AgentMesh: Synchronize AI Coding Runtime Context

What is AgentMesh?

AgentMesh is an open-source Rust CLI that keeps project-level AI configuration in sync across coding tools. Instead of maintaining separate copies of instructions, skills, and subagents in .claude/, .codex/, and other runtime folders, AgentMesh maintains one canonical model and propagates changes bidirectionally.

The goal: write once, run everywhere — the same way web standards let you write HTML once and run it in every browser.

The problem AgentMesh solves

Every AI coding runtime uses its own config layout:

Runtime	Configuration
Claude Code	.claude/, CLAUDE.md
Codex	.codex/, AGENTS.md
Cursor	.cursor/rules
Copilot	.github/copilot-instructions.md

If your team uses more than one tool — or you switch between them — you end up duplicating skills and instructions, chasing drift, and reviewing noisy diffs across dotfolders. AgentMesh sits between runtimes and keeps them aligned.

How it works (v0.1)

AgentMesh v0.1 ships with two bundled adapters: Claude Code and Codex.

You edit a skill in .claude/skills/
        ↓
Runtime hook fires (~100ms)
        ↓
AgentMesh updates .ai/ (canonical) + .codex/ (other runtimes)
        ↓
agentmesh.lock records resolved state

Most of the time you never run a command. Sync is triggered by runtime hooks. A per-repo watcher daemon catches direct file edits, git pull, and other cases hooks miss.

What gets synchronized

Entity type	What it is	Example locations
instructions:root	Project-wide instructions	AGENTS.md ↔ CLAUDE.md
skill	Named, invocable capability	.claude/skills/, .codex/skills/, .ai/
subagent	Specialized agent for delegated work	.claude/agents/, .codex/agents/, .ai/

What AgentMesh adds to your repo

After agentmesh init, you will see:

File / folder	Committed?	Purpose
AGENTS.md	Yes	Canonical cross-runtime instructions
.ai/	Yes	Canonical skills and subagents
agentmesh.lock	Yes	Resolved sync state (review in PRs like any lockfile)
agentmesh.config.yaml	Optional	Overrides — only needed for non-default behavior
.claude/settings.local.json	No (gitignored)	Claude hook entry on your machine
.codex/hooks.json	No (recommended gitignore)	Codex hook entry on your machine

User-visible files stay pristine — no AgentMesh metadata blocks in your skills or instructions.

Key design principles

• Local-first — no hosted sync service; everything runs on your machine
• Non-destructive adoption — agentmesh init imports what you already have
• Explicit hook installation — hooks are installed only when you run init or install
• Recoverable conflicts — auto-resolution with audit trail; restore losing versions with agentmesh restore

Supported runtimes

Runtime	v0.1 status
Claude Code	Bundled
Codex	Bundled
Cursor	Planned v0.2
Copilot	Planned v0.2
Gemini CLI	Planned v0.2

Getting started

1. Install AgentMesh (official script for macOS, Linux, and Windows)
2. Follow the Quick Start to initialize a repository
3. Read Repository Setup for teammate onboarding and gitignore recommendations

Most days you will not run AgentMesh commands. The CLI is for setup, inspection, and recovery — see the CLI Reference.