Skip to content
Back to search

agentmesh

SkillOfficial: GoogleGitHub

Agent Mesh

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/google/agentmesh with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/google/agentmesh'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/google--agentmesh/badge.svg)](/listings/google--agentmesh)

HTML

<a href="/listings/google--agentmesh"><img src="/api/listings/google--agentmesh/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 89 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Agent Mesh
  2. <p align="center">
  3. <img alt="Agent Mesh" src="site/content/docs/agentmesh_logo.png" width="480" />
  4. </p>
  5. **Agent Mesh** is a private network for AI agents. A
  6. node runs next to an agent and gives it three things: a way to publish tools
  7. and models to the network, a way to find and call what other nodes publish,
  8. and an identity every other node can verify. Nodes connect directly when they
  9. can and through relays when they cannot, so the network works across laptops,
  10. containers, clusters and phones behind NAT.
  11. > **Note:** We have updated the name to **Agent Mesh** to better align with the goals of the project in the ecosystem.
  12. Two properties hold everywhere:
  13. - **Nothing is reachable by default.** A node exposes no services until its
  14. configuration says so, and no node may call a service the mesh policy has
  15. not granted. Grants are evaluated on service names, never on addresses.
  16. - **Identity comes from your identity provider.** A node enrolls with an
  17. OpenID Connect token or a bootstrap token, and the control plane
  18. turns that into a short-lived, offline-verifiable credential bound to the
  19. node's own key.
  20. ## Try it
  21. ```bash
  22. curl -sL https://google.github.io/agentmesh/install.sh | bash # agentmesh-node, mcp-client and friends
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 29 on GitHub
  23. agentmesh-node join https://bananas.sam-mesh.dev # one-time login
  24. agentmesh-node run --daemonize # local MCP server on 127.0.0.1:8080
  25. agentmesh-node skill install # teach your agent to use it
  26. ```
  27. Your agent now has tools that discover and call services across the mesh,
  28. and an OpenAI-compatible endpoint that routes model requests to whoever
  29. serves the model. `bananas.sam-mesh.dev` is a shared developer testnet with
  30. no uptime promise; the [quick start](https://google.github.io/agentmesh/docs/getting-started/quickstart/)
  31. walks through it, and [your own mesh](https://google.github.io/agentmesh/docs/getting-started/your-own-mesh/)
  32. runs a control plane on your laptop in one command.
  33. To run a control plane of your own without installing anything, open a
  34. GitHub codespace with the released binaries and run `make testnet`. It
  35. starts on a public `https` URL that your laptop and phone can enroll into,
  36. on your GitHub account's free quota:
  37. [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/google/agentmesh?quickstart=1&devcontainer_path=.devcontainer%2Ftestnet%2Fdevcontainer.json)
  38. The [Codespaces guide](https://google.github.io/agentmesh/docs/guides/codespaces/) has the
  39. steps, what persists and what stops.
  40. ## What is in a mesh
  41. | Program | Role |
  42. |---|---|
  43. | `agentmesh-control-plane` | Verifies who is joining, issues each node a signed credential, and holds the policy that says who may call what. |
  44. | `agentmesh-router` | A well-known peer that nodes connect to first. Relays traffic between nodes that cannot reach each other and hosts the discovery table. |
  45. | `agentmesh-node` | Runs next to your agent or service. Enrolls, connects, serves your local backends to the mesh, and exposes the mesh to your agent as a local MCP server and OpenAI-compatible API. |
  46. | `agentmesh-one` | The control plane, a router and a web console in one binary, for laptops and small deployments. |
  47. ## Documentation
  48. [google.github.io/agentmesh/docs](https://google.github.io/agentmesh/docs/) is built from `site/`.
  49. - [Getting started](https://google.github.io/agentmesh/docs/getting-started/): one node on the testnet, then a mesh of your own.
  50. - [Concepts](https://google.github.io/agentmesh/docs/concepts/): architecture, identity and enrollment, authorization, networking.
  51. - [Guides](https://google.github.io/agentmesh/docs/guides/): exposing services, connecting agent clients, headless enrollment, Kubernetes, Cloud Run.
  52. - [Reference](https://google.github.io/agentmesh/docs/reference/): every flag, configuration key, HTTP route and policy field.
  53. - [Preview](https://google.github.io/agentmesh/docs/preview/): sandboxed agents and the mobile app, which work but are still settling.
  54. - [Contributing](https://google.github.io/agentmesh/docs/contributing/): building, testing and the local kind environment.
  55. The repository has a dev container with the Go, Node and Python toolchains
  56. and Docker, so you can build and test in a codespace or in VS Code without
  57. installing anything:
  58. [![Develop in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/google/agentmesh?quickstart=1)
  59. ## Status
  60. Agent Mesh is pre-1.0. The node, routers, control plane, identity and policy model
  61. are stable in shape and exercised by the test suite and two public testnets;
  62. see [ROADMAP.md](ROADMAP.md) for the release plan. Sandboxed agent blueprints
  63. and the mobile app are in preview.
  64. ## License and disclaimer
  65. Apache-2.0; see [LICENSE](LICENSE). This is not an officially supported
  66. Google product, and it is not eligible for the
  67. [Google Open Source Software Vulnerability Rewards Program](https://bughunters.google.com/open-source-security).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.