solace-agent-mesh

mcp
Security Audit
Pass
Health Pass
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 4914 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.

README.md

Solace Agent Mesh

Solace Agent Mesh is an agent development and runtime platform. It supports the full agent development lifecycle: build, test, deploy, monitor, and improve your agents and business process workflows. It hosts the agents you build, runs the tools they call, and coordinates everything over an event broker, with sessions, artifacts, authentication, evaluators, and observability built in.

[!NOTE]
The Solace Agent Mesh source code is coming to this repository soon.
Until then, this repository holds Agent Mesh Desktop downloads and
ready-to-run examples.

Installing Agent Mesh Desktop

Agent Mesh Desktop is free, runs as a single application on your computer, and
includes the sam command line interface (CLI).

To install the application, run the install command for your operating system.
The command downloads the application from the
latest release.

Agent Mesh Desktop runs on the following platforms:

  • macOS 11 (Big Sur) and later
  • Windows 10 and later (x86_64)
  • Linux (Experimental)

On macOS and Linux:

curl -fsSL https://raw.githubusercontent.com/SolaceProducts/solace-agent-mesh/main/install/install.sh | sh

On Windows, in PowerShell:

irm https://raw.githubusercontent.com/SolaceProducts/solace-agent-mesh/main/install/install.ps1 | iex

The script selects the download that matches your operating system and
processor. On Linux, it also selects your package format and WebKitGTK version.
Before it installs anything, the script checks the download against the SHA-256
checksum of the release asset, and verifies the Apple notarization on macOS or
the Authenticode signature on Windows.

To preview what the script does without installing, run it with --dry-run. On
macOS and Linux, pass the flag through sh -s --:

curl -fsSL https://raw.githubusercontent.com/SolaceProducts/solace-agent-mesh/main/install/install.sh | sh -s -- --dry-run

On Windows, set $env:SAM_INSTALL_DRY_RUN=1 instead.

You can also download the asset for your platform from the
latest release and install it yourself.

To connect an LLM the first time you open the application, see
Installing the Desktop Bundle.

Using the sam CLI

To run sam from a terminal, add it to your PATH on Windows, or create an
alias on macOS and Linux:

  • On Windows: The installer places sam.exe in
    %LOCALAPPDATA%\Programs\Solace Agent Mesh\cli, and the install script adds
    that folder to your user PATH. Open a new terminal to use sam. If you
    install without the script, add the folder yourself.
  • On macOS: Add an alias:
    alias sam='"/Applications/Solace Agent Mesh.app/Contents/MacOS/sam-desktop"'
  • On Linux: Add an alias: alias sam='solace-agent-mesh'

The following examples show common sam commands. The sam ai-assistance and
sam config commands are Early Access, so their commands, flags, and output may
change between releases.

# Install skills that teach your AI coding assistant, such as Claude Code or
# Codex CLI, to build agents, tools, and configuration for your Agent Mesh
# version. By default, the skills are written to .agents/skills/ in the current
# directory, where Codex CLI reads them. For Claude Code, add --target claude.
sam ai-assistance skill install

# Preview a configuration change, and then apply it to a running Agent Mesh
# instance. Replace manifest.yaml with the path to your manifest.
sam config plan -m manifest.yaml
sam config apply -m manifest.yaml

# Open the Agent Mesh documentation offline
sam docs

For every command and flag, see the
CLI reference.
To list the top-level commands, run sam --help. To see the flags of a command,
run sam <command> --help.

Examples

The examples directory contains use cases that you apply to Agent
Mesh with sam config apply. In the
support ticket triage use case, a customer creates a
ticket in the fictional Acme Help Desk, and Agent Mesh classifies the issue,
calculates the response deadline, drafts the first reply, escalates the ticket
if it is urgent, and writes the result back to the ticket.

The examples are for learning and evaluation, and are not production-ready.

Moving to Production

Production use of Agent Mesh requires a Solace commercial license. Agent Mesh
Desktop is for building and testing on your own computer. For production, deploy
Agent Mesh to Kubernetes, or use Agent Mesh Cloud, a managed cloud service. For
more information, see
Installing Kubernetes for Production
and Agent Mesh Cloud.
To discuss a production deployment with a Solace expert,
book a demo.

License

For the license that covers each part of this repository, see NOTICE.

Getting Help

This repository does not accept issues or pull requests. For more information,
see CONTRIBUTING.md.

Reviews (0)

No results found