Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,455 results
Foundation Model for MineDojo
Emerging and experimental patterns for building with the Foundation Models framework
Foundation model benchmarking tool. Run any model on any AWS platform and benchmark for performance across instance type and serving stack options.
Playground examples to demonstrate Foundation Models Framework
This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html
MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.
Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
🚀Official Repository of Intelligent Remote Sensing Agents: A Survey
MiniMax M2.1, a SOTA model for real-world dev & agents.
Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.
[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"
Build agents that scale with a zero-cost abstraction.
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome
Video Search and Streaming Agent 🕵️♂️
Paving the way for open agents and AGI for all.
An agent benchmark with tasks in a simulated software company.
If you can read ~100 lines of Python, you understand agents.
[COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)
InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
24,540 repositories in the index in total.
