Skip to content
Autonomous Engine Docs

Autonomous Engine docs

Autonomous Engine turns a written request (“fix the basemap error”, “add an export button”) into a reviewed pull request. It runs as a set of Go services on Kafka and PostgreSQL, uses a local or hosted LLM for each stage, and refuses to open a pull request for work it cannot verify.

It is free and open source under the Apache License 2.0. The source is at github.com/Autonomous-Engine/autonomous-engine. These docs describe v0.1.0.

Quickstart Clone, set three secrets, build and start the stack, sign in.
Your first product Add providers, onboard a repository, submit a request.
Configuration What goes in .env and what is configured in the dashboard.
Troubleshooting Known first-run issues and how to read the logs.

How a request flows

  1. Intake and PRD. A request from the dashboard chat, the request portal, Jira or a webhook becomes a work item with a product requirements document. PRD approval is a human gate.
  2. Research. Parallel research tasks read the repository through a code knowledge graph (the codex) and a vector index, seeded with the files the request names.
  3. Planning. The planner decomposes the work into tasks with acceptance criteria and the checks that prove each one, and repairs or normalises the plan before anything runs.
  4. Implementation. An agent edits a git worktree pinned to a base commit, with a per-edit syntax check, bounded repair rounds, and a pre-commit test gate.
  5. Verification before any PR. An independent verifier judges the change against every acceptance criterion in an isolated scratch clone. Small, actionable problems get a bounded fix round; anything else goes to human review. No pull request exists until verification approves.
  6. PR gate, review and QA. The PR is opened (or held at a manual gate), reviewed, and checked by QA.

Every stage is budgeted per work item, idempotent under redelivery, and recorded in an evidence trail shown in the dashboard.

What you need

  • Docker Desktop or Docker Engine with Compose v2. The full stack is about 25 containers; give Docker at least 16 GB of memory, more if the model runs on the same machine.
  • An LLM. An Ollama host is the default (a 30B-class coding model such as qwen2.5-coder:32b works). OpenAI, Anthropic, vLLM and other OpenAI-compatible endpoints can be added in the dashboard.
  • An embedding provider for the vector index (Ollama, OpenAI, Azure OpenAI or an OpenAI-compatible endpoint).
  • A GitHub personal access token for the repositories you onboard, and optionally Jira credentials.

What Autonomous Engine is not

  • Not a hosted service. There is nothing to sign up for. You run it.
  • Not an editor plugin. It is a pipeline that takes a request and produces a pull request, with human gates along the way.
  • Not a closed box. You can read every log, query PostgreSQL, and read the source.