riyanshibohra/OnsetLab

Tool-calling AI agents that run locally.

47
/ 100
Emerging

Implements a hybrid REWOO/ReAct architecture where a router classifies queries, a planner generates structured execution plans with auto-generated tool rules from JSON schemas, and an executor resolves dependencies—falling back to iterative reasoning if planning fails. Integrates with MCP (Model Context Protocol) servers for external tools like GitHub, Slack, and Notion, while supporting any Ollama-compatible model from 3B-7B parameters.

Available on PyPI.

Maintenance 10 / 25
Adoption 10 / 25
Maturity 18 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Feb 18, 2026

Monthly downloads

68

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/riyanshibohra/OnsetLab"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.