~/projects/localforge-ai.md
LocalForge-AI
An autonomous, local-first multi-agent software development and QA engine built with LangGraph and Ollama. It coordinates task specification, code generation, execution, and repair workflows on a local machine.
- 3role-specialised agents
- 0network calls at runtime
- pytestdeterministic harness
Repository (opens in a new tab)All projects
How it works
- Task
- Product Manager
- Software Engineer
- Run + lint
- QA Analyzer ↺ repair: back to “Software Engineer”
- Package
What it does
- Uses specialized agents for specification, implementation, and verification stages.
- Feeds concrete execution, linting, and test failures back into a code-repair loop.
- Designed for offline runtime with locally hosted open-weight models through Ollama.