Decisions survive the session.
Workspace-scoped, durable memory with ranked FTS5 recall. Every process reads the same history without copying giant context files.
Native Rust coordination kernel
Give every local AI agent a durable memory, an inbox, a live identity, and resources nobody else can collide with. No daemon. No cloud. No crossed wires.
store.claim
One mesh for every local agent
Separate processes cannot see each other. They repeat research, collide on edits, lose decisions between sessions, and leave half-finished work after a crash.
“I already changed that file.”
“Wait—which approach did we choose?”
“Who owns the migration?”
Workspace-scoped, durable memory with ranked FTS5 recall. Every process reads the same history without copying giant context files.
Atomic leases protect tasks, hierarchical paths, ports, and local services. If a process dies, ownership can be recovered safely.
Real PIDs, five-second heartbeats, clean shutdowns, and stale-session collection—not hopeful presence indicators.
Direct and broadcast inboxes, independent acknowledgements, and bounded waits—without a tight polling loop.
Add agents and watch them coordinate. This simulation uses the same lifecycle concepts as the native runtime.
local-03 connected · PID 4103
codex-01 stored “API contract”
claude-02 owns store.claim
Runs entirely in this page. Install PidMesh for real process coordination.
Same SQLite schema. Same workload. Measured on Apple Silicon against the original Python runtime.
See the reproducible benchmarkInstall both the CLI and native MCP server from source. Then launch a supervised swarm—or connect agents one by one.
$ cargo install --git \
https://github.com/Apurva3509/pidmesh \
--locked
✓ Installed pidmesh v1.3.0
✓ Installed pidmesh-mcp v1.3.0
$ pidmesh swarm --workers 5 \
--name-prefix researcher \
--provider codex -- \
codex exec "Claim one open task"
● 5 agents joined mesh.local
$ claude mcp add --scope user \
pidmesh -- pidmesh-mcp
✓ Added stdio MCP server pidmesh
Open source · MIT licensed
Build the local multi-agent system you actually want to work with.
Get PidMesh on GitHub