I built a desktop AI agent that writes its own tools — behind verification gates

A developer built AMA-teras, an open-source desktop AI agent that writes its own tool plugins when it encounters missing capabilities. The agent runs locally with swappable models and enforces a verification gate for all code, including self-written tools and community plugins, to prevent malicious or unsafe execution. The project is available on GitHub under the AGPL license.

A desktop AI agent that writes its own tools — and why every line passes a gate before it runs. Agent capability is quietly becoming synonymous with a specific vendor's pricing plan. I wanted the opposite: an agent that runs on my machine, where models are swappable parts Anthropic / OpenAI / Moonshot, or free-tier OpenAI-compatible APIs , and where the tools it writes stay on my PC as my assets. So I built AMA-teras AGPL, Electron + TypeScript : a desktop agent that, when it hits a capability it lacks, writes a new tool plugin for itself. "Self-evolving" sounds like a horror story, so the pipeline is the product: Nothing ships unreviewed — including code it wrote for itself, and anything imported from the community registry shared plugins carry a verification-evidence record; audits elsewhere report 12–20% of marketplace skills are malicious, so evidence-or-nothing felt right . A large part of this app was built by the agent itself, under the same gates. The failure stories are documented in the repo — including the night it deleted its own work branch and we had to rebuild two tools from scratch that incident is why nightly work now auto-backs-up to a private remote . Repo: https://github.com/moriwo-dev-ai/ama-teras https://github.com/moriwo-dev-ai/ama-teras Feedback very welcome, especially on the safety model.