Point it at any GitHub repository and have a real conversation with it — architecture, data flow, where something happens, how to add a feature. Retrieval-augmented generation over source code.
You land on an unfamiliar repository with 400 files and a README that says “see the docs.”
The docs are stale. grep gives you 90 hits with no ranking and no explanation.
Onboarding eats days — not because the code is hard, but because finding the relevant
200 lines is hard.
LLMs explain code beautifully, but they can’t hold a whole repository in their head and they confidently invent functions that don’t exist. This closes that gap: index the repo into a semantic vector space, retrieve only the passages that matter, and force the model to answer from retrieved code — citing the files it used.
Built for the questions you actually have on day one of a new codebase.
Paste a GitHub link — or a /tree/branch URL to target a specific branch.
Python, JS/TS, Java, Go, Rust, C/C++, C#, Ruby, PHP, Swift, Kotlin, SQL, notebooks and config.
The vector index is cached per owner/repo@branch, so follow-up questions skip embedding entirely.
Responses arrive token-by-token instead of behind a spinner.
Every answer ships an expandable panel listing the exact files it was drawn from.
Credentials live in session state only — never logged, never persisted, never committed.
Five stages, from a URL to a grounded answer.
A GitHub reader walks the repo tree over the API with 5 concurrent requests, keeping only source and documentation extensions.
Documents are chunked and encoded with BAAI/bge-en-icl, an embedding model tuned for retrieval over technical text.
Vectors land in an in-memory vector index, memoised so a UI rerun never re-pays the embedding cost.
Your question is embedded into the same space; the k nearest chunks come back as context. k is tunable in the sidebar.
A grounding prompt hands DeepSeek-V3 only those chunks and instructs it to cite file paths — and to say “not in the context” rather than guess.
Once a repository is indexed:
Chosen for retrieval quality per dollar.
| Layer | Choice | Why |
|---|---|---|
| Orchestration | LlamaIndex | Batteries-included RAG primitives — readers, chunking, vector index, query engines. |
| Ingestion | GitHub reader | Walks the tree API concurrently; no local clone required. |
| Embeddings | BAAI/bge-en-icl | Strong retrieval performance on technical text, served cheaply via Nebius. |
| LLM | DeepSeek-V3 | Excellent code reasoning at a fraction of frontier-model pricing. |
| Interface | Streamlit | Native chat, streaming and resource caching in pure Python. |