litgpt
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
kani
kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)
oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
gpt-researcher
LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.
tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
guardrails
VSCode extension to help developers set up guardrails around their functions, by helping them disambiguate purpose statements.
distilabel
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
https://github.com/modelscope/data-juicer
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
https://github.com/lancedb/lance
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
cambrian
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
linear-relational
Linear Relational Embeddings (LREs) and Linear Relational Concepts (LRCs) for LLMs in PyTorch
opennmt-py
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
ml-keyframer
Keyframer: Empowering Animation Design Using Large Language Models
https://github.com/adaptivemotorcontrollab/amadeusgpt
We turn natural language descriptions of behaviors into machine-executable code
tamingllms
Taming LLMs: A Practical Guide to LLM Pitfalls with Open Source Software
symmetry-cli
The client for the Symmetry peer-to-peer inference network. Enabling users to connect with each other, share computational resources, and collect valuable machine learning data.
boilerbot
Official Open-Source Implementation of BoilerBot: A Reliable Task-Oriented Chatbot Enhanced with Large Language Models.
gemgpt
Explore the power of Gemma model with GemGPT, a project leveraging AI for innovative solutions. Join us in shaping the future of AI!
token-wars-dataviz
A data visualisation in `matplotlib` of the number of parameters in major LLMs as well as the number of tokens of text they were trained on.
https://github.com/epsilla-cloud/vectordb
Epsilla is a high performance Vector Database Management System
https://github.com/amazon-science/refchecker
RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.
https://github.com/bminixhofer/tokenkit
A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.
https://github.com/google-deepmind/simulation_streams
Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.
keras-gpt-copilot
Integrate an LLM copilot within your Keras model development workflow
https://github.com/spencerpresley/academicmetrics
AI-powered toolkit for analyzing and classifying academic research publications using LLMs and automated data collection. Output options: Mongodb database via providing your databse url. Json. Excel spreadsheet. See README for the quick setup, see documentation for implementation details.
https://github.com/deepset-ai/haystack-demos
Fully working applications that demonstrate how to use Haystack to implement various use cases
https://github.com/amazon-science/mezo_svrg
Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"
https://github.com/adaptivemotorcontrollab/llavaction
https://github.com/citiususc/blinkg
BLINKG: Benchmark for LLM-Integrated Knowledge Graph Generation
https://github.com/astorfi/llm-alignment-project
A comprehensive template for aligning large language models (LLMs) using Reinforcement Learning from Human Feedback (RLHF), transfer learning, and more. Build your own customizable LLM alignment solution with ease.
https://github.com/ahwang16/grounded-intuition-gpt-vision
Resources for Grounded Intuition of GPT-Vision's Abilities with Scientific Images
https://github.com/astorfi/large-scale-ai-blueprint
A comprehensive guide designed to empower readers with advanced strategies and practical insights for developing, optimizing, and deploying scalable AI models in real-world applications.
https://github.com/pixeltable/pixelagent
Pixelagent — Build your own stateful agent framework
https://github.com/amazon-science/factual-confidence-of-llms
Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"
semexp-thesis
The Semantic Workspace: Augmenting Exploratory Programming with Integrated Generative AI Tools [Master's Thesis]
fuzi.mingcha
夫子•明察司法大模型是由山东大学、浪潮云、中国政法大学联合研发，以 ChatGLM 为大模型底座，基于海量中文无监督司法语料与有监督司法微调数据训练的中文司法大模型。该模型支持法条检索、案例分析、三段论推理判决以及司法对话等功能，旨在为用户提供全方位、高精准的法律咨询与解答服务。
hackathon-leaderboard
Automated Leaderboard System for Hackathon Evaluation Using Large Language Models
https://github.com/aiplanethub/ai-stacks
Explore a variety of use cases and example stacks powered by LLMs, seamlessly integrated into the GenAI Stack platform.
https://github.com/aielte-research/hacksynth
LLM Agent and Evaluation Framework for Autonomous Penetration Testing
llmstack
No-code multi-agent framework to build LLM Agents, workflows and applications with your data
https://github.com/asanchezyali/library
llms4subjects
The official SemEval 2025 Task 5 - LLMs4Subjects - Shared Task Dataset repository
https://github.com/chonghin33/semantic-logic-system-1.0
Semantic Logic System v1.0 — A modular prompt-based semantic framework for LLMs.
lcm-1.13-whitepaper
This project contains the original white paper for Language Construct Modeling (LCM) v1.13, authored by Vincent Shing Hin Chong. It introduces a novel framework for prompt-layered semantic control in large language models (LLMs), built upon the Meta Prompt Layering (MPL) structure. LCM formalizes a modular system of prompt orchestration, enabling
interactive-learning-duo
Unlock Your Coding Potential: Explore, Learn, and Code with Our Interactive Python and SQL ChatBot!
https://github.com/safellmhub/hguard-go
Guardrails for LLMs: detect and block hallucinated tool calls to improve safety and reliability.
https://github.com/OpenDCAI/DataFlow
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
https://github.com/alan-turing-institute/prompto
An open source library for asynchronous querying of LLM endpoints
awesome-llms
🤓 A collection of AWESOME structured summaries of Large Language Models (LLMs)
https://github.com/chirayu-tripathi/mongodb-querifier
Improving LLMs MongoDB query generation capability with the help of advanced retrieval augmented generation.
llmswitcher
Routes to the most performant and cost efficient LLM based on your prompt [ 🚧 WIP ]
https://github.com/cosmaadrian/strawberry-problem
Official repository for "The Strawberry Problem 🍓: Emergence of Character-level Understanding in Tokenized Language Models"
scisum
Resources for the paper Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals? (ACL 2024).
llms4subjects
The official GermEval 2025 Task - LLMs4Subjects - Shared Task Dataset Repository
xrayglm
🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.
mdi-llm
Implementation of Model-Distributed Inference for Large Language Models, built on top of LitGPT
ai-for-grant-writing
A curated list of resources for using LLMs to develop more competitive grant applications.
backdoorllm
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
gptlint
A linter with superpowers! 🔥 Use LLMs to enforce best practices across your codebase.
curlora
The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.
https://github.com/asanchezyali/talking-avatar-with-ai
This project is a digital human that can talk and listen to you. It uses OpenAI's GPT to generate responses, OpenAI's Whisper to transcript the audio, Eleven Labs to generate voice and Rhubarb Lip Sync to generate the lip sync.
fed-rag
A framework for fine-tuning retrieval-augmented generation (RAG) systems.
https://github.com/alexisvassquez/juniper2.0
Conversational AI model and educational tool
https://github.com/dimits-ts/synthetic_moderation_experiments
Experiments relating to synthetic LLM user-agents and LLM facilitators in online discussions
awesome-llm-papers.github.io
A curated collection of the most impactful papers, tools, and resources on Large Language Models (LLMs). Continuously updated to help researchers, developers, and enthusiasts stay on top of LLM advancements.
self-refine
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.