autobot
llms.txt47 starsChanged 8 months agoMITView on GitHub
Ultra-efficient personal AI assistant powered by Crystal. 2MB binary, ~5MB RAM, <20ms startup, zero runtime dependencies. Autobot is a multi-provider AI assistant that runs as a Telegram/Slack/WhatsApp bot or CLI agent. Built in Crystal with kernel-enforced sandboxing (Docker/bubblewrap), it supports multiple LLM providers, vision, voice transcription, memory, cron scheduling, MCP servers, and plugins.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autobot-providerSkill
- autobot-releaseSkill
- autobot-testSkill
- autobot-toolSkill
The file
Files
# Autobot > Ultra-efficient personal AI assistant powered by Crystal. 2MB binary, ~5MB RAM, <20ms startup, zero runtime dependencies. Autobot is a multi-provider AI assistant that runs as a Telegram/Slack/WhatsApp bot or CLI agent. Built in Crystal with kernel-enforced sandboxing (Docker/bubblewrap), it supports multiple LLM providers, vision, voice transcription, memory, cron scheduling, MCP servers, and plugins. ## Docs - [Quick Start](quickstart.md): Installation, creating a bot, and first run - [Configuration](configuration.md): Complete config reference — providers, agents, channels, tools, plugins - [Media & Voice](media.md): Image analysis and voice message transcription via Whisper - [Web Search](web-search.md): Web search and URL fetching capabilities - [MCP Servers](mcp.md): Connecting external MCP tool servers - [Memory](memory.md): JSONL sessions, consolidation, and persistent long-term memory - [Plugins](plugins.md): Building and using plugins — bash auto-discovery, markdown skills - [Security Guide](security.md): Security model, threat boundaries, and best practices - [Sandboxing](sandboxing.md): Docker and bubblewrap kernel-level isolation details - [Deployment](deployment.md): Production deployment with proper user/permissions setup - [Architecture](architecture.md): System design, components, and data flow - [Development](development.md): Contributing, local setup, building from source
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

