One issue-text search finds every fix file in the top 10 for 83.0% of SWE-bench Verified issues (semble: 71.0%). Measured accuracy, speed and trade-offs.

[![agent-ready 93/100](https://mark.sylphx.com/badge/agent--ready-93%2F100-brightgreen)](https://github.com/SylphxAI/repomap#agent-readiness-score)

Live demo · Docs · Quickstart · Tools · Graph UI · Benchmarks · Compare

repomap demo: the map of excalidraw, searching restoreElements, its code and callers, then the impact of changing it

_{The real UI on excalidraw (687 files, indexed in under half a second): search, a symbol's code and callers, then the blast radius of a change. Try it in your browser, no install needed.}

Quickstart

npx -y @sylphx/repomap setup     # add repomap to Claude Code, Codex, Cursor, VS Code, Claude Desktop, Windsurf, Gemini CLI
npx -y @sylphx/repomap serve     # open the graph UI for the current repo

That's it. Add --claude-hooks to also enrich Claude Code's Grep and Glob. setup detects the clients you have, writes their MCP config, and prints every change it made. Run it again and nothing changes. Then ask your agent: "Use repomap to map this repo."

Manual MCP config

{
  "mcpServers": {
    "repomap": { "command": "npx", "args": ["-y", "@sylphx/repomap", "mcp"] }
  }
}

Claude Code: claude mcp add repomap -- npx -y @sylphx/repomap mcp Claude Desktop, one click: download repomap-<version>.mcpb from the latest release, open it, and pick your project folder. Claude Code plugin: /plugin marketplace add SylphxAI/repomap, then /plugin install repomap@repomap Codex (~/.codex/config.toml):

[mcp_servers.repomap]
command = "npx"
args = ["-y", "@sylphx/repomap", "mcp"]

Docker (stdio, amd64/arm64):

{ "mcpServers": { "repomap": { "command": "docker", "args": ["run", "-i", "--rm", "-v", "/path/to/repo:/workspace:ro", "ghcr.io/sylphxai/repomap"] } } }

The server indexes the client's workspace root (or its working directory, or REPOMAP_ROOT). Every tool also takes root.

Why

Agents burn most of their context on grep, ls and reading whole files just to work out where things are. repomap gives them the map up front:

Where is it? Hybrid search that matches symbol names, the words inside functions and what the code means, with the lines that matched. Ask "where are failed requests retried" or parseConfig.
What is this? One call returns a symbol's code, callers with call-site lines, callees, subtypes and the tests that reach it.
How does A reach B? The shortest call path, each hop cited file:line.
What breaks if I change this? Direct and indirect callers, importing files, modules touched, tests to run, and a risk level. Point it at your git diff before you commit.
What does this repo look like? Modules found from real dependencies (not just folders), the most central files, the most used symbols, and entry points.

All of it comes from a local index: tree-sitter parsing, a resolved import and call graph, PageRank, Louvain communities, BM25 over AST chunks, and a small static code embedding model (33 MB, downloaded once from Hugging Face, then offline). Nothing leaves your machine, and no API is called.

What your agent gets

Six tools, each with an obvious job:

Tool	Ask it	Returns
`map`	"Give me the lay of the land" / `focus: "src/server"`	Modules, central files, key symbols, entry points; an outline with line numbers when focused
`search`	`"where are failed requests retried"`, `"parseConfig"`	Ranked `file:line` ranges (functions, methods, classes) by keywords, names and meaning, with the matching lines
`context`	`SessionStore.refresh`, `src/auth/token.ts`, `token.ts:42`	Code, callers (with call sites), callees, subtypes, members, imports, importers, tests
`trace`	`from: handleRequest, to: db.query`	Shortest call path, or the call tree above/below a symbol
`impact`	`target: verifyToken` or `changed: true`	Risk level, callers by depth, importing files, modules, tests to run
`db`	`table: users`, or `url_env: DATABASE_URL` for a live database	Tables, keys, indexes, and the code (`file:line`) that queries each table

Answers are compact text that cites file:line, so they cost few tokens. Pass format: "json" for structured output.

> impact target=decode

# Impact (LOW risk)
Changing: function decode (src/auth/token.ts:14)
1 direct caller, 3 symbols affected in total across 3 files and 2 modules; 1 file importing the changed files; no tests reach this.

## Direct callers (will break if the contract changes)
- function verifyToken — src/auth/token.ts:8

## Indirect (depth 2)
- method SessionStore.refresh — src/auth/session.ts:5

## Indirect (depth 3)
- function handleRefresh — src/api/router.ts:6

## Importing files
- src/auth/session.ts

The same commands work in your terminal: repomap map, repomap search "…", repomap context X, repomap trace A B, repomap impact --changed, repomap db.

The graph UI

npx -y @sylphx/repomap serve            # live, with code preview
npx -y @sylphx/repomap export           # repomap.html: one self-contained file you can publish


Impact. Select a file and press `i`: everything that depends on it lights up by depth, with a list you can click through.	Code. Click a symbol to see its source, callers and callees. Open ↗ jumps to your editor or to GitHub.

WebGL rendering (Sigma.js) that stays smooth with tens of thousands of files and edges
Modules coloured and clustered by their real dependencies, file size by PageRank; tests, examples and docs are muted and one click away
/ searches files, symbols and code; d shows dependencies; f fits the view
Click a module to focus it, Shift-click to hide it; toggle tests, edges and labels
export writes one HTML file with deep links (#path/to/file) and GitHub links pinned to your commit. It's a good fit for a README, a wiki or a design review.

Database map

npx -y @sylphx/repomap db                              # from migrations / Prisma / Drizzle / SQLAlchemy / Diesel / Django
npx -y @sylphx/repomap db --url-env DATABASE_URL       # live Postgres, MySQL or SQLite, read-only
npx -y @sylphx/repomap db users                        # one table: columns, indexes, who references it, where it is queried
npx -y @sylphx/repomap db --serve                      # the same graph UI, for tables and foreign keys

repomap reads your schema from the repository: SQL migrations (applied in order, with down migrations skipped), schema.prisma, Drizzle pgTable/mysqlTable/sqliteTable, SQLAlchemy and Flask-SQLAlchemy models, Diesel table!, and Django models.py (fields, ForeignKey/ManyToManyField, Meta, implicit join tables). It can also introspect a live database. Each table is linked to the code that queries it: raw SQL (FROM users), Prisma (prisma.user.findMany), Diesel (users::table), Django (Post.objects…), and ORM models or tables used by files that import them.

repomap db --serve on crates.io: 39 tables, 78 foreign keys, 527 code references

Live connections are strictly read-only:

Postgres runs in a READ ONLY transaction that the server must confirm.
MySQL runs in a START TRANSACTION READ ONLY transaction.
SQLite is opened read-only with query_only.

Only catalog metadata is read, never table rows. The connection string comes from an argument or an environment variable, and it is never stored or printed. Agents get the same data through the db MCP tool; pass url_env rather than the URL itself.

Agent-readiness score

npx -y @sylphx/repomap score

The score rates how well an AI agent can work in the repository, from 0 to 100. It covers eight checks:

agent instructions (AGENTS.md / CLAUDE.md and how useful they are)
discoverable build and test commands
test coverage
CI
module boundaries
file sizes
docs
types

Each check that falls short comes with a concrete fix, and the score ends with a badge line for your README. For CI, use --min 70; --update-readme README.md refreshes the badge.

Keep the badge fresh with the GitHub Action:

# .github/workflows/agent-ready.yml
on: { push: { branches: [main] } }
permissions: { contents: write, pull-requests: write }
jobs:
  score:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: SylphxAI/repomap@v1
        with:
          update-readme: true   # opens or updates one PR with the fresh badge
          min-score: 0          # set e.g. 70 to fail below a bar

Claude Code hook

npx -y @sylphx/repomap setup --claude-hooks

This is opt-in and safe to run again; setup --remove takes it out. It installs a PreToolUse hook: whenever Claude Code runs Grep or Glob, repomap adds where the symbol is defined, who calls it and which module it belongs to. It answers in tens of milliseconds and never blocks the search.

repomap (code map) for this search:
- function `compose` defined at src/compose.ts:15 (module router); 3 callers: Hono.route (src/hono-base.ts:228), Hono.#dispatch (src/hono-base.ts:452), every (src/middleware/combine/index.ts:102)

Languages

Parsed with tree-sitter for symbols, calls, imports and inheritance: TypeScript, TSX, JavaScript, Python, Go, Rust, Java, Kotlin, Swift, C, C++, C#, Ruby, PHP. Search also covers Markdown, YAML, TOML, JSON, SQL, shell, Protobuf, GraphQL, HTML/CSS, Vue, Svelte, Scala and more.

Modules are found among your core code only. Tests, examples, docs and benchmarks are grouped separately, so they never name or blur a module.

Import resolution understands relative paths, @/ aliases, npm workspace packages, Python packages and relative imports, Go modules, Rust mod/use/workspace crates, Java/PHP namespaces, C/C++ includes and Ruby require. .gitignore is respected, and so is .repomapignore.

Search that understands the question

On semble's public code-search benchmark (63 repositories, 19 languages, 1,251 questions), repomap's search scores NDCG@10 0.845, versus semble 0.851 on the same runner. The previous repomap score was 0.851: stronger issue localization trades about 0.006 here. On our 60 large-repository questions, repomap scores 0.846 versus semble 0.799, but semble still wins on VS Code. The 137M-parameter CodeRankEmbed model's published score is 0.839 and plain BM25's 0.673 (cited, not re-run).

On file localization (500 SWE-bench Verified issues, one search call with the issue text), repomap finds every fix file in the top 10 for 83.0% of issues (Acc@10; 74.8% at 5, 48.8% at 1), versus semble's 71.0% / 61.6% / 34.0%. Before this change, repomap scored 62.2% / 51.8% / 23.6%. Plain BM25 scores 55.8% at 10, and repomap with embeddings off 77.6%. Same-run median index/query costs are 1.682 s / 54.4 ms, versus the old binary's 1.686 s / 59.8 ms and semble's 12.813 s / 354.4 ms. Defaults were selected only on a disjoint 300-instance tuning split, then frozen before one Verified measurement. Agent systems such as LocAgent report higher numbers on a different subset with a language model in the loop; those are cited, not re-run.

This needs no GPU, no vector database and no API key. A 33 MB static code model runs on the CPU, next to BM25 and symbol names.

Fast

The index is built in parallel and cached per file, so after the first run only changed files are parsed again. The MCP server keeps the graph in memory and refreshes it when files change.

Measured on a 4 vCPU GitHub-hosted runner (method and full table):

Repository	Code files	Cold index	Warm index	search p50	impact p50
kubernetes	11,710	13.1 s	2.0 s	74 ms	6 ms
vscode	6,126	9.3 s	1.4 s	17 ms	8 ms
django	2,271	2.6 s	0.5 s	24 ms	1 ms
rust-analyzer	1,512	2.1 s	0.4 s	8 ms	2 ms

How it compares

	repomap	GitNexus	Serena	claude-context	Aider repo map
Licence	MIT	PolyForm Noncommercial	MIT	MIT	Apache-2.0 (inside Aider)
Setup	`npx … setup`, one binary, or a one-click `.mcpb`	`npx`, Node	Python + language servers	Vector DB + embedding API key	Part of Aider
API key / network	None (model downloaded once)	None for the graph	None	Required (embeddings)	None
Code graph (calls, imports, inheritance)	✅	✅	Via LSP references	—	Ranking only
Change impact / blast radius	✅ incl. `git diff`	✅	—	—	—
Call path between two symbols	✅	✅	—	—	—
Search	✅ names + BM25 + local embeddings	✅	✅ symbols	Semantic (vectors)	—
Interactive graph UI	✅ local + static export	✅	—	—	—
Claude Code Grep/Glob hook	✅ opt-in	✅	—	—	—
Database schema map linked to code	✅ live (read-only) + migrations/ORMs	—	—	—	—
Agent-readiness score + badge	✅ + GitHub Action	—	—	—	—
Module detection	✅ Louvain	✅	—	—	—
Edits code	— (read-only)	—	✅	—	✅
Engine	Rust	TypeScript	Python	TypeScript	Python

Pick Serena if you want LSP-precise refactoring edits. repomap is for understanding and navigating a codebase with zero setup, including semantic search without a vector database or an API key, and a licence you can use at work. Search quality is measured on public benchmarks in Benchmarks.

CLI

repomap setup [--client cursor,codex] [--claude-hooks] [--dry-run] [--remove]
repomap serve [dir] [--port 7878] [--no-open]
repomap export [dir] [--out repomap.html] [--json]
repomap map [dir-to-focus] [-C root] [--json]
repomap search <query> [--path src/] [--kind function] [--limit 10]
repomap context <target> [--code-lines 60]
repomap trace <from> [to] [--callers] [--depth 3]
repomap impact [targets…] [--changed] [--base main]
repomap db [table] [--url-env VAR | --url URL] [--serve | --out db.html] [--json]
repomap score [dir] [--json] [--min N] [--update-readme README.md [--insert]]
repomap index [dir] [--no-cache] [--json]
repomap mcp [--root dir]

Binaries for macOS (arm64, x64), Linux glibc (x64, arm64) and Windows x64 ship as npm optional dependencies. They're also attached to each GitHub release. From source: cargo install --git https://github.com/SylphxAI/repomap repomap.

Migrating from Spine, Locus or CodeRAG

@sylphx/spine, @sylphx/locus and @sylphx/coderag are thin aliases of @sylphx/repomap, and their old tool names still work. See the migration guide for the name mapping and how to switch.

Contributing

cargo test --workspace          # engine + CLI tests
bun install && bun run build:ui # rebuild the UI bundle (ui/ -> crates/repomap/assets/)
cargo run -p repomap -- serve .

Issues and PRs are welcome, and new language support is especially useful: add a grammar and a query in crates/repomap-core/src/lang.rs.

Also from Sylphx

anymd: Any file (PDF, Word, PowerPoint, Excel, EPUB, HTML, images) to clean Markdown for AI agents.
lockdocs: Exact-version library docs from your lockfile. Local, offline, no rate limits.
skills: Battle-tested agent skills for Claude Code and Codex, installed in one command.
readme-mark: Beautiful README images from one URL: banners, badges, icons and stats cards.

More from Sylphx: https://sylphx.com/open-source