How SourceVault works

From a one-command install to a cited answer — the whole loop, on your machine. Watch it run, then see what each stage is doing.

Ask a question, get a cited answer, click straight to the source

A 100-second session against the public Express repository: search, a cited Ask answer, the source viewer, and a watch re-checking itself. Everything on screen runs locally.

The engine, step by step

Every question moves through four stages — the retrieval patterns the leading RAG frameworks document as best practice, implemented natively on ChromaDB and Ollama:

  1. Hybrid retrieval. Each query combines semantic search and exact keyword matching, then fuses the rankings so the strongest results rise to the top. Semantic-only search misses exact identifiers; keyword-only search misses paraphrased questions — fusing both covers each one's blind spot.
  2. Code-aware chunking. Files are split along function and class boundaries, so every result maps to readable code with exact line ranges. You never get a chunk that starts mid-function.
  3. Context-aware embeddings. Each chunk is embedded with its path and symbol names so the vector store knows where code lives, not just what it says. "The auth middleware" finds middleware/auth.js even when the file never uses the word "middleware."
  4. Grounded answers. Ask mode checks whether it has enough context, retrieves again if needed, and answers only from source-backed snippets instead of guessing. If the index can't support an answer, it says so.

Three commands cover it

Search for code, read a file, ask a grounded question. They behave the same way every time — in the CLI, Telegram, or Hermes Desktop — so they're easy to teach, support, and repeat. Just ask; the engine retrieves on its own.

$/code-search express "trust proxy client ip"
$/code-read express lib/request.js
$/code-ask express "how does the trust proxy setting affect the client IP?"

The same engine is available over MCP to Claude Code, OpenClaw, and any MCP client, so every AI tool you run answers from the same private, cited index.

A session in the dashboard

Everything ships with a browser dashboard, so the whole team can use it without touching a terminal:

  1. Connect your source control. Sign in to GitHub, GitLab, or Bitbucket once. Browse and autocomplete your repositories as you type, and clone private repos without per-clone credentials.
  2. Index in one click. Repositories index automatically on import. Update, sync, or switch branches per repo — and a stale index is one click from fresh.
  3. Search and Ask. Literal and semantic search with file-type filters, plus Ask mode for grounded answers where every citation clicks open to its source. History and archive are built in.
  4. Read the source, in place. Citations and search results open the full file in a syntax-highlighted viewer — cited lines marked and scrolled into view, 15 languages, selectable light and dark code themes.
  5. Set a watch. Pin a question as a standing check. After every reindex it re-asks itself and flags you when the cited answer drifts — "did the auth flow change this sprint?" answers itself.

See it on your own code

The trial is the real product on one repository — no account, no card, nothing leaves your machine.

Install free — 7-day trial →
See every capability →
See the benchmark →