aisync: one local hub for rules and coordination across AI coding agents
If you run Claude Code, Codex and Cursor on the same machine, each tool keeps its own rules, two of them can edit the same file, and nothing records who did what. aisync is a small local hub that tries to fix those three
If you run Claude Code, Codex and Cursor on the same machine, each tool keeps its own rules, two of them can edit the same file, and nothing records who did what. aisync is a small local hub that tries to fix those three things.
What it is
aisync keeps everything in ~/.ai-sync, which is a plain git repo. It is agent-agnostic at its core. It ships native hooks for Claude Code, Codex and Cursor, and other agents can use the same hub through a CLI, an MCP server or shared instruction files.
What it does
- Shared rules. Rules are shared across tools and synced with a 3-way merge, so a rule written once reaches every agent.
-
A verifiable journal. Agent activity is written to a hash-chained journal.
aisync verifychecks the chain for edits. - File claims. An agent declares the files it is about to touch. An overlapping claim is detected and reported with exit code 3, so two agents can avoid editing the same file.
- Mid-session news. Where hooks are available, an agent is told what other agents did while it was working.
Limits
File claims are cooperative, not OS-level locks: agents have to use the claim protocol. Hash-chain verification detects changes to recorded events. It does not prove that every claimed action happened.
Try it
It is MIT licensed, needs Python 3.11 or newer and has no runtime dependencies.
pip install aisync-cli
Source and docs: https://github.com/MaxonT/aisync
Website: https://maxont.github.io/aisync/
Originally published by Dev.to AI. Aggregated on AIWithGhost for educational purposes β full credit and traffic to the original publisher.