
We research how autonomous agents reason, use tools, and stay under human control — and we ship what we learn as open-source software. Our first system is Zeline, with more products to come.
We study the systems behind autonomous agents — reasoning, memory, tool-use, and control — and turn that research into open, reusable software.

We start from open questions about how agents should think and act, then build to test them.
Our first system, Zeline, turns that research into something developers can run.
Zeline is the foundation. New tools grow on top as the lab expands.
A foundation for agents that reason, use tools, and run multi-step workflows — while you keep control of models, tools, and data.
OpenAI-compatible agent loop with tool calling and an interactive CLI.
OpenAI, OpenRouter, vLLM, Ollama — swap without rebuilding.
Long-term memory per identity, stored locally, surviving restarts.

Markdown procedures loaded on demand — new workflows, no code.
Web search, deep research, file I/O, code execution, and shell.
Connect external MCP servers and expose their tools automatically.
Telegram, WhatsApp, and a local webhook — one agent, many surfaces.
safe · workspace · full — gate host and shell access per surface.
History in SQLite, so context survives restarts.
Agentic AI should amplify people, not lock them in. Our mission: make autonomous systems open, portable, and controllable — your models, your tools, your data.

No black boxes. Every layer is open-source and self-hostable.
Models and providers swap freely — the architecture outlives any vendor.
Scoped permissions keep people in charge of what agents can do.
A lightweight framework with no heavy dependencies — run it locally or deploy to your own server.

Point Zeline at any OpenAI- or Anthropic-compatible endpoint.
Run the CLI, or set up a Telegram / WhatsApp / webhook gateway.
Add built-in tools, MCP servers, and Markdown skills.
Ship it anywhere — scoped profiles keep access safe.
Maturing the agent core, gateways, and tool ecosystem.
Long-running, self-directed workflows and richer plugin APIs.
Purpose-built tools layered on the framework as the lab grows.
Installation, providers, gateways, skills, tools, and API reference — all in one place.