Pinned Loading

1. multi-agent-coding-system multi-agent-coding-system Public

   Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.

   Python 1.3k 170

2. terminal-bench-rl terminal-bench-rl Public

   GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.

   Python 323 21

3. Orca-Agent-RL Orca-Agent-RL Public

   Scaling Coding-Agent RL to 32x H100s. **Achieving 160% improvement** on Stanford's TerminalBench

   Python 89 12

4. calculator_agent_rl calculator_agent_rl Public

   Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.

   Python 65 6

5. tbench-agentic-data-pipeline tbench-agentic-data-pipeline Public

   Multi-agent synthetic data generation pipeline capable of generating and validating long horizon terminal/coding tasks for RL training

   Python 46 8

6. auto_agent_optimiser auto_agent_optimiser Public

   An AI Agent that automatically optimises other AI agents.

   Python 4 2