TRL and OpenEnv now let you train coding agents end to end with opencode
SergioPaniego · x · 2026-07-24
- The post says you can now train your own coding agents with TRL + OpenEnv, starting from opencode.
- The new setup adds end-to-end support for training agent harnesses: TRL launches the agent inside an OpenEnv session, captures its trace, reconstructs training samples, and trains with AsyncGRPO.
- OpenEnv acts as the OpenCode harness environment plus a transparent proxy that records each turn’s token IDs and logprobs.
- The key idea is to train the actual agent loop “as is,” so the policy learns from the exact tokens it produced while using tools.
- They also mention a self-contained example using a local subprocess sandbox and DeepCoder problems, validated on Qwen3-8B.
Related event: TRL and OpenEnv Enable Custom Agent Harness Training(4 posts)→
More from coding & agent
- Coco adopts GUM proposition-evidence memory for better in-memory search — EchoShao8899 · 2026-07-24
- A small agent-name joke lands inside the AI community — huangyun_122 · 2026-07-24
- Open-source package normalizes coding-agent sessions into one standard trajectory format — carsonfarmer · 2026-07-24
- Vercel lets Workflows pin state to a region, with AI Gateway limits coming soon — cramforce · 2026-07-24
- ChatGPT Voice tips warn users to offload work into new threads and expect context resets — jxnlco · 2026-07-24
- 30 open-source AI repos covering agents, local inference, and workflow automation — Shruti_0810 · 2026-07-24