Show HN: I got tired of hand-syncing AI coding rules across four tools
Developers often face challenges maintaining consistent AI coding assistant configurations across multiple tools, leading to configuration drift. AgentsMesh is an open-source CLI and TypeScript library that centralizes these configurations in a single .agentsmesh/ directory, generating tool-specific files automatically. It supports import, preview, and drift detection features to streamline adoption and maintain consistency.
- ▪AgentsMesh allows developers to define rules, prompts, and configurations once in a canonical format within the .agentsmesh/ directory.
- ▪The tool generates native configuration files for various AI coding assistants like Claude, GitHub Copilot, Cursor, and Gemini from the centralized source.
- ▪AgentsMesh includes commands like import, generate, diff, and check to support safe adoption, preview changes, and detect configuration drift in CI pipelines.
Opening excerpt (first ~120 words) tap to expand
AgentsMesh — One .agentsmesh/ Directory for Every AI Coding Tool AI coding assistants now ship with their own configuration formats — CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, .github/copilot-instructions.md, .gemini/settings.json, .windsurf/rules/*.md, .codex/config.toml, .kiro/steering/*.md, and more. Maintaining the same rules, prompts, MCP servers, hooks, and permissions across all of them by hand causes config drift fast. AgentsMesh is an open-source CLI and TypeScript library that fixes this. You write canonical rules, commands, agents, skills, MCP, hooks, ignore files, and permissions once in .agentsmesh/, then agentsmesh generate projects them out as native config for every supported assistant.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.