Highlighted
Open highlighted repo slot
Put your repository first
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Awesome
GitHub projects from awesome lists
Search awesome repositories
Search names, descriptions, topics, tags, and stacks, then tune results by ecosystem, freshness, health, and cross-list signal.
- Repos indexed
- 18,423
- Awesome lists tracked
- 132
- Current results
- 10
10 repos shown
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
GitHub topics
- Updated
- 2026-09-09
- Lists
- 2 list mentions
- First commit
- 2023-08-01
- History
- 7 history points
- License
- Apache-2.0
- Issues
- 566 open
15,554
stars
- Forks
- 1,669
- Commits
- 3,676 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
Orchestra-Research/AI-Research-SKILLs
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
AI dev
GitHub topics
- Updated
- 2026-06-16
- Lists
- 0 list mentions
- First commit
- 2025-11-03
- History
- 106 history points
- License
- MIT
- Issues
- 21 open
- Forks
- 915
- Commits
- 220 commits
- Star growth, last 7 days
- +227 +1.8%
- Commit velocity, last 7 days
- 0 0.0%
OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
AI dev
- Updated
- 2026-09-03
- Lists
- 1 list mention
- First commit
- 2025-03-10
- History
- 5 history points
- License
- Apache-2.0
- Issues
- 127 open
10,690
stars
- Forks
- 981
- Commits
- 1,353 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
adongwanai/AgentGuide
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成
AI dev
GitHub topics
- Updated
- 2026-09-04
- Lists
- 1 list mention
- First commit
- 2025-11-03
- History
- 1 history point
- License
- Unknown
- Issues
- 4 open
9,193
stars
- Forks
- 899
- Commits
- 202 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
GitHub topics
- Updated
- 2026-07-07
- Lists
- 1 list mention
- First commit
- 2025-02-02
- History
- 1 history point
- License
- Apache-2.0
- Issues
- 167 open
6,018
stars
- Forks
- 385
- Commits
- 237 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
Gen-Verse/OpenClaw-RL
OpenClaw-RL: Train any agent simply by talking
GitHub topics
- Updated
- 2026-05-23
- Lists
- 1 list mention
- First commit
- 2026-02-26
- History
- 104 history points
- License
- Apache-2.0
- Issues
- 75 open
5,683
stars
- Forks
- 608
- Commits
- 252 commits
- Star growth, last 7 days
- +12 +0.2%
- Commit velocity, last 7 days
- 0 0.0%
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
Stack
GitHub topics
- Updated
- 2026-09-06
- Lists
- 1 list mention
- First commit
- 2025-03-04
- History
- 1 history point
- License
- Apache-2.0
- Issues
- 2 open
5,174
stars
- Forks
- 806
- Commits
- 296 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
walkinglabs/hands-on-modern-rl
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
AI dev
GitHub topics
- Updated
- 2026-09-03
- Lists
- 1 list mention
- First commit
- 2026-04-10
- History
- 1 history point
- License
- NOASSERTION
- Issues
- 11 open
4,342
stars
- Forks
- 313
- Commits
- 758 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
SkyworkAI/Skywork-R1V
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
GitHub topics
- Updated
- 2026-07-29
- Lists
- 2 list mentions
- First commit
- 2025-03-16
- History
- 7 history points
- License
- MIT
- Issues
- 36 open
3,169
stars
- Forks
- 282
- Commits
- 284 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
GitHub topics
- Updated
- 2026-09-09
- Lists
- 1 list mention
- First commit
- 2024-10-25
- History
- 5 history points
- License
- Apache-2.0
- Issues
- 38 open
1,060
stars
- Forks
- 99
- Commits
- 1,776 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
