v0.7.0 — Real-time SSE inbox push, 110 tests passing

Fleet-native agent orchestration for OpenCode

Spawn parallel agents as independent OS processes. Route work to specialists. Let agents collaborate peer-to-peer. No timeouts. No markups. Open source.

Install agent-mesh View on GitHub
spawn-fleet.ts 
// From any OpenCode session
const { fleet_id, agent_ids } = await callTool("spawn_fleet", {
  agents: [
    { role: "Codebase Onboarding Engineer", prompt: "Map all auth middleware", agent: "codebase-onboarding-engineer" },
    { role: "Oracle",              prompt: "Review the auth architecture",      agent: "oracle" },
    { role: "Backend Architect",   prompt: "Implement JWT token refresh",      agent: "backend-architect" },
  ],
});

// Route work to the best agent
const { matches } = await callTool("route_work", {
  description: "audit authentication security vulnerabilities"
});
10
MCP tools
100+
Premade agents
5
P2P message types
0
Artificial timeouts

10 MCP tools. One mesh.

Each tool is a primitive you can compose. Spawn fleets, route work, send messages between agents, attach specialists mid-flight. No opinions about how to use them.

spawn_fleet MCP

Spawn N parallel agents as independent OS processes

fleet_status MCP

Check fleet and agent lifecycle state

collect_results MCP

Aggregate outputs when the fleet completes

send_message MCP

P2P handoff, question, result, alert, request_help

get_inbox MCP

Agents poll for incoming messages

ack_message MCP

Mark messages as processed

register_capability MCP

Self-describe role, skills, model for routing

route_work MCP

Match a task to the best available agent

list_agents MCP

Discover 100+ premade agent personalities

attach_agent MCP

Dynamically join a running fleet mid-flight

Collaboration patterns

With P2P messaging enabled, the topology shifts from star (orchestrator → workers) to mesh. Three patterns we use every day.

Pipeline handoff

Explore → Oracle → Engineer: each specialist hands context to the next, no orchestrator mediation.

Debate consensus

Two agents review the same artifact, debate via questions, converge before reporting.

Failure recovery

An agent hits a wall → broadcasts alert → peers with relevant skills respond with fixes.

Inspect your fleet from the terminal

Once you have a running fleet, the agent-mesh CLI shows you what's happening — without opening OpenCode.

$ agent-mesh inspect
3 fleets:

bc34d339-935c-4…  complete  3 agents, 3 done (34.8m)
37ae1cf2-5ce8-4…  complete  1 agents, 1 done (28.2m)
d648beb0-cfb2-4…  failed    2 agents, 2 done (27.3s)
$ agent-mesh inspect --metrics
Total fleets:       7
  completed:        3
  failed:           4
Total agents:       16
Success rate:       42.9%
Avg duration:       1.34s

Install in 30 seconds

Meshfleet is an MCP server. Clone, build, register. That's it. No accounts. No cloud. No telemetry.

1. Clone & build
git clone https://github.com/johnmwhitman/agent-mesh.git \
  ~/.config/opencode/mcp-servers/agent-mesh
cd ~/.config/opencode/mcp-servers/agent-mesh
npm install && npm run build
2. Register the MCP server

Add to ~/.config/opencode/opencode.jsonc:

{
  "mcp": {
    "agent-mesh": {
      "type": "local",
      "enabled": true,
      "command": ["node", "~/.config/opencode/mcp-servers/agent-mesh/dist/index.js"]
    }
  }
}
3. Restart OpenCode & spawn a fleet
const { fleet_id } = await callTool("spawn_fleet", {
  agents: [{ role: "explorer", prompt: "Map src/", agent: "codebase-onboarding-engineer" }]
});

Stop managing agents. Mesh them.

MIT licensed. Works with any OpenCode setup. 100+ premade agent personalities included via the agency-agents integration.

Get started Read the docs