---
title: "Index Your Codebase for AI Agents with CocoIndex V1"
description: "Index a codebase for RAG and AI coding agents with CocoIndex V1 and Tree-sitter: language-aware chunking, embedding, and a live vector index in async Python."
last_updated: 2026-06-10
doc_version: "2026-06-10"
canonical: https://cocoindex.io/blogs/index-codebase-v1/
---
# Index Your Codebase for AI Agents with CocoIndex V1

> Index a codebase for RAG and AI coding agents with CocoIndex V1 and Tree-sitter: language-aware chunking, embedding, and a live vector index in async Python.

Published: 2026-06-10 · Canonical: https://cocoindex.io/blogs/index-codebase-v1/

In this blog, we'll build a live semantic index over a codebase with [CocoIndex V1](https://github.com/cocoindex-io/cocoindex). Point it at a repo, and you get a vector index you can search in natural language ("where do we embed chunks?") that updates itself as you edit. It's the kind of fresh, low-latency code context a [coding agent](https://cocoindex.io/docs/getting_started/ai_coding_agents/) needs, and it's about 100 lines of plain async Python.

CocoIndex has built-in support for codebase chunking, with native Tree-sitter parsing and live updates.

The heavy lifting ([incremental processing](https://cocoindex.io/blogs/incremental-processing), change tracking, managed targets) runs in a Rust engine underneath. With a source that watches for changes, like the local filesystem in `live` mode, the index tracks your edits as they happen: save a file, and only the chunks that changed get re-embedded and re-upserted.

## Use case

- Code context for agents: semantic context for Claude, Codex, OpenCode, Factory.
- Code search: natural-language and semantic search over your repo.
- Review & refactor agents: context for code review, security analysis, and large-scale refactoring.

## Why CocoIndex for codebase indexing

A codebase is hard to keep indexed well, and it exercises most of what CocoIndex was built for:

- Chunks follow real code structure (functions, classes, blocks) instead of arbitrary line windows. Tree-sitter parsing is built in for every major language.
- Code changes constantly: every commit, save, and rebase mutates a handful of files. CocoIndex re-embeds only the chunks that changed, and with `live=True` plus `cocoindex update -L` it keeps watching and applies each edit as it happens.
- The engine is Rust. The run below indexes 622 files in 43 seconds cold; after that, a save costs one file.
- The pipeline is ordinary `async` Python and your own types. Pick your embedding model, chunking strategy, and vector database; if your agent can write Python, it can extend this flow.

<ExampleRepoCard
  href="https://github.com/cocoindex-io/cocoindex/tree/main/examples/code_embedding"
  path="examples/code_embedding"
  description="The whole example is ~100 lines of plain Python. Clone it, point it at your repo, and swap in your favorite model or vector store."
/>

## Overview

From a high level, these are the steps:
1. Read code files from a local directory.
2. Split each file into syntax-aware chunks with Tree-sitter, then embed every chunk.
3. Store the chunks and their embeddings in Postgres (as [**target states**](https://cocoindex.io/docs/programming_guide/target_state/)).

With CocoIndex, you [declare the transformation logic](https://cocoindex.io/docs/programming_guide/core_concepts/) with native Python, without worrying about handling updates. 

Think: **target_state = transformation(source_state)**.

When your codebase changes, or your processing logic changes (a different embedding model, a new chunk size), only the difference is reprocessed. The [Incremental updates](#incremental-updates) section walks through exactly what gets recomputed when.

## Setup

In this example we store the indexed rows in Postgres with the [pgvector](https://github.com/pgvector/pgvector) extension. Your metadata and the vector search index both live there. CocoIndex supports [many targets](https://cocoindex.io/docs/connectors/postgres/), so you can pick the one that works best for you.

1. If you don't have Postgres running, use the Docker Compose file in the [cocoindex repo](https://github.com/cocoindex-io/cocoindex) to start one.

   ```sh
   docker compose -f dev/postgres.yaml up -d
   ```

2. Point CocoIndex at it

   ```sh
   export POSTGRES_URL="postgres://cocoindex:cocoindex@localhost/cocoindex"
   ```

3. Install CocoIndex and the dependencies

   ```sh
   pip install -U "cocoindex[postgres,sentence_transformers]" asyncpg pgvector numpy python-dotenv
   ```

## Define the App
[Apps](https://cocoindex.io/docs/programming_guide/app/) are the top-level runnable unit in CocoIndex. An app names your pipeline and binds a main function with its parameters.

### Define the data and shared resources

This block sets up two things the rest of the code builds on. `CodeEmbedding` defines one row of the output table: each chunk of code becomes one row, with its text, location, and embedding vector. `coco_lifespan` provides the [shared resources](https://cocoindex.io/docs/programming_guide/context/) every step needs, the Postgres connection pool and the embedding model, built once at startup instead of per file.

```python
import os
import pathlib
from dataclasses import dataclass
from typing import AsyncIterator, Annotated

import asyncpg
from numpy.typing import NDArray

import cocoindex as coco
from cocoindex.connectors import localfs, postgres
from cocoindex.ops.text import RecursiveSplitter, detect_code_language
from cocoindex.ops.sentence_transformers import SentenceTransformerEmbedder
from cocoindex.resources.chunk import Chunk
from cocoindex.resources.file import FileLike, PatternFilePathMatcher
from cocoindex.resources.id import IdGenerator

DATABASE_URL = os.getenv("POSTGRES_URL", "postgres://cocoindex:cocoindex@localhost/cocoindex")
TABLE_NAME = "code_embeddings"
EMBED_MODEL = "sentence-transformers/all-MiniLM-L6-v2"

PG_DB = coco.ContextKey[asyncpg.Pool]("code_embedding_db")
EMBEDDER = coco.ContextKey[SentenceTransformerEmbedder]("embedder", detect_change=True)

_splitter = RecursiveSplitter()

@dataclass
class CodeEmbedding:
    id: int
    filename: str
    code: str
    embedding: Annotated[NDArray, EMBEDDER]
    start_line: int
    end_line: int

@coco.lifespan
async def coco_lifespan(builder: coco.EnvironmentBuilder) -> AsyncIterator[None]:
    async with asyncpg.create_pool(DATABASE_URL) as pool:
        builder.provide(PG_DB, pool)
        builder.provide(EMBEDDER, SentenceTransformerEmbedder(EMBED_MODEL))
        yield
```

### Define file processing

With the row schema and shared resources in place, we can write the actual work: turning a file into rows. 

#### Process file

```python
@coco.fn(memo=True)
async def process_file(
    file: FileLike,
    table: postgres.TableTarget[CodeEmbedding],
) -> None:
    text = await file.read_text()
    language = detect_code_language(filename=str(file.file_path.path.name))
    chunks = _splitter.split(
        text,
        chunk_size=1000,
        min_chunk_size=300,
        chunk_overlap=300,
        language=language,
    )
    id_gen = IdGenerator()
    await coco.map(process_chunk, chunks, file.file_path.path, id_gen, table)
```

`process_file` runs once per file. It reads the file, detects the language so Tree-sitter can parse it, [splits the code](https://cocoindex.io/docs/ops/text/) along the syntax tree, and maps each chunk to `process_chunk`. 

Each chunk is a coherent syntactic unit, so retrieval returns whole functions or blocks, never a fragment cut mid-statement. All major languages are supported (Python, Rust, JavaScript, TypeScript, Java, C++, and more); unknown types fall back to plain text.

Note that [`@coco.fn`](https://cocoindex.io/docs/programming_guide/function/) with [`memo=True`](https://cocoindex.io/docs/advanced_topics/memoization_keys/) is what makes this incremental: if a file's content and this function's code are both unchanged, the whole file is skipped on the next run. `coco.map` fans out to one `process_chunk` call per chunk.

Here is what chunking produces: each file is split into syntactic chunks, each with its own location and text.

#### Process chunk

Next, we embed the chunk with the shared embedder and declare the target row. 

```python
@coco.fn
async def process_chunk(
    chunk: Chunk,
    filename: pathlib.PurePath,
    id_gen: IdGenerator,
    table: postgres.TableTarget[CodeEmbedding],
) -> None:
    embedding = await coco.use_context(EMBEDDER).embed(chunk.text)
    table.declare_row(
        row=CodeEmbedding(
            id=await id_gen.next_id(chunk.text),
            filename=str(filename),
            code=chunk.text,
            embedding=embedding,
            start_line=chunk.start.line,
            end_line=chunk.end.line,
        ),
    )
```

We use [`SentenceTransformerEmbedder`](https://cocoindex.io/docs/ops/sentence_transformers/) with `all-MiniLM-L6-v2`; there are 12k+ sentence-transformer models on [Hugging Face](https://huggingface.co/models?other=sentence-transformers), so swap in whichever you prefer. Note `chunk.start.line` and `chunk.end.line`: V1 carries line numbers through, so search results point straight at the lines that matched.

### Define the main function

`app_main` wires the source to the target. It mounts the Postgres table (with a [vector index](https://cocoindex.io/docs/common_resources/vector_schema/)), walks the codebase, and mounts one [processing component](https://cocoindex.io/docs/programming_guide/processing_component/) per file.

```python
@coco.fn
async def app_main(sourcedir: pathlib.Path) -> None:
    target_table = await postgres.mount_table_target(
        PG_DB,
        table_name=TABLE_NAME,
        table_schema=await postgres.TableSchema.from_class(
            CodeEmbedding, primary_key=["id"],
        ),
    )
    target_table.declare_vector_index(column="embedding")

    files = localfs.walk_dir(
        sourcedir,
        recursive=True,
        path_matcher=PatternFilePathMatcher(
            included_patterns=["**/*.py", "**/*.rs", "**/*.toml", "**/*.md", "**/*.mdx"],
            excluded_patterns=["**/.*", "**/target", "**/node_modules"],
        ),
        live=True,  # watch for changes; pass -L to `cocoindex update` to run live
    )
    await coco.mount_each(process_file, files.items(), target_table)
```

We walk the codebase from `sourcedir` (point this at the repository you want to index). We index files with the extensions `.py`, `.rs`, `.toml`, `.md`, `.mdx`, and skip dot-directories, `target`, and `node_modules`.

`mount_table_target` creates and manages the Postgres table for you: schema, the pgvector index, idempotent upserts, and orphan cleanup when a file disappears. `live=True` makes the [filesystem source](https://cocoindex.io/docs/connectors/localfs/) [watch for changes](https://cocoindex.io/docs/programming_guide/live_mode/), and `mount_each` runs one component per file so the engine can track and update them independently.

### Create the App

Bind `app_main` into a `coco.App` and point it at the codebase root.

```python
app = coco.App(
    coco.AppConfig(name="CodeEmbeddingV1"),
    app_main,
    sourcedir=pathlib.Path(__file__).parent / ".." / "..",  # index from repo root
)
```

That is the entire indexing path.

## Run the pipeline

Run the [`cocoindex` CLI](https://cocoindex.io/docs/cli/) to set up and update the index. Choose catch-up (scan, sync, exit) or live (catch up, then keep watching):

```sh
# Catch-up run
cocoindex update main

# Live run: keep watching for file changes
cocoindex update -L main
```

You'll see the index update state in the terminal:

```text
✅ app_main: 1 total | 1 added
✅ declare_target_state_with_child: 1 total | 1 added
✅ _MountEachLiveComponent.process: 1 total | 1 added
✅ process_file: 622 total | 622 added
⏳ Elapsed: 43.4s
```

## Query the index

We match user text against the index with a plain SQL query, reusing the *same* embedder from the indexing flow so indexing and querying stay consistent.

```python
async def query_once(pool, embedder, query: str, *, top_k: int = 5) -> None:
    query_vec = await embedder.embed(query)
    async with pool.acquire() as conn:
        rows = await conn.fetch(
            f"""
            SELECT filename, code, embedding <=> $1 AS distance, start_line, end_line
            FROM "{TABLE_NAME}"
            ORDER BY distance ASC
            LIMIT $2
            """,
            query_vec, top_k,
        )
    for r in rows:
        score = 1.0 - float(r["distance"])
        print(f"[{score:.3f}] {r['filename']} (L{r['start_line']}-L{r['end_line']})")
        print(f"    {r['code']}")
        print("---")
```

The `<=>` operator is pgvector's cosine distance. We turn it into a similarity score and print the filename, the matched line range, and the code snippet. Run it against your index:

```bash
python main.py "embedding"
```

The search results print in the terminal:

## Incremental updates

You never compute a diff or write update logic: you change something, and CocoIndex works out what to embed, upsert, and delete. `@coco.fn(memo=True)` decides what to *recompute*: a file is skipped when its content and the function's code are both unchanged, and an embedding is reused when its chunk text is unchanged. `mount_table_target` decides what to *write*: each row's `id` is derived from its chunk's content, so only rows that actually changed are upserted, and rows whose source is gone are deleted.

The same machinery covers two kinds of change: changes to your **data** (the code being indexed) and changes to your **logic** (the pipeline itself).

**Data changes.**

- **A file is added**: only that file is chunked and embedded, and its rows are inserted. The rest of the repo is untouched.
- **A file is deleted**: its rows are removed from the target.
- **A file is edited**: the file is re-chunked, and the new chunks usually overlap the old ones. Chunks whose text is unchanged keep their `id` and embedding, so they are left as-is; genuinely new chunks are embedded and inserted; chunks that no longer exist are deleted. Edit one function and only that function's chunks are re-embedded, even though the whole file was re-read.

**Logic changes.** A pipeline change is reconciled the same way: CocoIndex compares the new output against what is already in Postgres and applies only the difference.

- **Change the file patterns** (`included_patterns` / `excluded_patterns`): files that now match are added automatically; files that no longer match have their rows deleted automatically.
- **Tune the chunking** (chunk size, overlap): files are re-chunked, producing the same partial-overlap diff shown above: unchanged chunks are no-ops, new chunks are embedded and inserted, dropped chunks are deleted.
- **Swap the embedding model**: the vectors genuinely change, so all embeddings are recomputed, but row identity is stable: it is an in-place update of the `embedding` column, with no rows added or removed.

A catch-up run (`cocoindex update main`) does this once and exits; live mode (`cocoindex update -L main`) keeps watching and applies each change as you code.

## CocoIndex Code

If you'd rather not wire the pipeline yourself, [CocoIndex Code](https://github.com/cocoindex-io/cocoindex-code) is an end-to-end implementation of exactly this indexing, packaged as a CLI and an MCP server. It does the same thing the example above does: AST-aware chunking, incremental re-index on file changes, local embeddings by default.

You can plug it straight into your coding agent or code-review agent:

- **Claude Code skill:** `npx skills add cocoindex-io/cocoindex-code`, then invoke `/ccc`.
- **MCP server:** `claude mcp add cocoindex-code -- ccc mcp` (Codex, OpenCode, Cursor, and any MCP client work the same way).
- **CLI:** `ccc index` to build the index, `ccc search "where we embed chunks"` to query it.

The agent gets the whole repository as semantic context instead of reading one file at a time.

## Next steps

The full, runnable example is in the CocoIndex repo: [examples/code_embedding](https://github.com/cocoindex-io/cocoindex/tree/main/examples/code_embedding), with a walkthrough in the [index-codebase example](https://cocoindex.io/docs/examples/index-codebase/).

- Point `sourcedir` at your own repository.
- Swap the embedding model or the target store; the pipeline is plain Python.
- Read the [CocoIndex V1 docs](https://cocoindex.io/docs/) for more on incremental processing, components, and targets.

Issues and contributions are welcome on [GitHub](https://github.com/cocoindex-io/cocoindex).

## Sitemap

- [Blog index](https://cocoindex.io/blogs/)
- [Site index (llms.txt)](https://cocoindex.io/llms.txt)
- [Full blog corpus](https://cocoindex.io/llms-full.txt)
- [Markdown sitemap](https://cocoindex.io/sitemap.md)
- [XML sitemap](https://cocoindex.io/sitemap.xml)
- [RSS feed](https://cocoindex.io/blogs/rss.xml)