Mutex from OpenAI Astra Hackathon lets multiple coding agents share one repo without collisions
gabrielchua · x · 2026-09-14
A team built Mutex at the OpenAI Astra Hackathon in Singapore to solve a real pain point: multiple developers running multiple coding agents against one shared repository.
- Mutex lets teams chat, queue, and refine code requests, executing one coding task per project at a time so agents never collide.
- Tasks run locally on the requester's machine via a local Companion, with the system managing refinements, validation, Git synchronization, diffs, previews, and rollback.
- The team used Astra throughout development — from architecture reasoning (deterministic multi-user scheduling, real-time state management, auth) to tracing bugs across browser, server, database, desktop app, and local repos.
The project is currently open for hackathon voting.
More from coding & agent
- Astra-built racer spawns a ghost of your last lap every time you finish one — LexicalLegend · 2026-09-14
- Alchemy Console ships a visual UI for browsing and deleting Alchemy cloud resources — samgoodwin89 · 2026-09-14
- Edit video for free: pair Codex Astra 6 with the free DaVinci Resolve 19.1 — alexcovo_eth · 2026-09-14
- Multi-agent RAG lesson: structured JSON schemas plus runtime verification to stop hallucinated API calls — kashifmanzoor · 2026-09-14
- A security layer for agent infra: replay attacks in sandboxes, learn from them — wandb · 2026-09-14
- Muse Spark 1.3 wins fans: browser agent files insurance claims faster than humans — alexandr_wang · 2026-09-14