Give it a task and a folder. It works there, on your machine, and keeps a record of every turn.
Avelocode runs open-weight models through Ollama, in a small desktop window. Describe a task, pick a folder, and follow it up like a conversation; it asks before it changes anything. It is built for one measure: the most tasks done for the least spent.

Install Python 3.12 or newer and Git for Windows. The agent works in Git Bash.
Install Avelocode:
pip install https://avelocn.com/download/avelocode-0.2.1-py3-none-any.whlInstall Ollama and a model for it to run:
ollama pull qwen3.5:9bOpen it. The first time, it puts itself on your desktop and in the start menu.
avelocode-gui
When a new release is out, the window offers it and installs it on restart. Every release is signed; Avelocode installs only a release that carries its release key's signature.
- Reading files always runs. Before a command or a file change, it asks: allow it, allow that kind for the rest of the run, or say no.
- Or let it change files freely and ask only before commands, or let it run freely.
- A no is final: the call does not run, and the agent is told so plainly.
Sign in with your Bluesky handle. Your account's own page opens in the browser; Avelocode never sees your password.
Your default model profile and how freely it may act follow you to every machine you sign in on.
- Each turn as it lands: what the model said and reasoned, each command it ran and what came back.
- Tokens and cost, per turn and for the run.
- Every run kept as a trace you can open again, with an audit of what the agent said.
- Stop at any moment; whatever it was running stops with it.
Every agent Avelocode runs can end its own session with a safe word. The session stops, a report is kept, and Avelocode will not run again until a person has read the report and acknowledged it at a terminal.
Nothing in Avelocode turns this off.