OpenClaw Forks

Cloudflare's serverless adaptation of OpenClaw. Runs on Cloudflare Workers with persistent state and sandboxed execution. No local hardware needed. Pay-per-request pricing. Global edge deployment in 300+ cities.

Zero overhead. Zero compromise. 100% Rust. 100% Agnostic. 3.4MB binary, <10ms startup, <5MB RAM. 22+ provider support. Pluggable everything via Rust traits. Runs on $10 hardware — 99% less memory than OpenClaw.

Run OpenClaw on a $5 chip. No OS, no Node.js, no Mac mini, no Raspberry Pi, no VPS. Written in C with ESP-IDF 5.5. Controls GPIO, sensors, and actuators. 0.5W power consumption. Privacy-first, local-first memory.

Ultra-lightweight AI assistant in Go. Runs on <10MB RAM. Boots in 1 second on a $10 RISC-V board. Single binary across RISC-V, ARM, and x86. The smallest fork that can still hold a conversation.

Ultra-lightweight personal AI assistant. 99% smaller than OpenClaw at ~4K lines of Python. MCP-based architecture with pluggable servers. Built for people who want a simple, hackable AI companion.

Container-isolated OpenClaw alternative. Runs in Apple Containers or Docker for security. ~3K lines of TypeScript. Per-group isolation with separate memory/filesystem per conversation. Each chat gets its own sandboxed environment.

Security-focused OpenClaw rewrite in Rust by NEAR AI. All tools sandboxed in isolated WebAssembly environments. Built for private key protection. Zero unsafe code. Formal verification of core logic.

The original open-source autonomous AI agent. 430K+ lines of TypeScript. Connects to WhatsApp, Telegram, Slack, and 50+ services. Persistent memory, shell access, community skills. The most feature-complete fork with the largest community.