RepoGraph AI turns any repo into a live dependency graph — every import traced, every answer backed by file:line evidence. Install once, use it in every project. New to a codebase? Understand it in minutes.
A 57-second walkthrough from inside VS Code - one-click analysis, the dependency graph, the data-flow map and the context file your AI agent gets.
From your first side-project to a production monorepo — if you read code, this is for you.
No per-project config. No server to keep running. Open any folder, hit Analyze Workspace, and the graph is ready in seconds — switch projects and repeat, same flow every time.
Get set up in 3 steps →One click from the Marketplace. Keys stay in your OS keychain.
Any language, any size — the scanner adapts on its own.
Map, summaries and Q&A — in seconds, every single time.
Six essentials. Every answer traces a real path with file:line citations — no re-reading the repo four times.
Interactive canvas of every file and import. Click for details, double-click to open. God-nodes surface the files everything depends on. No setup per project — open any folder and go.
Plain-English explanations of what each file does, exports, and depends on — generated on your key.
Ask in plain English with full graph context and file references. Multi-turn, with history. Paste any answer into your agent — cited context, zero wasted tokens.
Groq, Ollama, Gemini, Claude, OpenAI. Custom models. Switch anytime without re-analyzing.
Every analysis saved locally per workspace. Diff understanding across refactors.
Skips node_modules, dist, lockfiles and generated code automatically. Parsing stays on your machine.
New to the repo? Get grounded answers with file:line citations — for you and your agent.
Follow every edge from a diff before it merges. Run the right tests.
Repo overview + per-file docs refresh with each analysis. Nothing goes stale.
| Approach | Citations | Stays current | Private by default |
|---|---|---|---|
| RepoGraph AI · graph + summaries | ✓ file:line paths | ✓ re-analyze anytime | ✓ on-device |
| Plain grep / go-to-definition | — one hop only | ✓ always live | ✓ local |
| Vector RAG chunks | ~ fuzzy snippets | — needs re-embed | — usually cloud |
| Cloud-hosted indexers | ~ varies by tool | — re-run per repo | — repo leaves machine |
The entire pipeline runs locally. The only external call is to the AI provider you choose.
Reads all source files. Skips node_modules, dist, lockfiles, minified & generated code.
Extracts every import, resolves relative & alias paths into a node-edge map.
Batched calls to your provider. Repo overview, architecture, tech stack, per-file docs.
Q&A agent with full graph + summary context. Multi-turn with history.
The usual shortlist for reading a repo — and what each tool actually does inside yours.
| Compared on |
RepoGraph AI
|
 Sourcegraph |
 Greptile |
 CodeRabbit |
|---|---|---|---|---|
| Runs on your machine | ✓parsing stays in the editor | ✗cloud index | ✗cloud SaaS | ✗cloud SaaS |
| Every import, mapped | ✓interactive graph + god-nodes | ~search-first code intel | ✗graph, but review-only | ✗diffs, not a graph |
| Works fully offline | ✓with Ollama, zero cloud | ✗needs the cloud | ✗needs the cloud | ✗needs the cloud |
| Any AI provider, BYO key | ✓Groq · Ollama · Gemini · Claude · OpenAI | ✗built-in models only | ✗built-in only | ✗built-in only |
| Ready in one install | ✓open any repo → it analyzes | ✗index a repo first | ✗connect repo, wait on index | ✗install the GitHub app |
| Install once, use in any project | ✓no setup — just install the extension and use | ✗index each repo first | ✗connect repo by repo | ✗set up per repo |
| Open source (MIT) | ✓auditable, forkable | ~open clients, closed core | ✗proprietary | ✗proprietary |
| Free to start | ✓free — bring your key | ~free tier → paid teams | ✗paid per dev | ~free for OSS → paid |
Not just what a file imports - where each value travels. Every hop declares its input and output, so you can audit the whole path. COMING SOON
Walks call edges across files, hop by hop.
The full path, saved per workspace. Diff it across refactors.
Click any hop to jump straight to the line.
No backend. No account. No tracking. The only network request is to the AI provider you configure.
Keys in VS Code SecretStorage via OS keychain. Never plaintext on disk.
No analytics, no crash reports. Fully offline except AI calls.
Every line public on GitHub. Read it, verify it, fork it.
Search “RepoGraph AI” in Extensions and click Install - or paste this in VS Code:
Open the RepoGraph panel → Settings → pick a provider → paste key. Start free with Groq.
Get a free Groq key →Open a project → Analyze tab → Analyze Workspace. Graph ready in seconds.
Yes - 100% free and MIT-licensed. Bring your own key from Groq (free tier) or Ollama (fully local). No subscription, no account, no paywall.
No. There is no backend. The only external call is to the AI provider you configure. Everything else stays on your machine.
Groq, Ollama, Gemini, Claude and OpenAI - with custom model names. Switch providers anytime without re-analyzing.
Files are processed in batches with generated code skipped. Most repos of 50–500 files finish in under a minute.
An AI coding agent graph is a machine-readable map of a repository: files as nodes, imports and calls as typed edges. RepoGraph AI builds exactly this graph for any repo, so both you and an AI coding agent can navigate, summarize, and question the codebase with full structural context.
Yes. The v2 flow tracer exports the repo graph as typed trace records that coding agents can consume: which file calls which, with file and line references. Until then, paste any AI summary or Q&A answer straight into your agent's context — cited structure in, no wasted tokens re-reading files.
Analyze the workspace once: the dependency graph shows you what connects to what, the repo overview explains the architecture, and Q&A answers "where is X handled?" with file references. Most developers go from zero to productive in a single sitting.
Most repo graph tools only draw static pictures. RepoGraph AI combines a live dependency graph, per-file AI summaries, multi-turn codebase Q&A, five AI providers, and zero telemetry - free and open source, entirely inside VS Code.
20+: TypeScript, JavaScript, Python, Go, Rust, Java, Kotlin, C/C++, C#, Ruby, PHP, Swift, Vue, Svelte, Astro, GraphQL, Prisma, SQL, Shell.
Free · Open source · No account required
