GoGogot — Open-Source Self-Hosted AI Agent Written in Go
GoGogot is a lightweight, self-hosted personal AI agent written in Go. Deploy on your own server as a single ~15 MB binary — it runs shell commands, edits files, browses the web, manages persistent memory, and schedules tasks. 7 built-in LLMs (Claude, DeepSeek, Gemini, MiniMax, Qwen, Llama, Kimi). A lightweight alternative to OpenClaw (Claude Code) in ~4,500 lines of Go. No frameworks, no plugins, no magic.
Features — 27 built-in tools across 10 categories
- Shell Access — Execute bash commands, manage files, run scripts on your server.
- Web Tools — Search with Brave, fetch pages, make HTTP requests, download files.
- Persistent Memory — Markdown-based memory the AI agent reads and writes across sessions.
- Identity — Persistent soul.md (agent personality) and user.md (owner profile), auto-evolving through conversations.
- Skills — Reusable procedural knowledge the agent creates and consults itself.
- Task Planning — Session-scoped checklist for multi-step work.
- Task Scheduler — Cron-based self-scheduling, persisted across restarts.
- Single Binary — ~15 MB compiled Go binary. Only 8 dependencies. No runtime required.
- Telegram Bot — Multi-chat support, attachments, typing indicators. Extensible transport layer.
- Auto Compaction — Automatic context window compression when approaching token limits.
- Multi-Model — 7 built-in models (Claude, DeepSeek, Gemini, MiniMax, Qwen, Llama, Kimi). Pass any OpenRouter model via slug.
Architecture
No frameworks, no plugins, no magic. One agentic loop in Go with good tools and a smart prompt. The LLM decides everything — when to plan, when to act, when to self-correct. The entire agent idles at ~10 MB RAM on any Linux server or cheap VPS.
GoGogot vs OpenClaw vs Nanobot
GoGogot compiles to a ~15 MB binary with 8 dependencies and ~10 MB RAM idle. OpenClaw requires ~1 GB install size, 800+ npm packages, and ~450 MB RAM idle. Nanobot needs ~150 MB with 30+ pip packages. GoGogot is the lightest self-hosted AI agent available — deploy it on a $4/month VPS with docker compose up.
Quick Start
Configure .env with your Telegram bot token, set GOGOGOT_PROVIDER (anthropic or openrouter) and the corresponding API key, pick a model, and run docker compose up. Your personal AI agent is ready in 60 seconds.
View on GitHub — Open source, MIT license.