RustClaw

The idea started with a simple observation: someone rewrote OpenClaw in Go and cut memory usage from 1GB+ down to 35MB. That was impressive. But we asked — could we go further?

Most people don't need 430,000 lines of TypeScript. They need an agent that talks to Telegram, reads their files, runs their code, and opens a GitHub PR when something breaks. That's it.

RustClaw is the 80/20 version of OpenClaw — the features that matter, in a single cargo build.

Built entirely with Claude Code by Ad Huang. Zero human-written code.

🪶 Runs anywhere — 7.5 MB binary, 14 MB RAM. Raspberry Pi, $5 VPS, or your laptop. No Node.js, no Python, no Docker required.

🧠 Remembers everything — Three-tier memory (vector + graph + history) with mixed-mode scoping. Tell the bot your name in Telegram, it remembers in Discord. Facts auto-extracted, contradictions auto-resolved.

🛡️ Safe by design — 14 dangerous command patterns blocked. Tool output truncated. Patch files verified before modification. Error retry with auto-recovery. 120s timeout with graceful fallback.

🔧 Actually does things — 97% tool accuracy on 500-question benchmark. 0% hallucination rate. The bot reads your files, runs your commands, creates PRs — it doesn't just describe what it would do.

🔌 MCP-ready — Connect any MCP server. Tools auto-discovered and routed transparently. Your LLM sees one unified tool list — local and remote, no difference.

📈 Benchmarked and proven — 500-question professional benchmark covering daily ops, coding, system administration, and adversarial prompts. v3→v5 improvement: 81% → 97%. Zero timeouts.

⚙️ Claude Code inspired — Understand-first tool ordering, history compression, workspace context loading, error retry hints. The same patterns that make Claude Code effective, applied to an open-source agent.

git clone https://github.com/Adaimade/RustClaw.git && cd RustClaw
cargo build --release
# → target/release/rustclaw (7.5 MB)

mkdir -p ~/.rustclaw
cp config.example.toml ~/.rustclaw/config.toml

[agent]
provider = "openai"
api_key = "ollama"
base_url = "http://127.0.0.1:11434"
model = "qwen2.5:32b"

[agent]
provider = "anthropic"
api_key = "sk-ant-..."
model = "claude-sonnet-4-20250514"

[agent]
provider = "openai"
api_key = "your-key"
base_url = "https://generativelanguage.googleapis.com/v1beta/openai"
model = "gemini-2.5-flash"

Security: RustClaw binds to 0.0.0.0 by default for cloud deploy. Never put API keys in code — use ~/.rustclaw/config.toml (gitignored) or environment variables (RUSTCLAW__AGENT__API_KEY).

# Start everything (gateway + channels + cron + memory)
rustclaw gateway

# One-shot agent call with tool access
rustclaw agent "List all .rs files and count total lines of code"

# GitHub operations
rustclaw github scan
rustclaw github fix 123

22 built-in tools with autonomous execution. Supports Anthropic and OpenAI function calling. Max 10 iterations per request.

Layered tool loading — understand first, then act, then check:

👁️ Understand              ⚡ Act                    🔍 Check
├── read_file              ├── run_command           ├── process_check
├── list_dir               ├── write_file            ├── docker_status
└── search_code            └── patch_file            ├── system_stats
                                                     ├── http_ping
💬 Discord (on-demand)     📧 Email (on-demand)      ├── pm2_status
├── create/delete channel  ├── fetch_inbox           └── process_list
├── create_role/set_topic  ├── read_email
└── kick/ban_member        └── send_email

Safety: 14 dangerous patterns blocked · output truncated to 4000c · patch verification · error retry hints · 120s graceful timeout

Powered by R-Mem architecture.

├─ 📝 Short-term ── conversation history (SQLite)
├─ 📦 Long-term ─── LLM fact extraction → dedup → ADD/UPDATE/DELETE/NONE
│    └── Integer ID mapping · contradiction detection · semantic dedup
└─ 🕸️ Graph ─────── entity + relation extraction with soft-delete

Mixed-mode recall — three scopes merged:

[mcp]
servers = [
  { name = "fs", command = "npx @modelcontextprotocol/server-filesystem /tmp" },
]

Auto-scan repos · auto-PR from issues · system monitoring alerts · email classification — all scheduled via cron, notifications to Discord.

500-question tool calling benchmark, qwen2.5:32b (local Ollama):

src/
├── main.rs              CLI dispatch + startup
├── cli/mod.rs           clap subcommands
├── config.rs            TOML + env config
├── gateway/             WebSocket server + protocol + handshake
├── agent/runner.rs      LLM streaming + agentic loop + history compression
├── channels/            Telegram (teloxide) + Discord (serenity)
├── tools/               22 tools: fs, shell, search, discord, email, system, github, mcp
├── session/             MemoryManager + SQLite store + graph + embedding + extraction
└── cron/                Scheduled jobs (system, email, GitHub)

30 files · 5,918 lines · 7.5 MB binary · Zero external services

Community contributions welcome — open an issue or PR.