Logo
Deploy Now

SaaS Alternative

Claude

Categories

Self-Hosted Developer Tools Automation Chatbot IoT AI Assistant LLM Gateway Edge Computing

Developer links

Last Updated: 01-01-2023 12:00 AM (UTC)

PicoClaw

An 8MB Go binary that boots in under one second, uses less than 10MB of RAM, yet delivers full AI agent capabilities across 16+ chat platforms simultaneously. PicoClaw connects to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, and QQ while supporting LLM providers spanning OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, and local models via Ollama. Native Model Context Protocol support enables standardized tool integration, and the built-in smart routing engine directs simple queries to lightweight models to reduce API costs while sending complex tasks to capable models. Tool capabilities include secure shell execution, filesystem access, web search, cron scheduling for recurring tasks, and sub-agent spawning with status tracking. Gateway mode transforms PicoClaw into a full AI backend with REST API endpoints accessible from any client. The Skills system loads hierarchical behavior definitions from SKILL.md files, enabling customizable agent personalities and workflows. Compiles for x86_64, ARM64, ARMv7, RISC-V, MIPS, and LoongArch, making it deployable on hardware as cheap as a $10 Sipeed LicheeRV Nano. Achieved nearly 30,000 stars within six months of its February 2026 release. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

PicoClaw

Benefits

  • Single Binary Under 10MB RAM
  • Deploy a complete AI assistant as one static Go binary requiring less than 10MB of memory, enabling deployment on minimal VPS instances or edge devices costing as little as $10.
  • 16+ Chat Platform Integrations
  • Connect to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, QQ, and more simultaneously, managing AI conversations across all platforms from one instance.
  • Smart Model Routing
  • Rule-based routing directs simple queries to lightweight models and complex tasks to capable models, automatically optimizing API costs without sacrificing response quality.
  • Gateway Mode REST API
  • Transform PicoClaw into an AI backend exposing REST API endpoints and Model Context Protocol server, enabling integration with any external application or automation workflow.

Features

  • MCP Protocol Support
  • Native Model Context Protocol implementation enables standardized tool integration with IDE clients, automation platforms, and external AI agent frameworks.
  • Multi-Provider LLM
  • Connect to OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, Xiaomi MiMo, or local Ollama instances with a single configuration change.
  • Cron Task Scheduler
  • Built-in cron engine executes recurring AI prompts and automated jobs on schedule, enabling autonomous monitoring, reporting, and maintenance workflows.
  • Vision Pipeline
  • Automatic base64 encoding for images sent via communication channels enables multimodal interactions with vision-capable LLMs like GPT-4V and Claude Vision.
  • Skills System
  • Hierarchical SKILL.md files define agent behavior, personality, and tool preferences, enabling fully customizable assistant workflows loaded at runtime.