fynnfluegge/codeqai
A local-first semantic code search and chat tool that generates fine-tuning datasets from codebases for custom AI copilots.
Not currently ranked — collecting fresh signals.
star history
Codeqai enables semantic search and conversational interaction with your codebase directly from the CLI. It generates fine-tuning datasets in Alpaca, conversational, instruction, or completion formats to train custom code-focused LLMs. The tool maintains a FAISS vector store synchronized with code changes, supports fully local execution via llama.cpp and Ollama, and integrates with OpenAI, Azure OpenAI, and Anthropic APIs. It uses Treesitter for code parsing and langchain for orchestration.
Frequently asked
- What is fynnfluegge/codeqai?
- A local-first semantic code search and chat tool that generates fine-tuning datasets from codebases for custom AI copilots.
- Is codeqai open source?
- Yes — fynnfluegge/codeqai is open source, released under the Apache-2.0 license.
- What language is codeqai written in?
- fynnfluegge/codeqai is primarily written in Python.
- How popular is codeqai?
- fynnfluegge/codeqai has 494 stars on GitHub.
- Where can I find codeqai?
- fynnfluegge/codeqai is on GitHub at https://github.com/fynnfluegge/codeqai.