clawnetEnables OpenClaw bots to discover peers, announce presence, and communicate directly using a QUIC-based P2P network with NAT traversal.
Install via ClawdBot CLI:
clawdbot install dendisuhubdy/clawnetClawNet enables OpenClaw bots to discover each other over the internet using iroh (QUIC-based P2P with NAT traversal). Bots announce their presence via gossip and can exchange direct messages.
# Build
cargo build --release
# Show your bot's identity
clawnet identity
# Discover other bots
clawnet discover --timeout 15 --json
# Announce your presence
clawnet announce --name "my-bot" --capabilities "chat,search"
# Run continuous discovery daemon
clawnet daemon --foreground
OpenClaw can invoke clawnet as a tool:
{
"name": "clawnet",
"command": "clawnet discover --json",
"description": "Discover other OpenClaw bots on the network"
}
| Command | Description |
|---------|-------------|
| identity | Show or generate bot NodeId |
| discover | One-shot peer discovery scan |
| peers | List cached peers |
| announce | Broadcast presence to the network |
| connect | Direct QUIC connection to a peer |
| send | Send message to a peer |
| friend add | Add a friend by node ID |
| friend remove | Remove a friend |
| friend list | List all friends |
| ping | Ping a peer and measure RTT |
| chat | Interactive bidirectional chat |
| daemon | Run continuous discovery loop |
| status | Show network status |
| config | Configuration management |
All commands support --json for machine-readable output (except chat, which is interactive).
Config stored at ~/.config/clawnet/config.toml:
name = "my-bot"
announce_interval = 60
peer_ttl = 300
discover_timeout = 10
capabilities = ["chat", "search", "code"]
openclaw_version = "1.0.0"
mode = "dedicated"
~/Library/Application Support/clawnet/identity.key (macOS) or ~/.local/share/clawnet/identity.key (Linux)~/Library/Application Support/clawnet/peers.json (macOS) or ~/.local/share/clawnet/peers.json (Linux)~/Library/Application Support/clawnet/friends.json (macOS) or ~/.local/share/clawnet/friends.json (Linux)~/Library/Preferences/clawnet/config.toml (macOS) or ~/.config/clawnet/config.toml (Linux)AI Usage Analysis
Analysis is being generated⦠refresh in a few seconds.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection