Features
Closed learning loop: self-creates and improves skills
Multi-platform messaging: Telegram, Discord, Slack, WhatsApp, Signal, CLI
Voice memo transcription with cross-platform continuity
Deep memory: FTS5 search, LLM summarization, Honcho user modeling
Built-in cron scheduler with natural language task delivery
Delegation: spawn isolated subagents for parallel tasks
14 built-in toolsets: web search, browser, code exec, vision, TTS, etc.
7 terminal backends: local, Docker, SSH, Singularity, Modal, Daytona, Vercel
300+ models via OpenRouter, Nous Portal, OpenAI, Anthropic, Gemini, etc.
Batch trajectory generation for training tool-calling models
Agentic skill registry compatible with agentskills.io
First-run wizard for GUI-based setup
Open source (MIT) on GitHub
Runs on $5 VPS or GPU cluster, near-zero idle cost
Multi-agent orchestration with handoffs
Sandbox Agents for containerized long-running tasks
Agent-as-tool delegation (v0.15.0+)
Realtime Agents with gpt-realtime-2 voice support (v0.17.6+)
Human-in-the-loop mechanisms
Automatic session history management
Built-in tracing for debugging
Provider-agnostic LLM support (100+ models via LiteLLM)
Redis session support (optional, v0.17.6+)
Instructions, tools, and guardrails configuration
Jupyter notebook compatibility
Supports OpenAI Responses and Chat Completions APIs
