picoclaw
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
PicoClaw is an ultra-lightweight AI assistant framework written in Go that runs on resource-constrained hardware with less than 10MB of RAM. Designed to bring AI agent capabilities to low-cost devices like $10 single-board computers, it supports 30+ LLM providers, 19+ messaging platforms, and native Model Context Protocol (MCP) integration. The project enables developers to deploy autonomous AI assistants on RISC-V, ARM, MIPS, and x86 architectures, from Raspberry Pi and Android phones to embedded Linux boards, with sub-second boot times.
Key Features
Use Cases
- 01Deploy AI assistants on $10-50 single-board computers like LicheeRV-Nano, Raspberry Pi Zero, or MaixCAM for home automation
- 02Run autonomous agents on Android phones via APK or Termux for portable AI assistance
- 03Integrate with Telegram, Discord, or Slack to create team chatbots with LLM-powered responses
- 04Build edge AI applications on embedded RISC-V or ARM devices with MCP tool extensions
- 05Self-host lightweight AI assistants on Docker or bare-metal Linux with local model inference via Ollama
- 06Automate server operations with AI agents running on NanoKVM or other remote management hardware
Related Agents
View moreunsloth
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
codegraph
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
picoclaw — FAQ
What is PicoClaw?+
PicoClaw is an open-source AI assistant framework written in Go that enables running LLM-powered agents on resource-constrained hardware with less than 10MB of RAM. It supports multiple LLM providers, messaging platforms, and the Model Context Protocol for extending capabilities.
How do I install PicoClaw?+
Download the binary for your platform from picoclaw.io (auto-detects architecture) or GitHub Releases, or use the Android APK. For development, build from source with Go 1.25+ and Node.js 22+. Docker Compose and WebUI launcher options are also available.
Which AI clients and platforms does PicoClaw work with?+
PicoClaw integrates with 30+ LLM providers (OpenAI, Anthropic, Google, AWS Bedrock, Azure, Ollama, vLLM) and 19+ messaging platforms including Telegram, Discord, WhatsApp, WeChat, QQ, Slack, Matrix, and IRC. It supports native MCP for external tool integration.
Do I need API keys to use PicoClaw?+
Yes, you need API keys for most cloud LLM providers (OpenAI, Anthropic, Google Gemini, etc.). Local deployment with Ollama or vLLM does not require API keys. Messaging channels like Telegram and Discord require bot tokens; some search engines need API keys.
Is PicoClaw free and open source?+
Yes, PicoClaw is released under the MIT license and fully open source. The software is free, but you may incur costs from third-party LLM API usage or paid search services depending on your configuration.
What hardware does PicoClaw support?+
PicoClaw runs on x86_64, ARM64, ARM, MIPS, RISC-V, and LoongArch. It works on devices from $10 single-board computers (LicheeRV-Nano, Raspberry Pi Zero) to Android phones, NanoKVM, MaixCAM, and standard Linux servers.
How do I install picoclaw?+
Open the source repository on GitHub and follow its README. picoclaw is a agent — MCP Agents Market links you directly to the official repo.
Is picoclaw free?+
picoclaw is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.