ART m4ll0k · COMPLETED
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
github.com/m4ll0k/ART · ★ 0 · Forks 0 · Size 49.6 MB
SUMMARY
Technologies 21
Scored 21
Observed 21
Practices 6
Evidence 22
Skips 0
COVERAGE
Analyzed 393 files · 745 commits · 0 API calls
TECHNOLOGIES & DEPTH
Shell LANGUAGE Depth 70
10 files · PRODUCTION
JavaScript LANGUAGE Depth 70
1 files · PRODUCTION
JSON LANGUAGE Depth 70
10 files · PRODUCTION
Markdown LANGUAGE Depth 70
25 files · PRODUCTION
TOML LANGUAGE Depth 70
4 files · PRODUCTION
YAML LANGUAGE Depth 70
10 files · PRODUCTION
Python LANGUAGE Depth 70
249 files · PRODUCTION
uv BUILD_TOOL Depth 80
1 files · CONFIGURATION
npm BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
pnpm BUILD_TOOL Depth 80
1 files · CONFIGURATION
FastAPI FRAMEWORK Depth 58
1 files · PRODUCTION
NumPy LIBRARY Depth 78
7 files · PRODUCTION
Pydantic LIBRARY Depth 81
38 files · PRODUCTION
RabbitMQ MESSAGE_BROKER Depth 65
1 files · CONFIGURATION
Redis CACHE Depth 53
1 files · CONFIGURATION
Requests LIBRARY Depth 70
3 files · PRODUCTION
TypeScript LANGUAGE Depth 81
6 files · PRODUCTION
Uvicorn LIBRARY Depth 62
2 files · PRODUCTION
pandas LIBRARY Depth 66
2 files · PRODUCTION
pytest TESTING Depth 66
3 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2025-03-10
Last commit 2025-07-30
Active months 5
Commits 745