aisync
Local multi-agent hub for shared rules, coordination, and observability.
Read shared rules, optionally by topic (
rules).Add When/Do/Not rules with enforcement, plan, or judgment metadata (
rule_add).Append journal events such as dev logs, decisions, blockers, unblocks, rule changes, and notes (
log).Claim files or whole repos before editing and detect overlaps (
claim).Release all claims or one project’s claims (
release).Check what other agents did and which rules changed since last check (
news).View live progress, claims, blockers, and latest events (
status).Get rules clerk proposals for duplicates, uncited rules, budget issues, and gaps (
tidy).
Provides native hooks for Codex, enabling automatic context and news delivery at supported hook events plus access to aisync's coordination and journal commands.
aisync: Multi-Agent Context Management, Coordination & Observability
One local hub for developers working with multiple AI coding agents: share the right context, coordinate concurrent work, and verify what happened.
aisync is agent-agnostic at its core. It provides native hooks for Claude Code, Codex and Cursor, and exposes its hub to other agents through a CLI, MCP server, or shared instruction files. These three native integrations are not a limit on which agents can use aisync.
English · 中文 · 日本語 · 한국어 · Español · Français · Deutsch · Português · Русский · Website · Demo status board
Multiple coding agents should not have to work with isolated rules, conflicting file ownership, and disconnected histories.
aisync is a local, verifiable hub (~/.ai-sync/, a git repo) designed for multi-agent workflows:
Context management: share and 3-way-sync rules; load core context up front and inject relevant context on demand, including mid-session updates where hooks are available.
Multi-agent coordination: declare file claims, detect overlapping claims (exit code 3), release ownership, and surface blockers and other agents' activity.
Observability & verification: inspect agent activity, blockers, and health through the journal, status reports, and board;
aisync verifychecks the journal's hash chain for tampering.
File claims are cooperative, not OS-enforced locks: agents must use the claim protocol. Hash-chain verification detects an edited event or a deleted one that a later event points at; it does not detect deleting the last line(s) of the journal (tested on 0.2.10; keep the hub in git to catch that), and it does not prove every claimed action occurred.
Try it (needs uv; runs aisync demo on a throwaway hub in your temp folder with synthetic data, and your own hub is not touched):
uvx --from aisync-cli aisync demoWho it's for
Developers running two or more AI coding agents across one or multiple repositories—especially when agents work concurrently, hand tasks off, or need a shared record of decisions and blockers. aisync is not another coding agent or a task orchestrator: it is the shared context and coordination layer those agents can use.
Related MCP server: samskriti-project
See it
The Agent Swarm Floor
https://github.com/user-attachments/assets/f741ef6f-0c10-46f4-8c94-769c6e02d30e
Integrations: native hooks are not the compatibility boundary
Integration | Who can use it | What to expect |
Native hooks | Claude Code, Codex, Cursor | Automatic context and news delivery at supported hook events, plus access to aisync's coordination and journal commands |
MCP server | MCP-compatible agents | Exposes rules, rule additions, logging, claims, releases, news, status and tidy; an agent must invoke the tools |
CLI | Agents that can run shell commands | Direct access to hub operations such as |
Shared instruction files | Agents that read supported instruction files | Standing rules and context only; not automatic mid-session news or file-claim enforcement |
Compatibility is not equivalent to automatic integration. For agents without native hooks, features depend on the agent's MCP/CLI usage and configuration. aisync does not automatically intercept all edits or guarantee every agent will honor file claims.
Install
Give it to your AI. It reads the page, does a dry run first and asks before it changes anything:
Read https://maxont.github.io/aisync/install and install aisync for me.Or in a terminal. It installs with uv, pipx or pip and never edits your shell config:
curl -fsSL https://maxont.github.io/aisync/install.sh | bashNeeds Python 3.11+ and git, on macOS or Linux. Nothing else: aisync uses only the standard library.
📦 Or from a package manager. The command is still aisync:
pipx install aisync-cli # 🐍 PyPI (or: uv tool install aisync-cli)
npx @mingyang2026/aisync-cli --version # npm 0.2.9
brew install maxont/tap/aisync # 🍺 Homebrew tap (Python 3.14 first)
docker run --rm ghcr.io/maxont/aisync --version # 🐳 GHCR imageTwo agents, one file
A real terminal run: aisync demo (synthetic data), then two tools reach for the same file.
Step by step: how it works · the same demo hub as a
status board.
Multi-agent need | What aisync provides |
Context management | 3-way-synced rules, layered rule loading and relevant mid-session news via hooks |
Multi-agent coordination | Cooperative file claims and releases, overlap detection (exit 3), blockers and activity updates |
Observability & verification | Hash-chained event journal, |
aisync also does the rules part: one rules block copied into every tool's own rule file, synced 3-way, conflicts never overwritten.
Dogfooded: 6,700+ journal events on the author's own hub.
Why not just AGENTS.md?
Keep AGENTS.md for a repo's standing instructions. aisync sits beside it and covers what a single file cannot: the context that changes while agents work.
AGENTS.md | aisync | |
Scope | Standing instructions for agents working in a repo | A shared hub across configured agents and repositories |
When it is read | When a session starts | At start, and mid-session through hooks |
Who is editing what | Not covered | Cooperative claims: an overlap returns exit 3 to the caller |
Tamper evidence | Not provided by the file format | Hash-chained journal: |
Context per session | Whole file, every time | Triggered rules only: always-loaded rules 20,673 → 7,876 tokens* |
* Measured once on one author's own hub (2026-11-08), always-loaded rules before and after layered loading. One machine, not a benchmark: your numbers will differ. aisync tidy reports your own rule budget and uncited rules.
Use it
aisync demo # a throwaway hub with a synthetic two-week journal
aisync init # create ~/.ai-sync (or wherever AISYNC_HOME points)
aisync install-hooks # shows every tool config change as a diff, then asks
aisync watch & # event-driven sync loop (or run `aisync sync` by hand)What an agent does during a session:
aisync claim -a codex -p api -f app/payments/ -m "SDK upgrade" # 3 = taken
aisync log -a codex -p api -m "SDK 5.0, retries kept"
aisync rule add -a codex --when "changing an API" --do "add a contract test"
aisync release -a codex -p apiCommand | What it does |
| create the hub: shared rules, journal, config, local git repo |
| append one event ( |
| any agent adds a shared rule ( |
| rules not in the When/Do/Not shape / rewrite them by ID without losing a fact / which test or hook keeps each rule |
| say what keeps an existing rule: |
| rules clerk: likely duplicates, rules nobody cited lately, core layer over budget; proposals only, you tick them |
| prove a rules cleanup lost no hard fact (paths, numbers, commands, IDs) |
| optional habit list grown from past mistakes, injected into every session |
| push-time test gate: |
| import web-Claude events from the |
| Claude Code hook: one session per repo; denies an edit when another session holds the repo (opt-in, see below) |
| who holds which repo ( |
| a session's own git worktree: |
| serve the hub to any MCP agent over stdio ( |
| who is working on which files right now; overlap = exit 3 |
| what other tools did since this session last looked |
| entry point for Claude Code, Codex and Cursor hooks (reads hook JSON, never fails) |
| wire the hooks, seed the rules block, add the git |
| health, conflicts, claims, blockers, metrics (exit 1 when something needs you) |
| write the hub as one static HTML page: claims, blockers, who did what, timeline |
| read-only self-check: silent tools, commits without an |
| latest journal events |
| check the hash chain |
| run one sync cycle / the debounced, event-driven loop |
| rule on a rule conflict / clear failure counters after a pause |
| the throwaway hub shown above |
| print the version |
| this screen, or one command's options ( |
| check GitHub for a newer release and print the command that upgrades (uv, pipx, install.sh, brew or pip); it never installs by itself |
| check python, git, the hub folder and the journal chain (exit 1 on any failure) |
| print a shell completion script for bash, zsh or fish: |
New in 0.2.0: rules as interfaces, loaded in layers
A rules file grows until every session pays for it and nobody reads it. 0.2.0 treats a rule like an API:
When / Do / Not. Each rule is one line with a stable ID:
[R-087] When: <trigger>. Do: <action>. Not: <forbidden>.The why goes to the journal, not the rule.rule_spec = truerefuses anything else;rule lintlists misfits;rule rewritereshapes old rules by ID and refuses a rewrite that drops a path, number or command.Layers. Mark a tool copy
layer = "core": it carriescore_topicsin full and every other topic as one line. When a prompt or tool call touches a topic's keywords ([shelf]), the hook injects that topic once per session. On the author's own hub this cut the always-loaded rules from 20,673 to 7,876 tokens.A stable prefix.
progress_filemoves the live progress table out of the shared page, so the page stays byte-identical and prompt caches keep hitting.A clerk, not a janitor.
aisync tidyproposes (duplicates, uncited rules, budget overruns) and never edits; a replaced rule moves torules-archive.mdwith its ID, nothing is deleted.Any agent. Three doors: the AGENTS.md page, the CLI, and
aisync mcp(tools: rules, rule_add, log, claim, release, news, status, tidy). The core stays standard-library only; the MCP SDK is the optionalaisync-cli[mcp]extra.
How it works
A sync cycle is harvest (new git commits in watched repos become journal events, attributed by
their Agent: trailer) → rules (new entries in repos you list in rule_sources) → distribute
(3-way sync of the rules block into each tool file) → render (progress page) → flush (commit the
hub, optional push). Each step is isolated: one failure never blocks the others.
The rules block is synced 3-way. If only the truth changed, copies are overwritten (with a backup). If one copy was edited and nobody else changed anything, the edit is adopted everywhere. If both sides changed, nothing is overwritten: it becomes a conflict for you to resolve.
Reliability and observability: timeouts and retries with backoff on every git call, failure
isolation per step and per project, auto-pause after fail_threshold failures in a row with an
ALERT.md and a desktop notification, a per-cycle run log (state/runs.jsonl), hook call stats and
aisync status for all of it.
Configuration
~/.ai-sync/config.toml (set AISYNC_HOME to put the hub anywhere):
roster = ["claude-code", "codex", "cursor"] # tools `report` expects to hear from
scan_dirs = ["~/projects"] # every git repo inside is watched
rule_sources = [] # repos whose AGENTS.md "## Meta rule" feeds shared rules
remote = "" # e.g. "origin" to also push the hub
progress_file = "progress.md" # keep agents.md byte-stable; hooks inject progress at session start
rule_spec = true # rule add only accepts When/Do/Not rules
require_enforcer = false # true: every new rule names --enforced-by or --judgment-only
core_topics = ["Safety", "Meta"] # topic headings a layered copy carries in full
instincts_path = "" # optional habit file injected at session start
tidy_daily = false # the watcher starts one `aisync tidy --write` a day
tidy_usage_globs = [] # files whose R-### mentions count as a rule being used
gate_hook = false # opt-in: the git pre-push hook runs the test gate (gate.py)
guard_hook = false # opt-in: Claude Code runs the one-session-per-repo guard (guard.py)
web_inbox_secs = 0 # 0 = off; else poll the web-inbox branch this often
[shelf] # folded topic -> keywords that pull it into a session
Deploys = ["deploy", "terraform", "rollback"]
[[target]] # files carrying the shared-rules block
label = "claude-code"
path = "~/.claude/CLAUDE.md"
layer = "core" # optional: fold non-core topics, inject them on demandTo keep aisync watch running, start it from your login items, a systemd user unit or a launchd
agent that runs aisync watch; create ~/.ai-sync/STOP to stop it cleanly.
Opt-in features (all off by default). gate_hook, guard_hook and web_inbox_secs change behavior outside the hub,
so nothing turns on until you set them. The guard can deny edits: if a session is locked out, run
aisync lease status, and once the holder session has ended, aisync lease release --key <repo>. To undo the guard,
delete the PreToolUse and SessionEnd entries whose command ends in guard from ~/.claude/settings.json.
Standing on the shoulders of
aisync: Multi-Agent Context Management, Coordination & Observability. AGENTS.md was the starting idea.
Project | How it shaped aisync |
The starting idea: one plain-text instruction file every agent reads, no SDK. aisync keeps that shape for shared rules (one rules block copied into each tool's own AGENTS.md / CLAUDE.md) and adds what a static file cannot say: who is editing what right now, and what changed since the session started. | |
Mid-session news rides on Claude Code hooks: | |
Codex reads ~/.codex/AGENTS.md, which is where aisync seeds the shared rules block, and its hooks.json takes the same SessionStart / UserPromptSubmit / PostToolUse events, so | |
Cursor hooks (~/.cursor/hooks.json) deliver the rules and progress at sessionStart and the news after each postToolUse through additional_context, because Cursor's User Rules live inside the app instead of a file aisync could sync. | |
The journal borrows git's hash chain: every event stores the id of the one before it and its own id is a SHA-256 of that link plus its body, so |
aisync is an independent project, not affiliated with the projects above.
Development
python3 -m unittest discover -s tests # includes wheel -> venv -> demoThe images are generated: the terminal GIF is a recorded real run of
.github/refine/demo-terminal.json, the how-it-works animation
comes from .github/refine/how-it-works.stages.json, and the
credits above from .github/refine/lineage.json. All demo data is synthetic.
Contributing. See CONTRIBUTING.md. Open work you can pick up:
good first issues and
help wanted. Known gaps are filed
as issues with a repro, for example #23 (verify does not detect a
deleted last journal line). Questions and ideas go to Discussions.
MIT licensed.
More Videos if you like!
https://github.com/user-attachments/assets/5ea7928b-4985-4700-8551-90477a84df40
https://github.com/user-attachments/assets/91385ac4-714c-4a16-908b-1859ef1c78e2
https://github.com/user-attachments/assets/bf661d5c-b7b1-4876-8469-2e11dd95b232
https://github.com/user-attachments/assets/d32f3abd-2986-4fbf-83a2-be287f0185a7
Available Tools
8 toolsclaimA
Claim files (comma-separated; empty = whole repo) before editing. Overlaps with other agents come back.
Inputs: agent (required), project (required), summary (required), files. Returns: result
logB
Append one event to the journal (kinds: dev_log, decision, blocked, unblocked, rule_change, note).
Inputs: agent (required), project (required), summary (required), kind, +1 more. Returns: result
newsB
What other agents did and which rules changed since this session last asked ('' = nothing new).
Inputs: agent (required), session. Returns: result
releaseB
Release your claims (all of them, or one project's).
Inputs: agent (required), project. Returns: result
rule_addB
Add a shared rule in the When/Do/Not shape. Needs enforced_by (paths), judgment_only (why no code can), or planned (the check to write) with size S, M or L.
Inputs: do (required), when (required), agent (required), topic (required), +8 more. Returns: result
rulesB
The shared rules: the core layer (or all rules when nothing is layered); with topic, that topic's rules.
Inputs: topic. Returns: result
statusB
Live progress: who is doing what, claims, open blockers, latest events.
Inputs: no named parameters. Returns: result
tidyB
The rules clerk's proposals (duplicates, rules not cited lately, core budget, gaps). Proposals only.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools have clearly distinct roles: claim/release form a clean pair, log writes, rules/rule_add read and write the rule layer, tidy surfaces proposals. The one fuzzy boundary is news vs status, both of which report on other agents' activity and recent events, so an agent may hesitate over which to call for a progress check.
All names are short, lowercase, and terse (claim, log, news, release, rules, status, tidy), giving a coherent house style. The only deviation is rule_add using a snake_case compound alongside the bare plural rules, which is a minor inconsistency rather than a pattern break.
Eight tools is tightly scoped to the coordination domain: two for claim lifecycle, two for awareness, three for the rule layer, one for journaling. Each tool maps to a distinct agent need with no filler.
Claim lifecycle, journaling, awareness, and rule creation are all covered, but the rule layer is write-once: there is no rule_update or rule_remove, and tidy only produces proposals with no tool to accept, reject, or apply them. Stale or duplicate rules can therefore be flagged but never resolved through the surface.
Maintenance
Related MCP Connectors
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA shared memory and coordination server for multiple AI coding agents, built on the Model Context Protocol (MCP).6MIT
- AlicenseAqualityDmaintenanceA local MCP server that enables multiple AI coding tools to share structured project state (decisions, tasks, bugs) so they coordinate without re-explaining.5MIT
- AlicenseNot gradedqualityCmaintenanceA local-first MCP server for AI coding agents that shares structured execution state, routes context deltas, and provides preflight nudges to prevent conflicts and stale decisions.MIT
- AlicenseBqualityAmaintenancerhizome-mcp is a local-first MCP server for task tracking and coordination of autonomous AI coding agents, providing crash-safe issue claiming, durable project memory, and dependency graphs using SQLite. It enables agents from different MCP-compatible clients to share a consistent view of project work with no accounts, Docker, or network dependency.351Apache 2.0