Warning
Akio is under active development. The project is not yet fully functional and may not work as expected out of the box. If you'd like to contribute, feel free to open a pull request. Found a bug, vulnerability, or something unusual? Please open an issue.
Akio is a plug-and-play autonomous AI agent with embedded model inference, written in Rust. No OpenAI, no Anthropic, no Ollama — the inference runs directly inside the binary. It combines the power of large language models (LLMs) with real-world capabilities by integrating with a shell, read/write tools, a glob and websearch tools. Need more tools? Akio support MCP servers.
- LLM inference
- Default tools (shell, read, write, glob, and websearch)
- MCP
- API
- Orchestrator
- Model routing
- System prompt for each worker
- Built-in tools for each worker
- Voice mode
- VAD inference
- STT inference
- TTS inference
- Image model inference
- Video model inference
The Grimoire is the official Akio's documentation. You can read it here.
cargo install --git https://github.com/Fastiraz/akio.git- Download your first model
akio pull Fastiraz/Qwen3-8B-GGUF- Run the model
akio run -m Qwen3-8B-Q4_K_M.gguf