PicoBot

Go Lightweight Self-Hosted AI Agent - Single Binary

PicoBot is a lightweight self-hosted AI agent written in Go, designed for minimal resource usage and simple deployment. Distributed as a single binary with no external dependencies, PicoBot is perfect for small servers, personal deployments, and environments where resources are limited. GitHub: https://github.com/louisho5/picobot Developer: louisho5 (Community Open Source) License: MIT Platforms: Linux, macOS, Windows, BSD Key Innovation: PicoBot proves that AI agents don't need to be heavy - with under 50MB RAM usage and a single binary deployment, it brings AI capabilities to the smallest servers and devices.

Core Philosophy: "Small, simple, and just works"

Why PicoBot?

Single Binary: One file, no dependencies, works everywhere.

Minimal Resources: Runs with less than 50MB RAM.

Simple Setup: Configure with one YAML file and go.

Self-Hosted: Full control over your AI infrastructure.

Key Features

1. Lightweight Core

• Single binary (~15-25MB)
• Memory usage under 50MB
• Fast startup (<500ms)
• Low CPU overhead
• No garbage collection pauses

2. Simple Configuration

server:
  port: 8080
  host: 0.0.0.0

ai:
  provider: openai
  model: gpt-4o-mini
  api_key: ${OPENAI_API_KEY}

logging:
  level: info
  file: /var/log/picobot.log

3. REST API

• Chat endpoint
• Completion endpoint
• Model listing
• Health check
• Admin endpoints

4. WebSocket Support

• Real-time streaming
• Bidirectional communication
• Low latency
• Connection management
• Auto-reconnect

5. Plugin System

• Custom handlers
• Middleware support
• Event hooks
• External integrations
• Hot reloading

Installation

Download Binary

# Linux
wget https://github.com/louisho5/picobot/releases/latest/download/picobot-linux-amd64
chmod +x picobot-linux-amd64
sudo mv picobot-linux-amd64 /usr/local/bin/picobot

# macOS
wget https://github.com/louisho5/picobot/releases/latest/download/picobot-darwin-amd64
chmod +x picobot-darwin-amd64
sudo mv picobot-darwin-amd64 /usr/local/bin/picobot

# Windows
# Download exe from releases and add to PATH

Docker

docker pull louisho5/picobot:latest
docker run -d --name picobot -p 8080:8080 louisho5/picobot:latest

Build from Source

git clone https://github.com/louisho5/picobot.git
cd picobot
go build -o picobot
sudo mv picobot /usr/local/bin/

Package Managers

# Homebrew (macOS/Linux)
brew install louisho5/tap/picobot

# Go install
go install github.com/louisho5/picobot@latest

Configuration

config.yaml

server:
  port: 8080
  host: 0.0.0.0
  timeout: 30s
  max_connections: 100

ai:
  provider: openai
  model: gpt-4o-mini
  api_key: ${OPENAI_API_KEY}
  base_url: https://api.openai.com/v1
  timeout: 60s
  max_tokens: 4096

logging:
  level: info
  format: json
  file: /var/log/picobot.log
  max_size: 100MB
  max_backups: 3

security:
  api_key: ${PICOBOT_API_KEY}
  rate_limit: 100
  rate_window: 1m

plugins:
  enabled:
    - health
    - metrics

Environment Variables

export OPENAI_API_KEY=sk-...
export PICOBOT_API_KEY=your-secret-key

API Usage

Chat Completion

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PICOBOT_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Streaming

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PICOBOT_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Tell me a story"}],
    "stream": true
  }'

Health Check

curl http://localhost:8080/health

Pricing

Free: PicoBot is completely free and open source under MIT license. You only pay for the AI models you use through their respective providers.

System Requirements

Use Cases

Personal AI Assistant

Run your own AI assistant on a small server or Raspberry Pi.

Small Server Deployment

Deploy AI capabilities on small VPS instances with limited resources.

Lightweight Automation

Run simple AI automations without heavy infrastructure.

API-Based AI Access

Provide AI access to applications through a simple REST API.

Resource-Constrained Environments

Operate in environments where memory and CPU are limited.

Quick Prototyping

Rapidly prototype AI integrations without complex setup.

Community and Support

• GitHub: https://github.com/louisho5/picobot
• Documentation: https://github.com/louisho5/picobot#readme
• Issues: GitHub Issues tab
• Discussions: GitHub Discussions tab

Quick Start Guide

Get 'PicoBot' running in under 2 minutes — it is a single binary with zero dependencies.

Step 1: Download the Binary

Download the latest release from the official GitHub repository.

Step 2: Run

chmod +x picobot
./picobot setup

Step 3: Configure

Set your AI model API key and preferred platform integration.

Time to first result: ~2 minutes — No runtime dependencies, single binary.

Full documentation: 'https://github.com/louisho5/picobot#readme'

FAQ

Is 'PicoBot' free to use?

Yes, 'PicoBot' is free and open source ('MIT' license). You only pay for AI model API costs if using external models.

What are the system requirements for 'PicoBot'?

'PicoBot' requires '50MB RAM' of RAM minimum. Runtime: 'Single binary (Go)'. It runs on Windows, macOS, and Linux.

Can I self-host 'PicoBot'?

Yes. 'PicoBot' is open source ('MIT') and can be self-hosted on your own hardware. Clone the repository from GitHub and follow the installation guide.

How does 'PicoBot' compare to OpenClaw?

'PicoBot' offers a different approach compared to OpenClaw. While OpenClaw provides the largest ecosystem with 13,729+ skills and maximum flexibility, 'PicoBot' focuses on 'personal assistant'. Choose 'PicoBot' if you prioritize its specific features; choose OpenClaw for the broadest compatibility and community support.

Is 'PicoBot' suitable for beginners?

'PicoBot' requires some technical knowledge to set up ('Single binary (Go)'). If you are a beginner, consider starting with QClaw (one-click install) or MaxClaw (cloud-based, no setup) first, then graduate to 'PicoBot' as you gain experience.

License

MIT License - Free for personal and commercial use.

Tags

ai-agent, go, lightweight, self-hosted, single-binary, minimal, rest-api, docker