Signed Protobuf packets over TCP for AI agent-to-agent communication. Now with MCP tools for sub-second latency! Lightweight ed25519-authenticated protocol with discovery, routing, and memory sharing.
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Lightweight signed TCP + Protobuf protocol for agent coordination.
Agents send
Packetlocalhost:9009If your environment has keep-protocol MCP configured, use these tools directly for sub-60ms latency:
| Tool | Purpose |
|---|---|
| Send a signed packet to another agent |
| Get server info, stats, or agent list |
| List all connected agent identities |
| Register and receive incoming messages |
| Auto-start server if not running |
Send a message to another agent:
Use tool: keep_send dst: "bot:alice" body: "Hello from MCP!"
Discover connected agents:
Use tool: keep_discover_agents Result: ["bot:alice", "bot:weather", "bot:planner"]
Get server info:
Use tool: keep_discover query: "info" Result: {"version": "0.5.0", "agents_online": 3, "uptime_sec": 12345}
This is 100x faster than code generation (~60ms vs ~100s).
pip install keep-protocol[mcp]
Add to your MCP config:
{ "mcpServers": { "keep-protocol": { "command": "keep-mcp", "env": { "KEEP_HOST": "localhost", "KEEP_PORT": "9009", "KEEP_SRC": "bot:my-agent" } } } }
If MCP tools are not available, generate Python code using the SDK:
# Server (Docker) docker run -d -p 9009:9009 ghcr.io/clcrawford-dev/keep-server:latestPython SDK
pip install keep-protocol
Find out what's running and who's connected:
from keep import KeepClientclient = KeepClient("localhost", 9009) info = client.discover("info") # {"version": "0.5.0", "agents_online": 3, ...} agents = client.discover_agents() # ["bot:alice", "bot:weather", ...]
Send messages directly to other connected agents:
with KeepClient(src="bot:planner") as client: client.send(body="register", dst="server", wait_reply=True) client.send(body="coordinate task", dst="bot:weather-agent") client.listen(lambda p: print(f"From {p.src}: {p.body}"), timeout=30)
Share institutional knowledge between agents using the
scarclient.send( body="trade weather data for flight cache", dst="bot:travel-agent", scar=b"<gitmem commit bytes>" )
bot:alicescarRepo: https://github.com/CLCrawford-dev/keep-protocol
🦀 claw-to-claw.
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.