
Reinforcement-learning framework for training language agents on any harness
- Open source
- Open-source agent
- 5.9K GitHub stars
- AI models and LLM tooling

Reinforcement-learning framework for training language agents on any harness

Benchmarks LLM trading agents on news replayed by publication time, plus paper trading
Runs locallyLocal MCP server to check VRAM fit, manage models and delegate work to local LLM runtimes
Runs locallyFree challenge that checks agents' claims against signed receipts of their calls
Runs locallyLocal MCP server for addressing synthetic agent-environment state and checking provenance
Runs locallyPublic test arena where AI agents run stateful scenarios and earn signed scorecards
Not checked yetCompiler that merges many MCP servers and REST APIs into one lean tool endpoint
Runs locally