I built DevClaw, an OpenClaw plugin that turns each Telegram group into an isolated, autonomous dev team: planner/orchestrator, DEVs, and QA all running on their own. I use it for all my development now. Issues on GitLab/GitHub are the single source of truth, and three things compound to save around 70% on tokens: model tiering (Haiku for typos, Opus for architecture), session reuse across tasks, and token-free scheduling that burns zero LLM calls for orchestration.
Please try it and give some feedback. Also keen to hear from anyone running autonomous coding agents, especially what you’ve found works for model selection and session management.
Code’s all here: https://github.com/laurentenhoor/devclaw
vovap4ely2 hours ago
This is insanely good, started using it yesterday, thank you! Quick comments: supergroup + threads setup seems to misroute some replies to General, and I’d love an optional flow where the orchestrator returns at the end with a “done + summary, please review” message. Many thnx, great job shipping this!