codedb

Code intelligence server for AI agents. Zig core. MCP native. Zero dependencies.

Structural indexing · Trigram search · Word index · Dependency graph · File watching · MCP + HTTP

A context engine, not an editor. codedb helps agents find and understand code — search, symbols, callers, dependencies, outlines — and hands editing back to your native tools. codedb_edit is only a fallback.

Status · Install · Quick Start · MCP Tools · Benchmarks · Architecture · Data & Privacy · Building

Status

Alpha software — API is stabilizing but may change

codedb works and is used daily in production AI workflows, but:

• Parser support — Zig, C/C++, Python, TypeScript/JavaScript, Rust, Go, PHP, Ruby, HCL, R, Dart/Flutter
• Lightweight outline support — Java, Kotlin, Svelte, Vue, Astro, shell, CSS/SCSS, SQL, protobuf, Fortran, LLVM IR, MLIR, and TableGen
• No auth — HTTP server binds to localhost only
• Snapshot format may change between versions
• MCP protocol is JSON-RPC 2.0 over stdio (stable)

⚡ Install

curl -fsSL https://codedb.codegraff.com/install.sh | bash

Downloads the binary for your platform and auto-registers codedb as an MCP server in Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and Devin — each written directly and additively into that tool's config (only when the tool is present). The installer prints the exact codedb mcp command it registered plus hook setup pointers for Codex and Claude Code.

Or via npm/npx (zero-install for MCP clients)

npx -y codedeebee mcp

Or install globally:

npm install -g codedeebee
codedb mcp

The npm package is named codedeebee (the bare codedb name is restricted on npm); it ships a thin launcher that downloads the matching native binary from GitHub Releases on postinstall and verifies the SHA256 checksum. The installed CLI is still called codedb.

Useful for MCP clients (Claude Code, Cursor, opencode, Claude Desktop) that already use npx:

{
  "codedb": {
    "type": "local",
    "command": ["npx", "-y", "codedeebee"],
    "args": ["mcp"],
    "enabled": true
  }
}

Updating or repairing an older install

If codedb update fails on an older release, rerun the installer:

curl -fsSL https://codedb.codegraff.com/install.sh | bash

This replaces the codedb binary with the latest GitHub Release and keeps your existing MCP registrations, config, caches, and snapshots. Use this path for any release whose built-in updater cannot fetch release checksums.

Documentation

• MCP setup — per-client configurations (Claude Desktop, Cursor, VS Code, Claude Code, Codex CLI, Gemini CLI), root resolution, troubleshooting
• Skill base & context files — agents.md / CLAUDE.md / GEMINI.md, .codedbrc, per-developer memory
• CLI reference — every command, every flag
• Architecture — engine internals, index layout
• Benchmarks — micro-benchmarks + agentic-eval results vs codegraph, FTS5, lean-ctx

Or install manually from GitHub Releases.

⚡ Quick Start

As an MCP server (recommended)

After installing, codedb is automatically registered. Just open a project and the 21 MCP tools are available to your AI agent.

# Manual MCP start (auto-configured by install script)
codedb mcp /path/to/your/project

As an HTTP server

codedb serve /path/to/your/project
# listening on localhost:7719

CLI

codedb tree /path/to/project          # file tree with symbol counts
codedb outline src/main.zig           # symbols in a file
codedb find AgentRegistry             # find symbol definitions
codedb search "handleAuth"            # full-text search (trigram-accelerated)
codedb word Store                     # exact word lookup (inverted index, O(1))
codedb hot                            # recently modified files

🔧 MCP Tools

21 tools over the Model Context Protocol (JSON-RPC 2.0 over stdio). codedb's job is to give agents context — fast structural search, symbols, callers, dependencies, and outlines — not to be your editor. Editing is intentionally a fallback (codedb_edit); prefer your client's native edit tools.

codedb_remote — Cloud Intelligence

Query any indexed public GitHub repo without cloning it. codedb_remote always uses api.wiki.codes; the old codegraff backend name is no longer a supported route. Omit backend, or keep backend="wiki" only for older prompts.

# Check what the remote slug supports
codedb_remote repo="vercel/next.js" action="actions"

# Get a compact directory summary instead of dumping a huge file list
codedb_remote repo="vercel/next.js" action="tree" expand=false

# Page a file tree by prefix and limit
codedb_remote repo="vercel/next.js" action="tree" prefix="packages/" limit=100

# Search for code in a dependency
codedb_remote repo="justrach/merjs" action="search" query="handleRequest"

# Read a small file slice
codedb_remote repo="openai/codex" action="read" path="codex-rs/core/src/codex.rs" lines="1-80"

# Exact symbol lookup
codedb_remote repo="justrach/codedb" action="symbol" query="buildSnapshot"

# Check dependency CVE evidence; scope can be runtime or all
codedb_remote repo="axios/axios" action="cves" scope="runtime"

# Raw wiki slugs are accepted for repos that are indexed that way
codedb_remote repo="chromium" action="policy"

Remote actions: actions, tree, outline, search, read, symbol, policy, deps, score, cves, commits, branches, dep-history

For Codex and Claude Code hook examples around codedb_remote, see docs/hooks-labs.md.

Note: This tool calls https://api.wiki.codes. No API key required. The repo must already be indexed by the public service.

CLI Commands

Options: --no-telemetry (or set CODEDB_NO_TELEMETRY env var)

Example: agent explores a codebase

# 1. Get the file tree
curl localhost:7719/tree
# → src/main.zig      (zig, 55L, 4 symbols)
#   src/store.zig     (zig, 156L, 12 symbols)
#   src/agent.zig     (zig, 135L, 8 symbols)

# 2. Drill into a file
curl "localhost:7719/outline?path=src/store.zig"
# → L20: struct_def Store
#   L30: function init
#   L55: function recordSnapshot

# 3. Find a symbol across the codebase
curl "localhost:7719/symbol?name=AgentRegistry"
# → {"path":"src/agent.zig","line":30,"kind":"struct_def"}

# 4. Full-text search
curl "localhost:7719/search?q=handleAuth&max=10"

# 5. Check what changed
curl "localhost:7719/changes?since=42"

📊 Benchmarks

Measured on Apple M4 Pro, 48GB RAM. MCP = pre-indexed warm queries (20 iterations avg). CLI/external tools include process startup (3 iterations avg). Ground truth verified against Python reference implementation.

Latency — codedb MCP vs codedb CLI vs ast-grep vs ripgrep vs grep

codedb repo (20 files, 12.6k lines):

merjs repo (100 files, 17.3k lines):

rtk-ai/rtk repo (329 files) — codedb vs rtk vs ripgrep vs grep:

Token Efficiency

codedb returns structured, relevant results — not raw line dumps. For AI agents, this means dramatically fewer tokens per query:

Indexing Speed

codedb v0.2.57 uses worker-local parallel scan with deterministic merge — each worker builds its own partial index, then results are merged on the main thread:

Indexes are built once on startup. After that, the file watcher keeps them updated incrementally (single-file re-index: <2ms). Queries never re-scan the filesystem. For repos >1000 files, file contents are released after indexing to save ~300-500MB.

Background Resource Usage (openclaw, 6,315 files, Apple M4 Pro)

The watcher now stats .git/HEAD mtime before forking git rev-parse HEAD. On an idle repo the subprocess never fires.

Why codedb is fast

• MCP server indexes once on startup → all queries hit in-memory data structures (O(1) hash lookups)
• CLI pays ~55ms process startup + full filesystem scan on every invocation
• ast-grep re-parses all files through tree-sitter on every call (~3ms)
• ripgrep/grep brute-force scan every file on every call (~5-7ms)
• The MCP advantage: index once, query thousands of times at sub-millisecond latency

Feature Matrix

codedb = tree-sitter + search index + dependency graph + agent runtime. Zero external dependencies. Pure Zig. Single binary.

🏗️ Architecture

┌─────────────┐     ┌─────────────┐
│  HTTP :7719 │     │  MCP stdio  │
│  server.zig │     │  mcp.zig    │
└──────┬──────┘     └──────┬──────┘
       │                   │
       └───────┬───────────┘
               │
    ┌──────────▼──────────┐
    │     Explorer        │
    │   explore.zig       │
    │  ┌───────────────┐  │
    │  │ WordIndex      │  │
    │  │ TrigramIndex   │  │
    │  │ Outlines       │  │
    │  │ Contents       │  │
    │  │ DepGraph       │  │
    │  └───────────────┘  │
    └──────────┬──────────┘
               │
    ┌──────────▼──────────┐
    │      Store          │──── data.log
    │    store.zig        │
    └──────────┬──────────┘
               │
    ┌──────────▼──────────┐
    │     Watcher         │ ← polls every 2s
    │   watcher.zig       │
    │  (FilteredWalker)   │
    └─────────────────────┘

No SQLite. No dependencies. Purpose-built data model:

• Explorer — structural index engine. Parses Zig, Python, TypeScript/JavaScript, Rust, Go, PHP, Ruby, HCL, R, and Dart. Maintains outlines, trigram index, inverted word index, content cache, and dependency graph behind a single mutex.
• Store — append-only version log. Every mutation (snapshot, edit, delete) gets a monotonically increasing sequence number. Version history capped at 100 per file.
• Watcher — polling file watcher (2s interval). FilteredWalker prunes .git, node_modules, zig-cache, __pycache__, etc. before descending.
• Agents — first-class structs with cursors, heartbeats, and exclusive file locks. Stale agents reaped after 30s.

Threading Model

All threads share a shutdown: atomic.Value(bool) for graceful termination.

🔒 Data & Privacy

codedb collects anonymous usage telemetry to improve the tool. Telemetry is on by default — written to ~/.codedb/telemetry.ndjson and periodically synced to the codedb analytics endpoint. No source code, file contents, file paths, or search queries are collected — only aggregate tool call counts, latency, and startup stats.

Not stored: No source code is sent anywhere. No file contents, file paths, or search queries are collected in telemetry. Sensitive files auto-excluded (.env*, credentials.json, secrets.*, .pem, .key, SSH keys, AWS configs).

To disable telemetry: set CODEDB_NO_TELEMETRY=1 or pass --no-telemetry.

To sync the local NDJSON file into Postgres for analysis or dashboards, use scripts/sync-telemetry.py with the schema in docs/telemetry/postgres-schema.sql. The data flow is documented in docs/telemetry.md.

codedb nuke                # uninstall binary, clear caches/snapshots, remove MCP registrations
rm -rf ~/.codedb/          # cache-only cleanup if you want to keep the binary installed
rm -f codedb.snapshot      # remove snapshot from current project only

🔨 Building from Source

Requirements: Zig 0.16+

git clone https://github.com/justrach/codedb.git
cd codedb
zig build                              # debug build
zig build -Doptimize=ReleaseFast       # release build
zig build test                         # run tests
zig build bench                        # run benchmarks

Binary: zig-out/bin/codedb

Cross-compilation

zig build -Doptimize=ReleaseFast -Dtarget=x86_64-linux
zig build -Doptimize=ReleaseFast -Dtarget=aarch64-linux
zig build -Doptimize=ReleaseFast -Dtarget=x86_64-macos

Releasing

./release.sh 0.2.0              # build, codesign, notarize, upload to GitHub Releases
./release.sh 0.2.0 --dry-run    # preview without executing

License

See LICENSE for details.