AgentsMesh

AgentsMesh is an open-source agent harness and orchestration framework designed to standardize, validate, and execute portable agent skills across heterogeneous AI coding agent environments. In day-to-day operations, AgentsMesh maintains a canonical repository of skill definitions (`agents/skills/<name>`) and projects them via symlinks into client-specific directories such as `.claude/skills` and `.agents/skills`. This design allows CLI coding agents like Claude Code and OpenAI Codex to discover and execute identical automation workflows. The framework integrates with the Model Context Protocol (MCP) to hook agents into external tools, such as Chrome DevTools for automated browser verification and specialized Git workflow automations. What distinguishes AgentsMesh is its contract-driven validation harness. Rather than locking repository workflows to a single agent vendor, it includes automated validation scripts (`agents/validate.sh`) and CI pipeline checks (such as Bazel-based contract gates) to enforce frontmatter portability, path integrity, and client-neutral tool definitions across all agent capabilities. AgentsMesh is free and open-source software distributed via GitHub, maintained with automated container builds and CI integration for scalable agent orchestration.

Tags: agent harness, ai agent, cli, coding agent, developer tools, OpenSource

Visit AgentsMesh

Key features

  • Canonical Skill Architecture — Manages skills in a single canonical directory with projected links to .claude/ and .agents/ directories for cross-agent compatibility. - Contract Validation Harness — Includes built-in test scripts (agents/validate.sh) that verify skill frontmatter, format integrity, and ensure zero client-specific vendor lock-in. - MCP Server Support — Integrates Model Context Protocol servers (including chrome-devtools) to enable browser-driven testing and tool expansion. - Repository Automation Skills — Supplies prebuilt routines for Git worktree orchestration, GitHub/GitLab mirror syncing, PR merging, and architecture compliance checks. - CI/CD Integration Gates — Plugs into Bazel and Kubernetes runner pipelines to enforce agent contract compliance on every code change.

Use cases

Use Case: Cross-Agent Workflow Portability A platform team maintains shared repository automation scripts and uses AgentsMesh to expose the exact same skill definitions simultaneously to Claude Code and Codex CLI sessions without duplicating configuration.

Use Case: Automated Repository Operations A developer triggers predefined agent skills to manage isolated Git worktrees, sync changes across GitHub and GitLab mirrors, and execute end-to-end architecture checks from the terminal.

Use Case: CI-Gated Agent Contract Enforcement A team integrates agents/validate.sh into Bazel CI checks to ensure all contributed agent skills adhere strictly to standard schema and path integrity rules before merging.

Who it is for

AgentsMesh is built for platform engineers, DevOps teams, and developers orchestrating multi-agent developer environments across Claude Code, Codex, and MCP toolchains. It is not intended for users looking for a plug-and-play monolithic agent or a standalone chat GUI.

Install guide

Installation Clone the AgentsMesh repository to your local machine or add it as a submodule within your workspace: bash git clone https://github.com/AgentsMesh/AgentsMesh.git cd AgentsMesh

First Run 1. Ensure execute permissions on the validation harness: bash chmod +x agents/validate.sh 2. Run the validation suite to confirm skill symlinks and contracts are correctly configured: bash ./agents/validate.sh 3. Configure your local agent settings (e.g., in .claude/settings.json or MCP configuration) to enable MCP servers such as chrome-devtools.

Example Session Verify that the canonical skill projections are active for Claude Code and Codex: bash # Verify canonical skill projections ls -la .claude/skills ls -la .agents/skills # Run the agent validation gate ./agents/validate.sh

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories