config (#1024) by @ulivz in 0cd72b8
  • fix(agent-tars-web-ui): replay does not work (#981) by @ulivz in c39deb9
  • fix(mcp-browser): browser mcp screenshot and refactor forminputfill (#957) by @charles in 26c4131

Documentation πŸ“š

  • docs(tarko): enhance agent-server documentation (#1164) by @ulivz in 69f8505
  • docs(tarko): improve agent-cli documentation (#1162) by @ulivz in eae3a94
  • docs: clarify instructions field behavior (#1059) by @ulivz in 6955142
  • docs(agent-tars): fix dead feishu link (close: #1009) (#1010) by @ulivz in 5fdac47
  • docs(agent-tars): update showcase tags (#991) by @ulivz in ac40c73
  • docs(agent-tars): make showcase public (#988) by @ulivz in aa98838
  • docs: update redirects (#983) by @ulivz in ef97e19
  • docs: add new redirects (#980) by @ulivz in 6a6b08b
  • docs: quick-start.md add links for Volcano Engine's OS Agent (#972) by @skychx in 0e6f62f

Other Changes

  • refactor(tarko): flexible condition-based system for tool renderer (#1191) by @ulivz in 00df4a5
  • refactor(tarko): some enhancement for gui agent (#1198) by @ulivz in dcf7f7b
  • refactor(tarko-web-ui): some enhancements (#1185) by @ulivz in 5d56b38
  • refactor(agent-server): refine session item info naming (#1183) by @ulivz in 4a1983b
  • refactor(tarko): remote complex mid-layers in workspace renderer (#1120) by @ulivz in 09dcec3
  • refactor(tarko): migrate to extensible JSON schema database design (#1122) by @ulivz in 7f6802f
  • refactor(tarko): improve agent storage implementation type system (#1025) by @ulivz in 895d8be
  • refactor(agent-tars-cli): clean unused dependencies (#1014) by @ulivz in 5244e5d
  • refactor(all): refine project structures (#1012) by @ulivz in 74ab1dc
  • refactor(agent): sink workspace config to tarko (#998) by @ulivz in a3dca32
  • refactor(agent-tars): clean browser control info (#993) by @ulivz in e96f0cd
  • refactor(agent-tars-web-ui): comments (#990) by @ulivz in 08369ab
  • refactor(mcp-browser): browsergetmarkdown (#982) by @charles in cdf385f
  • chore(omni-tars): fix dev:agent launch issue by @chenhaoli in b99db7b
  • chore(tarko): fix which final environment is shown after non-screensh… (#1209) by @heh in 845cbd0
  • chore(gui-agent): fix the missing final screenshot (#1190) by @heh in 0ee8730
  • chore(tarko): remove fallback when no screenshot is available by @chenhaoli in 34ad81f
  • chore(mcp-browser): _meta add screen coords & fix console in stdio mode (#984) by @charles in 06243d4
  • chore(docs): correct workspace default path in English and Chinese guides (#1124) by @jacob in a437116
  • chore(agent-web-ui): remove unused ModelSelector component (#1115) by @ulivz in aec6dc9
  • chore: fix link leading to local docs for local and remote operators (#1112) by @alex unger in 22eb93a
  • chore(scripts): add build:omni-tars script (#1067) by @ulivz in 922f96f
  • chore(ci): add lint (#1002) by @charles in 17b0742
  • chore: rename @agent-tars/server to @multimodal/agent-server (#975) by @ulivz in 2d97b03
  • chore(ui-tars): update release version (#977) by @heh in ff78abb
  • release(agent-tars): release 0.3.0-beta.3 (#1210) by @ulivz in 8ce4c2e
  • release(agent-tars): release 0.3.0-beta.1 (#965) by @ulivz in edcf09b

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/@agent-tars@0.3.0-beta.1...@agent-tars@0.3.0-beta.3

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.8

What's Changed

New Features πŸŽ‰

  • feat(tarko): implement session state isolation (#1357) by @ulivz in 6f15635
  • feat(tarko): unify think rendering with markdown renderer (#1353) by @ulivz in 3a1d53c

Bug Fixes πŸ›

  • fix(tarko): resolve infinite recursion in layoutModeAtom (#1356) by @ulivz in 91e4016
  • fix(tarko): downgrade react-router-dom to v6 for compatibility (#1355) by @ulivz in 5c5887f
  • fix(tarko): fallback to beforeActionImage in afterAction strategy to prevent flickering (#1352) by @ulivz in 6190fea
  • fix(tarko): hide workspace navigation items in replay mode (#1350) by @ulivz in ccb2262

Other Changes

  • chore(tars-stack): release 0.3.0-beta.8 (#1366) by @ulivz in 4f1cd9b
  • chore(o-agent): update display texts (#1351) by @ulivz in 8c0f42a

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/@agent-tars@0.3.0-beta.7...@agent-tars@0.3.0-beta.8

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.7

What's Changed

New Features πŸŽ‰

  • feat(tarko): remove independent environment input rendering in final state (#1346) by @ulivz in db2515d
  • feat(browser-operator): use agent-infra's Hotkey to execute hotkeys (#1343) by @skychx in 0e758f5
  • feat(o-gui-agent): temporary solution for getting metadata when screenshot (#1341) by @heh in a56a6c3
  • feat(o-agent): enable enableStreamingToolCallEvents (#1340) by @ulivz in 97c937f
  • feat(o-gui-agent): support navigate action for new model (#1339) by @heh in 3927337
  • feat(tarko): apply RTL only to file-related tools in tool blocks (#1337) by @ulivz in 19bf806
  • feat(tarko): trim leading newlines from thinking message content (#1333) by @ulivz in 1e7a553
  • feat(omni-gui-agent): adapt tarko's screenshot rendering protocol (#1335) by @heh in cd84f2f
  • feat(tarko): only show MessageFooter on final assistant response (#1331) by @ulivz in da3196e
  • feat(o-agent): xml parser for agent model (#1330) by @小ε₯ in 80af8c7
  • feat(tarko): add math formula rendering support to markdown renderer (#1329) by @ulivz in 1239065
  • feat(tarko): show edit_file path in tool call block (#1309) by @ulivz in 28d58d3
  • feat(tarko): add url field to screenshot metadata and display in browser shell (#1308) by @ulivz in 4ca0fd9
  • feat(tarko): one-click copy raw tool data (#1304) by @ulivz in df001c6
  • feat(tarko-web-ui): narrow chat mode (#1298) by @ulivz in f4510f9
  • feat(tarko): add gui agent screenshot render strategy config (#1296) by @ulivz in 3730cf6
  • feat(agent-tars): strict-typed gui agent procotol (#1295) by @ulivz in 4aa9d78
  • feat: enhance streaming for o-agent with improved parsing and processing #1294 (#1294) by @小ε₯ in 4724244
  • feat(tarko): switch gui agent to percentage coordinates (#1292) by @ulivz in f56f6fc
  • feat(tarko): improve abort button styling (#1290) by @ulivz in 68437e6
  • feat(tarko): adjust maxIterations default to 1000 (#1289) by @ulivz in 94e890b
  • feat(tarko-web-ui): streaming thinking rendering support (#1284) by @ulivz in ae83d3d
  • feat(tarko-agent): add messageId to thinking events for proper session correlation (#1282) by @ulivz in 1fcba4c
  • feat(tarko): add codebase metadata to contextual references (#1274) by @ulivz in 6920d83
  • feat(tarko): adapt devicePixelRatio from metadata in web ui (#1275) by @ulivz in a728915
  • feat(tarko): add metadata field to EnvironmentInputEvent (#1272) by @ulivz in 97ad8aa
  • feat(mcp-agent): upgrade mcp-client to 1.2.20 and set 180s timeout (#1271) by @ulivz in 23d73a5
  • feat(tarko): support TTFT and TTLT metric (#1232) by @ulivz in bfa2879
  • feat(tarko-agent): refine contextual selector (#1134) by @ulivz in aee4bf8
  • feat(agent-tars): add static webui config to core (#1266) by @ulivz in 5ba0564

Bug Fixes πŸ›

  • fix(tarko): persist agent web ui config in share (#1347) by @ulivz in c190d00
  • fix(browser): server declares logging capability but doesn't implement method logging/setLevel (#1334) by @charles in 6f537a3
  • fix(tarko): browser shell url bar takes full width without spacing (#1327) by @ulivz in 32f71a6
  • fix(tarko): unexpected markdown render in generic renderer dark mode (#1324) by @ulivz in 282e306
  • fix(tarko): table dark mode styling (#1323) by @ulivz in 173a110
  • fix(tarko): move StrategySwitch after ScreenshotDisplay to prevent flicker (#1321) by @ulivz in 91b6053
  • fix(tarko): model displayName regression issue (#1315) by @ulivz in 18f34fa
  • fix(tarko): replace hardcoded agent name with dynamic config in TerminalOutput (#1306) by @ulivz in f27942e
  • fix(tarko): handle open_computer action normalization (#1305) by @ulivz in 871ea58
  • fix(tarko): resolve infinite re-render in BrowserControlRenderer hooks (#1303) by @ulivz in 7278561
  • fix(tarko): prevent unnecessary environment_input events without contextual references (#1301) by @ulivz in e394343
  • fix(agent-server): add safety check for agent.dispose in session cleanup (#1291) by @ulivz in 97ef7ad
  • fix(tarko): disable share button during agent execution (#1288) by @ulivz in ba4509b
  • fix(tarko-cli): --thinking does not work (#1283) by @ulivz in 03b1d21
  • fix(tarko-cli): prevent console interceptor recursion in debug mode (#1279) by @ulivz in 7bcff07
  • fix(tarko): improve script execution ui layout and styling (#1268) by @ulivz in fc7a80d
  • fix(agent-tars): correct webui property name to webuiConfig (#1267) by @ulivz in 4a5f2fc
  • fix(tarko): optimize EditFile title path display (#1246) by @ulivz in 83f8b85

Documentation πŸ“š

  • docs(agent-tars): agent hooks (#1277) by @ulivz in 8343182
  • docs(agent-tars): preserve tag filter state when navigating back (#1276) by @ulivz in 895c4b3
  • docs: fix missing useI18n import in NotFoundLayout (#1265) by @ulivz in 70f67a6
  • docs(tarko): add comprehensive event stream documentation (#1242) by @ulivz in 52b44be

Other Changes

  • refactor(tarko-web-ui): centralize markdown theme architecture (#1325) by @ulivz in 0067fde
  • refactor(common): extract LoadingSpinner and unify modal styles (#1317) by @ulivz in 5c38936
  • refactor(tarko): remove meaningless re-exports and restructure web-ui config (#1307) by @ulivz in d35602c
  • refactor(tarko-web-ui): extract tooltip props to shared config (#1300) by @ulivz in 9a1b124
  • refactor(tarko): remove unused workspace utilities (#1238) by @ulivz in 240595a
  • refactor(tarko): extract shared terminal component (#1264) by @ulivz in 37be890
  • refactor(tarko): remove over-designed language support (#1263) by @ulivz in 7180405
  • refactor(tarko): remove redundant FileRenderer wrapper (#1260) by @ulivz in 0d5a88e
  • refactor(tarko): merge EditFileRenderer into DiffRenderer (#1259) by @ulivz in 173a03d
  • chore(agent-tars): release 0.3.0-beta.7 (#1348) by @ulivz in 3bdac27
  • chore(tarko): remove codeblock action buttons (#1344) by @ulivz in 0f55ce9
  • chore(agent): update default layout config (#1311) by @ulivz in 2f4e78d
  • chore: only enable route.exclude in production build by @chenhaoli in 50c6923
  • chore(tarko): improve gui agent screenshot ui layout and placeholder (#1302) by @ulivz in e083c72
  • chore(tarko): replace @ui-tars/operator-browser with local @gui-agent/operator-browser (#1278) by @ulivz in 2c13c04
  • chore(mcp-client): release 1.2.20 (#1270) by @ulivz in 5a7200d
  • chore(all): unify naming case of webui config (#1269) by @ulivz in 55bb023

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/@agent-tars@0.3.0-beta.6...@agent-tars@0.3.0-beta.7

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.3.0-beta.6

What's Changed

New Features πŸŽ‰

  • feat(o-agent): add custom timeout for executebash tool; remove stopsequences config (#1256) by @小ε₯ in 5728e0b
  • feat(omni-gui-agent): optimize system prompt to use navigate instead of type (#1230) by @heh in c5b4993
  • feat(tarko): support top_p configuration for the model (#1247) by @小ε₯ in 9ba651a
  • feat(tarko): improve workspace header icons and raw mode spacing by @ulivz in 90a7a8d
  • feat(mcp-client): add configurable timeout (#1176) by @ulivz in 858c8c7
  • feat(tarko): temporary support for str_replace_editor view command (#1236) by @ulivz in dad2e3d
  • feat(tarko): refine str_replace_editor renderer (#1200) by @ulivz in b19de17

Bug Fixes πŸ›

  • fix(agent-tars): move required deps from devDependencies to dependencies (#1255) by @ulivz in 24e6acf
  • fix(tarko): enable line wrapping for command stdout/stderr (#1249) by @ulivz in cda0324
  • fix(tarko): update session title in correct metadata structure (#1233) by @ulivz in 94278e5

Documentation πŸ“š

  • docs(agent-tars): update video introduction url (#1248) by @ulivz in c81ed80
  • docs(tarko-agent): init readme (#1179) by @ulivz in 78fac95

Other Changes

  • refactor(tarko): consolidate state atoms (#1237) by @ulivz in 1447009
  • chore(agent-tars): release 0.3.0-beta.6 (#1257) by @ulivz in 5569064
  • chore(all): standardize the written terminology of Omni-TARS (#1235) by @ulivz in 923785a
  • chore(o-tars): using sync mode for execute_bash (#1228) by @ulivz in 06fa5bf
  • chore(agent-tars): release 0.3.0-beta.5 (#1227) by @ulivz in 280bbdc

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/@agent-tars@0.3.0-beta.5...@agent-tars@0.3.0-beta.6

- TypeScript
Published by ulivz 9 months ago

https://github.com/bytedance/ui-tars-desktop - v0.2.4

What's New

You can also experience the remote versions on Volcano Engine: Computer Operator and Browser Operator.

mac_app

What's Changed

  • feat(ui-tars): sunset UI-TARS-desktop remote operator by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/1135
  • chore(ui-tars): update release version by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/977

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.2.3...v0.2.4

- TypeScript
Published by github-actions[bot] 10 months ago

https://github.com/bytedance/ui-tars-desktop - v0.2.3

What's New

Bug Fixes πŸ› - Resolved an issue where the browser operator failed to support the HTTP/2 protocol. - Corrected the default width of the VNC window to ensure proper display.

before

after

Maintenance βš™οΈ - Updated the URL for the Volcano Engine OS Agent to point to the new, correct location.

What's Changed

  • fix(nut-js): rewrite drag/select by @joey1994 in https://github.com/bytedance/UI-TARS-desktop/pull/909
  • fix(browser): remove disable http2 by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/936
  • feat(ui-tars): change vnc default width and height by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/955
  • docs: quick-start.md add links for Volcano Engine's OS Agent by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/972

New Contributors

  • @joey1994 made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/909

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.2.2...v0.2.3

- TypeScript
Published by github-actions[bot] 10 months ago

https://github.com/bytedance/ui-tars-desktop - v0.2.2

Key Changes

  • support headful browser with VNC control
  • add model availability check logic

Details

VNC Browser

In this update, we have replaced the remote browser operator's screen casting feature with VNC Browser. This version provides a more stable screen casting experience and supports displaying the full Chrome UI:

https://github.com/user-attachments/assets/b5ec662f-1185-46fc-b354-82d0a913cb18


Check Model Availability

After configuring the VLM Model Settings, users can proactively click the Check Model Availability button below to verify the availability of the VLM Model:


What's Changed

  • chore(ui-tars): update release version by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/824
  • chore(mcp-browser): add custom logger and addMiddleware by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/813
  • fix(ui-tars): action parser edge case action Chinese colon by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/825
  • docs(agent-tars): new home page by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/841
  • docs: refine readme by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/843
  • feat(ui-tars): add model availability check logic by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/894
  • feat(ui-tars): update volcano engine FaaS url by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/895
  • feat(ui-tars): update model check logic by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/899
  • feat(remote-browser): support headful browser with VNC control by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/898

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.2.1...v0.2.2

- TypeScript
Published by github-actions[bot] 11 months ago

https://github.com/bytedance/ui-tars-desktop - πŸš€ Introducing Agent TARS CLI

image

Agent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product.
It primarily ships with a CLI and Web UI for usage. It aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world MCP tools.

πŸ“£ Just released: Agent TARS Beta - check out our announcement blog post!

https://github.com/user-attachments/assets/772b0eef-aef7-4ab9-8cb0-9611820539d8


Booking Hotel Generate Chart with extra MCP Servers
Instruction: I am in Los Angeles from September 1st to September 6th, with a budget of $5,000. Please help me book a Ritz-Carlton hotel closest to the airport on booking.com and compile a transportation guide for me Instruction: Draw me a chart of Hangzhou's weather for one month

For more use cases, please check out #842.

Core Features

  • πŸ–±οΈ One-Click Out-of-the-box CLI - Supports both headful Web UI and headless server) execution.
  • 🌐 Hybrid Browser Agent - Control browsers using GUI Agent, DOM, or a hybrid strategy.
  • πŸ”„ Event Stream - Protocol-driven Event Stream drives Context Engineering and Agent UI.
  • 🧰 MCP Integration - The kernel is built on MCP and also supports mounting MCP Servers to connect to real-world tools.

Quick Start

```bash

Luanch with npx.

npx @agent-tars/cli@latest

Install globally, required Node.js >= 22

npm install @agent-tars/cli@latest -g

Run with your preferred model provider

agent-tars --provider volcengine --model doubao-1-5-thinking-vision-pro-250428 --apiKey your-api-key agent-tars --provider anthropic --model claude-3-7-sonnet-latest --apiKey your-api-key ```

Visit the comprehensive Quick Start guide for detailed setup instructions.

πŸ“š Resources

agent-tars-banner

What's Changed

See Full CHANGELOG

- TypeScript
Published by ulivz 11 months ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.10

image

This release adds a global deprecation warning for Agent TARS Desktop.

We have released a brand new new Agent TARS based on Seed1.5-VL, see https://agent-tars.com/beta . To reduce our maintenance burden and make it easier for the community to contribute to this repository, we have to say goodbye to the old Agent TARS Desktop and thank you for your contributions to the open source of TARS App in the past. πŸ‘‹πŸ»

Thanks to all the early core committers of Agent TARS Desktop: @sanyuan0704 @ycjcl868 @ulivz @skychx @helio9cn, and all the early contributors in the community represented by @le0zh @lynxlangya ❀️

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.2.1...Agent-TARS-v1.0.0-alpha.10

- TypeScript
Published by github-actions[bot] 11 months ago

https://github.com/bytedance/ui-tars-desktop - v0.2.1

πŸ› οΈ Improvements

  • Added support for the Response API. Image Refer to the Responses API guide of VolcEngine to apply for a model that supports the Responses API. Once configuration is complete, turn on the β€œUse Response API” switch to start using this feature. The transmission efficiency gains of the Responses API compared to ChatCompletion: Image
  • Improved the stability of remote operators
  • Fixed some UI issues

What's Changed

  • remove await for non async function by @QuentinLowe in https://github.com/bytedance/UI-TARS-desktop/pull/707
  • fix(ui-tars): optimize VNC scaling by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/719
  • feat(ui-tars): Support Responses API by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/714
  • fix(ui-tars-sdk): add timeout for response api by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/736
  • fix(ui-tars-sdk): add auth headers when delete response Id by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/742
  • ci(all): bump @rslib@core to 0.10.0 by @cjraft in https://github.com/bytedance/UI-TARS-desktop/pull/737
  • fix(ui-tars): fix the UI flickering issue after importing preset config by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/749
  • fix(ui-tars): global settings dialog add ScrollArea component by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/787
  • feat(ui-tars-sdk): add remote api's request id into log and error by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/788
  • fix(ui-tars): clear time cache when time expired by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/798
  • fix(ui-tars-sdk): fix the format of history messages by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/799
  • fix(browser-operator): goto URL wait no events by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/810
  • feat(ui-tars): update proxy server's endpoint by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/811

New Contributors

  • @QuentinLowe made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/707
  • @cjraft made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/728

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.2.0...v0.2.1

- TypeScript
Published by github-actions[bot] 11 months ago

https://github.com/bytedance/ui-tars-desktop - v0.2.0

πŸŽ‰ Free Remote Operator

We are excited to announce the launch of the free Remote Computer Operator and Remote Browser Operator features. No configuration is neededβ€”simply click to remotely control a computer or browser and enjoy an unprecedented level of convenience and intelligence.

Getting started with Remote Operator is easy: just download and install version 0.2.0 of UI-TARS-Desktop. On the new home page, you’ll find the β€œUse Remote Computer” and β€œUse Remote Browser” buttonsβ€”click either one to start your experience.

Notice: This feature is currently available only in Mainland China. It is not supported in other regions at this time. We appreciate your understanding and support.

home


Simply enter the GUI tasks you want to accomplish in the chat panel on the left, and the AI model will operate the remote device for you. Each session gives you 30 minutes of free remote access, and after the session ends, you can immediately start a new 30-minute free instanceβ€”explore and enjoy without limits.

fly


The right side will display a remote screen for the computer or browser. You can operate these remote devices just like your local machine using your mouse and keyboard.

openfile

Notice for Commercial Use:

Beyond the free trial, if you wish to deploy your own Remote Computer and Browser Agent, you can explore more on Volcano Engine's OS Agent Services via deployment links (in Chinese) Computer Use Agent and Browser Use Agent.


contributors: @skychx @ZhaoHeh @ycjcl868

- TypeScript
Published by github-actions[bot] 12 months ago

https://github.com/bytedance/ui-tars-desktop - v0.1.3

Key Changes

  • Added version detection functionality
  • Key historical records will be sent during continuous conversations within the same session
  • A reminder popup will appear if VLM Settings are not configured

Details

Version Detection

The new version optimizes the auto-update feature and adds support for version detection under Settings -> General:

Others

  • Key historical records will be sent during continuous conversations within the same session
  • A reminder popup will appear if VLM Settings are not configured

What's Changed

  • docs: fixed desktop quickstart issue https://github.com/bytedance/UI-… by @Taoran-Lu in https://github.com/bytedance/UI-TARS-desktop/pull/612
  • feat(sdk): support thinking controll for model invoking by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/616
  • fix(electron-updater): agent-tars update bug by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/652
  • chore: agent tars version by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/653
  • fix(app): update check and releaseNotes by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/659
  • feat(ui-tars): settings add update checker by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/660
  • feat(SDK): expose uiTarsVerison and update Basic Usage to click(w,h) correctly by @meme-dayo in https://github.com/bytedance/UI-TARS-desktop/pull/645
  • feat(ui-tars): add VLM dialog component to chat input by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/666
  • feat(ui-tars-sdk): support histroy context when agent running by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/665

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.1.2...v0.1.3

- TypeScript
Published by github-actions[bot] 12 months ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.9

What's Changed

  • release(apps): ui-tars-desktop support Doubao-1.5-thinking-vision-pro by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/604
  • feat(mcp): mcp-server-browser support cdpEndpoint by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/603
  • docs: fixed desktop quickstart issue https://github.com/bytedance/UI-… by @Taoran-Lu in https://github.com/bytedance/UI-TARS-desktop/pull/612
  • feat(mcp-browser): readme and add userDataDir, wsEndpoint, userAgent by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/610
  • feat(sdk): support thinking controll for model invoking by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/616
  • feat(mcp-servers): native support sse and mcp serving by high performance mcp-http-server by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/613
  • chore:(mcp-server): add smithery remote by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/629
  • feat: agent tars next by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/480
  • chore: release agent tars beta packages by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/635
  • feat(mcp-browser): vision mode add browservisionclick and fullPage by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/637
  • feat(agent-tars): enhance browser control strategy by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/639
  • ci: reorganize the project structure by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/640
  • release: @agent-infra/shared by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/641
  • ci(agent-tars): init release workflow by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/644
  • feat(agent-tars): add content extraction benchmark by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/646
  • fix(electron-updater): agent-tars update bug by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/652
  • chore: agent tars version by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/653

New Contributors

  • @Taoran-Lu made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/612

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.1.2...Agent-TARS-v1.0.0-alpha.9

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - UI-TARS-v0.1.2

Key Changes

  • Added support for our latest model: Doubao-1.5-thinking-vision-pro
  • Improved Assistant message display in chat interface for better readability
  • Fixed several known issues to enhance overall stability

Details

Added support for our latest model: Doubao-1.5-thinking-vision-pro

We are excited to announce support for the Doubao-1.5-thinking-vision-pro model. This upgrade brings significant performance improvements: - Enhanced reasoning capabilities - More precise coordinate positioning - Better instruction following

Improved Assistant message display

To provide a better user experience, we have comprehensively optimized message history display: - More user-friendly Message history presentation - Optimized message layout and styling - Enhanced readability and interaction experience

Bug Fixes

We have addressed several key issues affecting user experience: - Fixed control window disappearance during runtime - Resolved search engine icon display issues - Optimized window display for Windows systems - Improved update checker mechanism stability


Commits in this release

  • fix(ui-tars): fixed the icons were not displayed in the release app by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/588
  • fix(ui-tars): fix the issue where the widget disappears in release mode by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/592
  • feat(ui-tars): widget window displays a border on Windows systems by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/594
  • fix: update checker bug by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/597
  • feat(nutjs): avoid compression to use png format instead by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/599
  • Support doubao-1.5-thinking-vision-pro by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/598
  • feat(ui-tars): support assistant message style in history by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/600

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.1.1...v0.1.2

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - UI-TARS-v0.1.1

We are excited to announce the release of UI-TARS-Desktop v0.1.1!

This update primarily focuses on fixing known issues and improving overall system stability. Below are the key changes:

Key Changes

  • Significantly enhanced the stability of Browser Operator functionality.
  • Optimized ErrorMessage handling and display, and enhanced the logging system functionality.
  • Fixes for various known stability issues.


Highlights

Name Changes

To better align with product positioning, we have renamed Browser Use and Computer Use to Browser Operator and Computer Operator. Additionally, we’ve added detailed explanations on the homepage to help users better understand these features. (#571)

WelcomePage UI


Browser Operator Enhancements

This update greatly improves the stability of Browser Operator.

  • Browser Compatibility: We now support Chrome, Edge, and Firefox, along with their sub-versions (Beta, Dev, Canary). The system will sequentially detect local browsers in the order of Chrome β†’ Edge β†’ Firefox, resolving issues where the target browser could not be found. (#537, #541, #547)
  • Default Search Engine Configuration: Users can now configure their default search engine, ensuring smoother usage of Browser Operator, even in cases of network issues during initialization. (#553)
Search Engine
  • Cross-Platform Shortcuts: Added support for common shortcuts across different OS platforms and browsers (e.g., Select All, Copy, Paste). (#530, #560)
  • Screenshot Fixes: Fixed an issue where the browser page would flicker during screenshots. (#551)


ErrorMessage Optimization

We’ve refined the error-handling mechanisms throughout the app:

  • Error Classification: Reorganized and detailed error states across different stages of the app, and refactored the GUIAgentError type for clearer issue identification. (#534)
  • Log Optimization: Added support for persisting recent history logs, making it easier to troubleshoot and identify past issues. (#548)
  • UI Improvements: Enhanced the UI for ErrorMessage, enabling users and developers to locate issues more efficiently. (#571)
ErrorMessage

Other Updates and Fixes

  • Report Enhancements: Reports in HTML format now display model and conversation information. (#574)
new report html
  • Bug Fixes:
    • Fixed an issue where manually closing the browser in Browser Operator mode prevented relaunching. (#582)
    • Resolved a white-screen issue caused by empty action_type. (#526)
    • Fixed a white-screen issue when unsupported shortcuts were used with action_type. (#560)
    • Fixed a black-screen background issue when closing the app in full-screen mode. (#575)


Thank you for your continued support! πŸŽ‰


What's Changed

  • release(apps): ui-tars-desktop support UI-TARS-1.5 model by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/519
  • fix(document): docs/quick-start.md VLM Base URL by @quicksandznzn in https://github.com/bytedance/UI-TARS-desktop/pull/524
  • chore(ci): release pkgs by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/525
  • fix(ui-tars): handle empty action_type to prevent white page by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/526
  • fix(agent-tars): set highlight div backgroundColor to transparent. by @youngjuning in https://github.com/bytedance/UI-TARS-desktop/pull/500
  • fix(ui-tars): add arrow hotkey actions for operators (#528) by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/530
  • feat(ui-tars): browser-finder support chrome and edge by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/537
  • chore(ci): update bugreportuitarsdesktop.yml by @helio9cn in https://github.com/bytedance/UI-TARS-desktop/pull/540
  • refactor(browser): refactor chrome-paths error by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/541
  • fix(agent-tars): implicitly chat session by @knoxnoe in https://github.com/bytedance/UI-TARS-desktop/pull/494
  • feat(browser): add firefox-paths and browser-use support firefox by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/547
  • feat(ui-tars): refact log files management by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/548
  • fixed page blinking caused by viewport changes when executing screenshot in Puppeteer by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/551
  • fix setting.md by @laoguodong in https://github.com/bytedance/UI-TARS-desktop/pull/550
  • feat(ui-tars): format error status and messages by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/534
  • docs(readme): add ask deepwiki by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/555
  • feat(action-parser): add support for format in action parser by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/556
  • fix(ui-tars): make error message expandable by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/554
  • feat(ui-tars): support costomize use's search enging preference at Br… by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/553
  • chore(mcp-client): remote pkg type module by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/546
  • fix(agent-tars): share reporter not work by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/558
  • fix(browser): add shortcut key support to the browser. by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/560
  • docs: readme github-trending by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/562
  • fix(browser-mcp): element index validation to properly handle zero index in browser tools by @falconlee236 in https://github.com/bytedance/UI-TARS-desktop/pull/567
  • feat(ui-tars): add operator desc in the welcome page and update the ErrorMessage UI by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/571
  • feat(visualizer): report html show model detail and actions by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/574
  • fix(ui-tars): where closing an Electron window in fullscreen mode leaves a black window by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/575
  • fix(browser): where the browser does not relaunch after being manually closed by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/582

New Contributors

  • @quicksandznzn made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/524
  • @laoguodong made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/550
  • @falconlee236 made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/567

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.1.0...v0.1.1

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - UI-TARS-v0.1.0

What's Changed

  • feat: UI-tars-1.5 by @ZhaoHeh @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/502
  • fix(ui-tars): x64 and arm64 pkg by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/514
  • fix(ui-tars): x64 bundle bug by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/513
  • feat(ui-tars): local browser availability detection by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/509
  • docs(ui-tars): update name for VLM by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/517
  • fix(ui-tars): clear history in new session by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/518

What's Changed

  • fix: apps lack app-update.yml by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/507
  • release(ui-tars): universal apps by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/508
  • feat: UI-tars-1.5 by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/502
  • chore(ui-tars): update docs by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/512
  • fix(ui-tars): x64 and arm64 pkg by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/514
  • fix(ui-tars): x64 bundle bug by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/513
  • feat(ui-tars): local browser availability detection by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/509
  • docs(ui-tars): update name for VLM by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/517
  • fix(ui-tars): clear history in new session by @skychx in https://github.com/bytedance/UI-TARS-desktop/pull/518

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.9...v0.1.0

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.8

What's Changed

  • feat(agent-tars): support streamable-http mcp server by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/489
  • feat: Added a test feature for Model Provider by @le0zh in https://github.com/bytedance/UI-TARS-desktop/pull/478
  • fix(agent-tars): mainWindow.webContents typeError: Object has been destroyed by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/482
  • fix: the click event of the modal close button becomes ineffective by @knoxnoe in https://github.com/bytedance/UI-TARS-desktop/pull/487
  • fix(agent-tars): execute write_file event always logger file error by @fix-echo in https://github.com/bytedance/UI-TARS-desktop/pull/486
  • fix(agent-tars): correct typo in FIXME comment regarding MCPToolResul… by @youngjuning in https://github.com/bytedance/UI-TARS-desktop/pull/490
  • fix(agent-tars): streamable http mcp client sync from official repo by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/493
  • chore(agent-tars): use streamable-http mcp sdk by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/505

image

New Contributors

  • @knoxnoe made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/487
  • @fix-echo made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/486
  • @youngjuning made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/490

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.8...Agent-TARS-v1.0.0-alpha.8

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - UI-TARS-v0.0.9

What's Changed

  • docs: update README for UI-TARS-1.5 by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/504
  • feat(ui-tars): add auto-updater by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/503
  • release(apps): ui-tars and agent-tars by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/506

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.8...v0.0.9

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - UI-TARS-v0.0.8

What's Changed

Features

  • feat(action-parser): add action parser supporting for new format by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/234

Bug Fixes

  • fix(ui-tars): actionInputs be null when coordinates has value 0 (clos… by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/449
  • feat(ui-tars): add ui-tars adb operator for cli by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/164

Miscellaneous

  • chore(ui-tars): update cli README to show adb operator demo by @ZhaoHeh in https://github.com/bytedance/UI-TARS-desktop/pull/401
  • Update CONTRIBUTING.md by @KPCOFGS in https://github.com/bytedance/UI-TARS-desktop/pull/363
  • docs: image url error by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/190
  • docs: README.md by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/254
  • chore: fix setting dead links and add deployment guide ref by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/312
  • chore: add issue templates by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/325 and https://github.com/bytedance/UI-TARS-desktop/pull/440

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.7...v0.0.8

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.7

[!TIP] Check out our new Quick Start documentation: https://agent-tars.com/doc/quick-start Check out our new MCP documentation: https://agent-tars.com/doc/mcp

What's Changed

Features

  • MCP servers settings by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/415 Setting | Video :-: | :-: image |

  • Local browser search (close: #333) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/414 , and add sogou search engine by @yokingma in https://github.com/bytedance/UI-TARS-desktop/pull/451

Setting | Video :-: | :-: image | full video

  • New search provider searxng #326 by @le0zh in https://github.com/bytedance/UI-TARS-desktop/pull/372 and introduce search servcie connection test by @le0zh in https://github.com/bytedance/UI-TARS-desktop/pull/402
  • Welcome screen (close: #460) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/461 with some other App experience enhancements
    • hide canvas panel by default (close:#453) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/454
    • remember the collapsed state of the sidebar (close: #453) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/455
    • Support reset setting (close: #429) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/456
    • Add about and manually check updates menu (close: #349) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/332

Bug Fixes

  • fix(agent-tars): new session should be added to the top (close: #356) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/424
  • fix(build-script): windows exec pnpm run build error by @sunshinego12138 in https://github.com/bytedance/UI-TARS-desktop/pull/369
  • fix(agent-tars): setting state not sync (close: #421) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/425
  • fix(agent-tars): greeter should not respond markdown or html format (close: #284) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/459
  • fix(ui): implement app drag functionality :bug: by @lynxlangya in https://github.com/bytedance/UI-TARS-desktop/pull/391
  • fix(agent-tars): mcp servers cleanup when windows all closed by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/396
  • fix(agent-tars): log sequence (close: #361) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/400
  • fix(agent-tars): correct spelling errors and code consistency issues by @QuietlyChan in https://github.com/bytedance/UI-TARS-desktop/pull/416

Miscellaneous

  • refactor(agent-tars): merge redundant setting constants across threads by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/457
  • refactor(agent-tars): mcp servers settings form by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/444
  • chore(agent-tars): fix ci type check error and set default search engine to local browser search by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/445
  • chore(agent-tars): add mcp config help link by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/446
  • ci: update issue template by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/440
  • ci: add pull request template by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/458

New Contributors

  • @sunshinego12138 made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/369
  • @le0zh made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/372
  • @QuietlyChan made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/416
  • @yokingma made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/451

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.6...Agent-TARS-v1.0.0-alpha.7

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.6

[!TIP] Check out our new announcement: Thank You for Your Support + Updates on Model Compatibility Check out our new blog: MCP Brings a New Paradigm to Layered AI Application Development

What's Changed

Features

  • Support DeepSeek model provider by @lynxlangya in https://github.com/bytedance/UI-TARS-desktop/pull/350

image

  • Highlight browser and fixed MCP browser screenshot issue by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/346

image

  • Log file rotation (close: #360) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/359

Bug Fixes

  • Probabilistic plan anomaly on gpt-4o (close: #273, #368, #374) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/373
  • App updater does not work by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/328 https://github.com/bytedance/UI-TARS-desktop/pull/329 https://github.com/bytedance/UI-TARS-desktop/pull/341
  • Should not open external links within app (close: #379) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/380
  • Report white screen (close: #347) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/348
  • Share bugs by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/300

Misnouncelles

  • refactor(agent-tars): too call log by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/351
  • chore: fix setting dead links and add deployment guide ref by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/312
  • chore: add issue templates by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/325
  • chore: update CONTRIBUTING.md by @KPCOFGS in https://github.com/bytedance/UI-TARS-desktop/pull/363
  • chore: typos by @omahs in https://github.com/bytedance/UI-TARS-desktop/pull/322

New Contributors

  • @omahs made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/322
  • @KPCOFGS made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/363
  • @lynxlangya made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/350

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.5...Agent-TARS-v1.0.0-alpha.6

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.5

What's Changed

Featues

  • Give users better feedback when encountering runtime errors in Main Process (close: #240, #248) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/292

Bug Fixes

  • Fixed an issue where Azure OpenAI Provider was not working properly (close: #290) by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/291
  • fix(agent-tars): custom model name should keep state (close: #285οΌ‰ by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/286
  • fix(agent-tars): cannot catch error within askLLMTool (close: #288οΌ‰ by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/289

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.4...Agent-TARS-v1.0.0-alpha.5

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.4

What's Changed

Features

  • feat(agent-tars): support "view logs" for trouble shooting by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/269

| Open Log | Log Window | | --- | --- | | image | image |

  • feat(agent-tars): make greeter response shorter by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/210
  • feat(agent-tars): refactor setting icon default display position by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/266
  • feat: enhance log for llm providers and settings by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/275

Bug Fixes

  • fix(agent-tars): all existing llm setting issues by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/276
    • Closes: #257
    • Closes: #259
    • Closes: #261
    • Closes: #270
    • Closes: #271
    • Closes: #272
    • Closes: #274
  • fix: titlebar cannot drag by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/260

Enhancements

  • refactor(agent-tars): title style by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/255
  • refactor(agent-tars): increase the size of the startup window by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/256
  • refactor(agent-tars): enhance markdown font rendering by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/258
  • refactor(agent-tars): increase logo size by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/265
  • docs: README.md by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/254

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.3...Agent-TARS-v1.0.0-alpha.4

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.3

What's Changed

  • docs: small fix for the typo by @jimone1 in https://github.com/bytedance/UI-TARS-desktop/pull/249
  • fix(agent-tars): browser-use mcp need MacOS accessibility by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/250
  • feat(tool): browser search bing engine & app updater by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/253

New Contributors

  • @jimone1 made their first contribution in https://github.com/bytedance/UI-TARS-desktop/pull/249

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.2...Agent-TARS-v1.0.0-alpha.3

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.2

What's Changed

  • fix(agent-tars): browser-use mcp need MacOS accessibility by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/250
  • feat: settings store by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/238
  • fix(mcp): client add default description avoid err by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/239
  • fix(agent-tars): share serialize error with html artifacts by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/241
  • docs: add introduction blog and showcase link by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/245
  • docs: support brew install by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/246
  • fix(agent-tars): claude 3.7 model name typo by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/247

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/Agent-TARS-v1.0.0-alpha.1...Agent-TARS-v1.0.0-alpha.2

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - Agent-TARS-v1.0.0-alpha.1

What's Changed

  • docs: image url error by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/190
  • Agent TARS by @ulivz in https://github.com/bytedance/UI-TARS-desktop/pull/213
  • feat: support trvily search by @sanyuan0704 in https://github.com/bytedance/UI-TARS-desktop/pull/231
  • Chore: add agent tars banner and update README.md by @helio9cn in https://github.com/bytedance/UI-TARS-desktop/pull/235
  • fix: quick start img crash by @sanyuan0704 in https://github.com/bytedance/UI-TARS-desktop/pull/236
  • feat(tool): add duckduckgo search for default by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/232
  • fix: bundle bug & browser click flash by @ycjcl868 in https://github.com/bytedance/UI-TARS-desktop/pull/237

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.7...Agent-TARS-v1.0.0-alpha.1

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.7

Features

  • feat: support operator-browserbase (#132)

Bugfix

  • fix(app): electron build issue & tweak sdk snapshot quality (#188)
  • fix(operator): macos cannot type (#126)

Chores

  • fix(app): native module deps build and reduce 28% bundle size (#181)
  • refactor(app): migrate to apps/desktop monorepo (#177)
  • refactor(sdk): screenshot only return base64 and scaleFactor (#171)
  • chore(sdk): allow custom factors via parseBoxToScreenCoords api (#162)

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.6...v0.0.7

- TypeScript
Published by github-actions[bot] about 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.6

Features

  • feat: add ui-tars GUI Agent SDK (#110), internal and external applications refactor the GUI Agent logic using the SDK doc, computer use implemented via SDK-based CLI:

Bugfix

  • fix(operator): typing and key input fail (#112) @5101good
  • fix(bug): ensure screen capture uses primary display source (#117) @skychx

Chores

  • feat(visualizer): reduce html report size (#119) @skychx
  • tweak(ux): close Settings Window after saving (#115) @ZhaoHeh
  • feat: enable easy copying of images to clipboard (#114) @Dugyu
  • feat(renderer): add a strong prompt when the report needs to be uploaded (#105) @ulivz

Full Changelog: https://github.com/bytedance/UI-TARS-desktop/compare/v0.0.5...v0.0.6

- TypeScript
Published by github-actions[bot] over 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.5

Features

  • feat: UTIO (UI-TARS Insights and Observation), detail (#60) @ulivz
  • feat: setting preset, detail (#61) @ulivz

Bugfix

  • fix(windows): windows fails to handle events when the dock bar is opened after being closed (#100) @ycjcl868
  • fix(share): not use system picker (#101) @ycjcl868

Chores

  • refactor(ipc-bridge): replace zutron to trpc-like ipc bridge (#94) @ycjcl868

- TypeScript
Published by github-actions[bot] over 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.4

Features

  • feat(share): add screen recording video sharing (#77) @ycjcl868

| Image | Video | | :---: | :---: | | |

Bugfixes

  • fix(actionParser): no action text return null not error (#73)
  • fix(screenMarker): action text screen marker not show for vlm (#80)

Chores

  • chore(reporter): reduce about 20M for package size (#93)
  • refactor(SoM): setOfMarks Overlays unify into setOfMarksOverlays function (#82)
  • refactor: enable moduleResolution: bundler to avoid ts-ignore (#78) @ulivz

- TypeScript
Published by github-actions[bot] over 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.3

  • feat(ui): full screen water flow video (#55)
  • feat(hitl): add human-in-the-loop, return control to human video (#55)
  • feat(main): add app autoUpdate #55

- TypeScript
Published by github-actions[bot] over 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.2

  • feat: support osx app sign (#17) @ycjcl868
  • fix(settings): create window twice not work (#51)
  • feat(vlmProvider): vLLM support (#51)
  • fix(action_parser): null values while parsing action inputs (#28) @prateekgarg08
  • style(ui): add action content (#35)
  • fix(agent): abort not break immediately (#49)

- TypeScript
Published by github-actions[bot] over 1 year ago

https://github.com/bytedance/ui-tars-desktop - v0.0.1

  • feat(execute): support hotkey PageUp and PageDown #6
  • fix(execute): type workaround for unexpected newline in content value (#6) @ulivz @ycjcl868
  • fix(execute): windows scaleFactor not work (#2)
  • fix(execute): scroll up/down not work (#15)
  • fix(execute): drag not work (#26)
  • test(e2e): add e2e test case (#5)

- TypeScript
Published by github-actions[bot] over 1 year ago