Everything you need to understand your codebase.

Codewalk is a codebase intelligence layer: it builds a persistent dependency graph, indexes code and docs, and exposes that intelligence through a Web UI, an MCP server, and a REST API.

Capabilities

Dependency Graph

Extracts imports across 15+ languages via tree-sitter and builds a complete dependency map with automatic module detection.

Blast Radius

BFS on the reversed dependency graph shows transitive impact before you change a file or module.

Semantic Search & RAG

ChromaDB vector search with parent-child chunking, distance-based filtering, and corrective RAG for grounded answers.

Code Review

Multi-stage review with OWASP security checks, blast-radius context, stack signals, and team guidelines — works with or without an index.

Voice Interface

Hands-free coding: mic → faster-whisper transcription → tool routing → spoken answer via edge-tts.

Architecture Health

Graph stats, betweenness centrality, PageRank, circular-dependency detection, and fix suggestions.

Docs & Guidelines

Index team docs (.md, .pdf, .txt) and coding guidelines, then ask questions with source citations.

Local-First & Private

Embeddings, graph, and vector store run locally. No data leaves your machine unless you enable cloud mode.

REVIEW_INTELLIGENCE

Code review powered by the intelligence layer

Codewalk's review engine is built on top of the codebase intelligence layer. It doesn't just lint — it understands your architecture, knows what files are risky, and reviews with full context.

How it works

git diff → Static Analysis
graph risk · PageRank · cycles · blast radius
batch files (3-5 per batch, grouped by feature)
host LLM reviews each batch with full context
submit findings to disk per batch
final summary: all findings + verdict

Works with or without indexing

Review runs on any git repo — no analyze step needed. The intelligence layer enhances it when available.

Component
No index
With index
Git diff + content
Rubrics + guidelines
Stack detection
Risk annotations ⚠️ → ✅
Neighborhood context ⚠️ → ✅
Blast radius ⚠️ → ✅

Severity levels

blockerMust fix before merge
errorReal bugs, logic errors, security risks
suggestionStyle, naming, minor improvements
CapabilityTypical toolsCodewalk
Architecture awarenessNo dependency graphDuckDB + igraph: PageRank, fan-in, cycles, bottlenecks
Blast radius"This file has 23 callers — review with extra care"
Works without indexingJust needs a git repo (graph enhances but isn't required)
Batched for large PRsDumps everything at once3-5 files per batch, sorted by risk, host LLM stays focused
Custom rubricsLimitedPer-language + per-framework + team guidelines
Fix applicationSuggests onlyAccept/reject → apply atomically → verify with tests

Run a review from the API

POST /review gathers the diff, runs static analysis, batches files by risk, reviews with the configured LLM, and returns a structured verdict with findings.

curl -X POST http://localhost:8000/review \ -H "Content-Type: application/json" \ -d '{ "staged": false, "target_branch": "master" }'

Three ways to use it

Web UI

Visual exploration: knowledge graph, module browser, blast-radius viewer, reading order, execution flow, chat, review, and admin.

Next.js frontend · http://localhost:3000

MCP Server

38 tools exposed through the Model Context Protocol for VS Code Copilot, Claude Code, Cursor, and OpenAI Codex CLI.

stdio transport · @codewalk

REST API

35+ FastAPI endpoints for analyze, chat, search, review, docs, voice, and health. Integrate into scripts or CI/CD.

FastAPI · http://localhost:8000

MCP tool examples

codewalk_get_overview
codewalk_search_codebase
codewalk_lookup_symbol
codewalk_get_module_info
codewalk_explain_function
codewalk_get_blast_radius_map
codewalk_find_circular_dependencies
codewalk_get_reading_order
codewalk_get_execution_flow
codewalk_get_architecture_health
codewalk_call_chain
codewalk_show_knowledge_graph
... 26 more tools including review, voice, cloud sync, and maintenance
Cloud Indexing

Indexing on your server. Query everywhere.

Deploy Codewalk to your own server, connect a GitHub App, and push to any repo. The server builds the index incrementally; every team member downloads it via MCP and queries locally. No per-user embedding cost, no stale local indexes.

  • · GitHub App webhook on push
  • · Atomic index swap on the server
  • · Per-repo tokens for secure downloads
  • · Staleness checks and catch-up re-indexing
git push → your codewalk server → team MCP clients
1. GitHub App receives push event
2. Server indexes in isolated build dir
3. Atomic swap publishes new index
4. MCP pulls index → local query

Built on solid foundations

Vector DBChromaDB
Graph DBDuckDB
Graph Runtimeigraph
EmbeddingsJina Code 1.5B
AgentLangGraph
ParsingTree-sitter
BackendFastAPI
LLMsOllama, OpenAI, Anthropic, Groq, Gemini, OpenRouter, DeepSeek

Start analyzing for free.

Initialize Workspace