agentic-dev-loop
Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase
The README carries the pitch, the key features, and a quickstart; the pages below are the manual.
- Architecture - the five layers, one full run end to end, and the host-boundary security model
- CLI - run flags, resuming, the live view, reports, container management, and onboarding commands
- pipeline.yaml reference - the complete configuration reference: steps, isolation, secrets, networking, dependency policy
- LLM providers - OpenAI-compatible endpoints and the GitHub Copilot subscription
- Authoring a loop - from
initto a committed pipeline: agent files, stage lineup, adaptation checklist - Setup and troubleshooting - Docker engines, the dev image, caching, error codes
- Browser sandbox - running a browser inside the sandbox
- Known issues - container lifecycle edge cases
- Development environment - hacking on the engine itself