AST-based semantic code search that just works

A lightweight, effective (AST-based) semantic code search tool for your codebase. Built on CocoIndex — a Rust-based ultra performant data transformation engine. Use it from the CLI, or integrate with Claude, Codex, Cursor — any coding agent — via Skill or MCP.

• Instant token saving by 70%.
• 1 min setup — install and go, zero config needed!

Get Started — zero config, let's go!

Install

Using pipx:

pipx install 'cocoindex-code[full]'          # batteries included (local embeddings)
pipx upgrade cocoindex-code                  # upgrade

Using uv:

uv tool install --upgrade 'cocoindex-code[full]' --prerelease explicit --with "cocoindex>=1.0.0a24"

Two install styles — they mirror the Docker image variants of the same names:

• cocoindex-code[full] — batteries-included. Pulls in sentence-transformers so local embeddings (no API key required) work out of the box. The ccc init interactive prompt defaults to Snowflake/snowflake-arctic-embed-xs.
• cocoindex-code (slim) — LiteLLM-only; requires a cloud embedding provider and API key. Use when you don't want the local-embedding deps (~1 GB of torch + transformers).

Next, set up your coding agent integration — or jump to Manual CLI Usage if you prefer direct control.

Coding Agent Integration

Skill (Recommended)

Install the ccc skill so your coding agent automatically uses semantic search when needed:

npx skills add cocoindex-io/cocoindex-code

That's it — no ccc init or ccc index needed. The skill teaches the agent to handle initialization, indexing, and searching on its own. It will automatically keep the index up to date as you work.

The agent uses semantic search automatically when it would be helpful. You can also nudge it explicitly — just ask it to search the codebase, e.g. "find how user sessions are managed", or type /ccc to invoke the skill directly.

Works with Claude Code and other skill-compatible agents.

MCP Server

Alternatively, use ccc mcp to run as an MCP server:

claude mcp add cocoindex-code -- ccc mcp

codex mcp add cocoindex-code -- ccc mcp

opencode mcp add

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cocoindex-code": {
      "type": "local",
      "command": [
        "ccc", "mcp"
      ]
    }
  }
}

Once configured, the agent automatically decides when semantic code search is helpful — finding code by description, exploring unfamiliar codebases, fuzzy/conceptual matches, or locating implementations without knowing exact names.

Note: The cocoindex-code command (without subcommand) still works as an MCP server for backward compatibility. It auto-creates settings from environment variables on first run.

search(
    query: str,                          # Natural language query or code snippet
    limit: int = 5,                      # Maximum results (1-100)
    offset: int = 0,                     # Pagination offset
    refresh_index: bool = True,          # Refresh index before querying
    languages: list[str] | None = None,  # Filter by language (e.g. ["python", "typescript"])
    paths: list[str] | None = None,      # Filter by path glob (e.g. ["src/utils/*"])
)

Manual CLI Usage

You can also use the CLI directly — useful for manual control, running indexing after changing settings, checking status, or searching outside an agent.

ccc init                                # initialize project (creates settings)
ccc index                               # build the index
ccc search "authentication logic"       # search!

The background daemon starts automatically on first use.

Tip: ccc index auto-initializes if you haven't run ccc init yet, so you can skip straight to indexing.

CLI Reference

Search Options

ccc search database schema                           # basic search
ccc search --lang python --lang markdown schema      # filter by language
ccc search --path 'src/utils/*' query handler        # filter by path
ccc search --offset 10 --limit 5 database schema     # pagination
ccc search --refresh database schema                 # update index first, then search

By default, ccc search scopes results to your current working directory (relative to the project root). Use --path to override.

Docker

A Docker image is available for teams who want a reproducible, dependency-free
setup — no Python, uv, or system dependencies required on the host.

The recommended approach is a persistent container: start it once, and use
docker exec to run CLI commands or connect MCP sessions to it. The daemon
inside stays warm across sessions, so the embedding model is loaded only once.

Choosing an image

Two variants are published from each release:

The rest of this section uses :latest — substitute :full in the image: /
docker run commands if you want the full variant.

Mac users running the :full variant: local embedding inference is
CPU-only inside Docker, because Docker on macOS can't access Apple's Metal
(MPS) GPU. If you want local embeddings and fast inference, install
natively instead: pipx install 'cocoindex-code[full]'. The :latest
(slim) variant is unaffected — LiteLLM runs the model on the provider's
side, so Docker vs. native makes no difference.

Quick start — docker compose up -d

Grab docker/docker-compose.yml from this repo and run:

# macOS / Windows
docker compose up -d

# Linux (aligns file ownership on bind-mounted paths with your host user)
PUID=$(id -u) PGID=$(id -g) docker compose up -d

By default your home directory is mounted into the container (set
COCOINDEX_HOST_WORKSPACE to narrow this to a specific code folder). Index
data and the embedding model cache persist in a Docker volume across
restarts. Your global settings file at $HOME/.cocoindex_code/global_settings.yml
is visible and editable on the host; edits take effect on your next ccc command.

GHCR: to pull from GitHub Container Registry instead of Docker Hub,
change the image: line in your copy of docker-compose.yml to
ghcr.io/cocoindex-io/cocoindex-code:latest.

Or: docker run

docker run -d --name cocoindex-code \
  --volume "$HOME:/workspace" \
  --volume cocoindex-data:/var/cocoindex \
  -e COCOINDEX_CODE_HOST_PATH_MAPPING="/workspace=$HOME" \
  cocoindex/cocoindex-code:latest

docker run -d --name cocoindex-code \
  -e PUID=$(id -u) -e PGID=$(id -g) \
  --volume "$HOME:/workspace" \
  --volume cocoindex-data:/var/cocoindex \
  -e COCOINDEX_CODE_HOST_PATH_MAPPING="/workspace=$HOME" \
  cocoindex/cocoindex-code:latest

Shell wrapper for ccc commands

Paste this into ~/.bashrc / ~/.zshrc so ccc feels native on the host
and picks up the right project based on your current directory:

ccc() {
  docker exec -it -e COCOINDEX_CODE_HOST_CWD="$PWD" cocoindex-code ccc "$@"
}

Now cd into any project under your workspace and run ccc init, ccc index,
ccc search ..., ccc status, etc. — it just works.

Connect your coding agent

claude mcp add cocoindex-code -- docker exec -i \
  -e COCOINDEX_CODE_HOST_CWD="$PWD" cocoindex-code ccc mcp

{
  "mcpServers": {
    "cocoindex-code": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "-e",
        "COCOINDEX_CODE_HOST_CWD=${PWD}",
        "cocoindex-code",
        "ccc",
        "mcp"
      ]
    }
  }
}

codex mcp add cocoindex-code -- docker exec -i \
  -e COCOINDEX_CODE_HOST_CWD="$PWD" cocoindex-code ccc mcp

Upgrading from an older image

Earlier images used separate cocoindex-db and cocoindex-model-cache
volumes; the current image consolidates them into a single cocoindex-data
volume. Before pulling the new image, drop the old container and volumes —
indexes rebuild on your next ccc index, and the embedding model is
re-populated automatically on first start:

docker rm -f cocoindex-code
docker volume rm cocoindex-db cocoindex-model-cache

Configuration via environment variables

Pass configuration to docker run / compose with -e:

# Extra extensions (e.g. Typesafe Config, SBT build files)
-e COCOINDEX_CODE_EXTRA_EXTENSIONS="conf,sbt"

# Exclude build artefacts (Scala/SBT example)
-e COCOINDEX_CODE_EXCLUDE_PATTERNS='["**/target/**","**/.bloop/**","**/.metals/**"]'

# Set an API key
-e VOYAGE_API_KEY=your-key

Security note: mounting $HOME gives the container read/write access
to everything under it. If that's too broad, bind-mount a narrower
directory instead (COCOINDEX_HOST_WORKSPACE=/path/to/code).

Build the image locally

docker build -t cocoindex-code:local -f docker/Dockerfile .

Features

• Semantic Code Search: Find relevant code using natural language queries when grep doesn't work well, and save tokens immediately.
• Ultra Performant: ⚡ Built on top of ultra performant Rust indexing engine. Only re-indexes changed files for fast updates.
• Multi-Language Support: Python, JavaScript/TypeScript, Rust, Go, Java, C/C++, C#, SQL, Shell, and more.
• Embedded: Portable and just works, no database setup required!
• Flexible Embeddings: Local SentenceTransformers via the [full] extra (free, no API key!) or 100+ cloud providers via LiteLLM.

Configuration

Configuration lives in two YAML files, both created automatically by ccc init.

User Settings (~/.cocoindex_code/global_settings.yml)

Shared across all projects. Controls the embedding model and environment variables for the daemon.

embedding:
  provider: sentence-transformers                    # or "litellm"
  model: Snowflake/snowflake-arctic-embed-xs
  device: mps                                        # optional: cpu, cuda, mps (auto-detected if omitted)
  min_interval_ms: 300                               # optional: pace LiteLLM embedding requests to reduce 429s; defaults to 5 for LiteLLM

envs:                                                # extra environment variables for the daemon
  OPENAI_API_KEY: your-key                           # only needed if not already in your shell environment

Note: The daemon inherits your shell environment. If an API key (e.g. OPENAI_API_KEY) is already set as an environment variable, you don't need to duplicate it in envs. The envs field is only for values that aren't in your environment.

Custom location: set COCOINDEX_CODE_DIR to place global_settings.yml somewhere other than ~/.cocoindex_code/ — useful if you want the file to live alongside your projects (e.g. on a synced folder).

Project Settings (<project>/.cocoindex_code/settings.yml)

Per-project. Controls which files to index.

include_patterns:
  - "**/*.py"
  - "**/*.js"
  - "**/*.ts"
  - "**/*.rs"
  - "**/*.go"
  # ... (sensible defaults for 28+ file types)

exclude_patterns:
  - "**/.*"                # hidden directories
  - "**/__pycache__"
  - "**/node_modules"
  - "**/dist"
  # ...

language_overrides:
  - ext: inc               # treat .inc files as PHP
    lang: php

chunkers:
  - ext: toml              # use a custom chunker for .toml files
    module: example_toml_chunker:toml_chunker

.cocoindex_code/ is automatically added to .gitignore during init.

Use chunkers when you want to control how a file type is split into chunks before indexing.

module: example_toml_chunker:toml_chunker means:

• example_toml_chunker is a local Python module
• toml_chunker is the function inside that module

In practice, this usually means:

• you create a Python file in your project, for example example_toml_chunker.py
• you add a function in that file
• you point settings.yml at it with module.path:function_name

The function should use this signature:

from pathlib import Path
from cocoindex_code.chunking import Chunk

def my_chunker(path: Path, content: str) -> tuple[str | None, list[Chunk]]:
    ...

• path is the file being indexed
• content is the full text of that file
• return language_override as a string like "toml" if you want to override language detection
• return None as language_override if you want to keep the detected language
• return a list[Chunk] with the chunks you want stored in the index

See src/cocoindex_code/chunking.py for the public types and tests/example_toml_chunker.py for a complete example.

Embedding Models

With the [full] extra installed, ccc init defaults to a local SentenceTransformers model (Snowflake/snowflake-arctic-embed-xs) — no API key required. To use a different model, edit ~/.cocoindex_code/global_settings.yml.

The envs entries below are only needed if the key isn't already in your shell environment — the daemon inherits your environment automatically.

embedding:
  model: ollama/nomic-embed-text

embedding:
  model: text-embedding-3-small
  min_interval_ms: 300                               # optional: override the 5ms LiteLLM default
envs:
  OPENAI_API_KEY: your-api-key

embedding:
  model: azure/your-deployment-name
envs:
  AZURE_API_KEY: your-api-key
  AZURE_API_BASE: https://your-resource.openai.azure.com
  AZURE_API_VERSION: "2024-06-01"

embedding:
  model: gemini/gemini-embedding-001
envs:
  GEMINI_API_KEY: your-api-key

embedding:
  model: mistral/mistral-embed
envs:
  MISTRAL_API_KEY: your-api-key

embedding:
  model: voyage/voyage-code-3
envs:
  VOYAGE_API_KEY: your-api-key

embedding:
  model: cohere/embed-v4.0
envs:
  COHERE_API_KEY: your-api-key

embedding:
  model: bedrock/amazon.titan-embed-text-v2:0
envs:
  AWS_ACCESS_KEY_ID: your-access-key
  AWS_SECRET_ACCESS_KEY: your-secret-key
  AWS_REGION_NAME: us-east-1

embedding:
  model: nebius/BAAI/bge-en-icl
envs:
  NEBIUS_API_KEY: your-api-key

Any LiteLLM-supported model works. When using a LiteLLM model, set provider: litellm (or omit provider — LiteLLM is the default for non-sentence-transformers models).

Local SentenceTransformers Models

Set provider: sentence-transformers and use any SentenceTransformers model (no API key required).

Example — general purpose text model:

embedding:
  provider: sentence-transformers
  model: nomic-ai/nomic-embed-text-v1.5

GPU-optimised code retrieval:

nomic-ai/CodeRankEmbed delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.

embedding:
  provider: sentence-transformers
  model: nomic-ai/CodeRankEmbed

Note: Switching models requires re-indexing your codebase (ccc reset && ccc index) since the vector dimensions differ.

Supported Languages

Custom Database Location

By default, index databases (cocoindex.db and target_sqlite.db) live alongside settings in <project>/.cocoindex_code/. When running in Docker, you may want the databases on the container's native filesystem for performance (LMDB doesn't work well on mounted volumes) while keeping the source code and settings on a mounted volume.

Set COCOINDEX_CODE_DB_PATH_MAPPING to remap database locations by path prefix:

COCOINDEX_CODE_DB_PATH_MAPPING=/workspace=/db-files

With this mapping, a project at /workspace/myrepo stores its databases in /db-files/myrepo/ instead of /workspace/myrepo/.cocoindex_code/. Settings files remain in the original location.

Multiple mappings are comma-separated and resolved in order (first match wins):

COCOINDEX_CODE_DB_PATH_MAPPING=/workspace=/db-files,/workspace2=/db-files2

Both source and target must be absolute paths. If no mapping matches, the default location is used.

Troubleshooting

Run ccc doctor to diagnose common issues. It checks your settings, daemon health, embedding model, file matching, and index status — all in one command.

sqlite3.Connection object has no attribute enable_load_extension

Some Python installations (e.g. the one pre-installed on macOS) ship with a SQLite library that doesn't enable extensions.

macOS fix: Install Python through Homebrew:

brew install python3

Then re-install cocoindex-code (see Get Started for install options):

Using pipx:

pipx install cocoindex-code       # first install
pipx upgrade cocoindex-code       # upgrade

Using uv (install or upgrade):

uv tool install --upgrade cocoindex-code --prerelease explicit --with "cocoindex>=1.0.0a24"

Legacy: Environment Variables

If you previously configured cocoindex-code via environment variables, the cocoindex-code MCP command still reads them and auto-migrates to YAML settings on first run. We recommend switching to the YAML settings for new setups.

Large codebase / Enterprise

CocoIndex is an ultra efficient indexing engine that also works on large codebases at scale for enterprises. In enterprise scenarios it is a lot more efficient to share indexes with teammates when there are large or many repos. We also have advanced features like branch dedupe etc designed for enterprise users.

If you need help with remote setup, please email our maintainer [email protected], happy to help!

Contributing

We welcome contributions! Before you start, please install the pre-commit hooks so that linting, formatting, type checking, and tests run automatically before each commit:

pip install pre-commit
pre-commit install

This catches common issues — trailing whitespace, lint errors (Ruff), type errors (mypy), and test failures — before they reach CI.

For more details, see our contributing guide.

License

Apache-2.0