Index Your Codebase for AI Agents with CocoIndex V1

In this blog, we’ll build a live semantic index over a codebase with CocoIndex V1. 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 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, change tracking, managed targets) runs in a Rust engine underneath. Because the engine reprocesses only what has changed, the index stays in sync in near real-time. With a source that watches for changes, like the local filesystem in live mode, it becomes real-time: edit a file, and only the chunks that changed get re-embedded and re-upserted. That fits what an AI coding agent needs: fresh context, low latency, and no full rebuilds.

Use case

• Code context for agents — semantic context for Claude, Codex, OpenCode, Factory instead of file-by-file reading.
• 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:

• Syntax-aware chunking is built in. Tree-sitter integration means chunks follow real code structure (functions, classes, blocks) instead of arbitrary line windows, for every major language.
• Incremental updates suit code that changes constantly. Every commit, save, and rebase mutates a handful of files; CocoIndex re-embeds only the chunks that changed and re-upserts only the rows that moved, with no full re-index on a one-line edit.
• Live updates keep the index current. With live=True on the filesystem source and cocoindex update -L, the index keeps watching and applies changes with low latency instead of waiting for a nightly rebuild.
• Rust core handles scale. The engine is written in Rust and processes large codebases with little compute per change.
• Plain Python keeps it customizable. Pick your embedding model, chunking strategy, and vector database. The pipeline is ordinary async Python and your own types, so if your agent can write Python, it can extend this flow.
• Consistent indexing and query. The same embedder is shared between the indexing path and the query path, so what you index is what you search against.

Try it yourself

Fork the code and make it your own.

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.

Fork the example on GitHub →

Overview

From 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).

With CocoIndex, you declare the transformation logic 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), CocoIndex performs smart incremental processing that only reprocesses the minimum. And it keeps your code index always up to date.

Setup

In this example we store the indexed rows in Postgres with the pgvector extension. Your metadata and the vector search index both live there. CocoIndex supports many targets, 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 to start one.

   Copysh

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

2. Point CocoIndex at it

   Copysh

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

3. Install CocoIndex and the dependencies

   Copysh

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

Define the App

Apps are the top-level runnable unit in CocoIndex. It 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.

• First, CodeEmbedding defines one row of the output table: each chunk of code becomes one row, with its text, location, and embedding vector.
• Second, coco_lifespan provides the shared resources every step needs, the Postgres connection pool and the embedding model, once at startup, so they’re shared instead of rebuilt per file.

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

@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 along the syntax tree, and maps each chunk to process_chunk.

CocoIndex uses Tree-sitter to chunk code along its actual syntax structure rather than arbitrary line breaks. Because each chunk is a coherent syntactic unit, retrieval returns whole functions or blocks instead of fragments cut mid-statement, which preserves context for RAG.

Tree-sitter is a parser generator and an incremental parsing library, available in Rust.

All major languages are supported (Python, Rust, JavaScript, TypeScript, Java, C++, and more); unknown types fall back to plain text.

Note that @coco.fn with memo=True 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 embeds the chunk with the shared embedder and declares the target row.

@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 with all-MiniLM-L6-v2; there are 12k+ sentence-transformer models on Hugging Face, 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), walks the codebase, and mounts one processing component per file.

@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 watch for changes, and mount_each runs one component per file so the engine can track and update them independently. The vector index uses cosine similarity to match queries against the indexed code.

Create the App

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

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 to set up and update the index. Choose catch-up (scan, sync, exit) or live (catch up, then keep watching):

# 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:

✅ 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.

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:

python main.py "embedding"

The search results print in the terminal:

Incremental updates

CocoIndex keeps the index in sync with the codebase and does the minimum work to get there. You never compute a diff or write update logic: you change something, and CocoIndex works out exactly what to embed, upsert, and delete. Two pieces make this work. @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 it upserts only the rows that actually changed and deletes rows whose source is gone.

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 with low latency, so the index stays current as you code.

CocoIndex Code

If you’d rather not wire the pipeline yourself, 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), hardened for production.

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.

• Point sourcedir at your own repository.
• Swap the embedding model or the target store; the pipeline is plain Python.
• Read the CocoIndex V1 docs for more on incremental processing, components, and targets.

Issues and contributions are welcome on GitHub.

CocoIndex

An incremental engine for long-horizon agents — always-fresh, explainable data, one Python file.

Learn the concept → View on GitHub

About the author.

Linghua Jin Cofounder & CEO of CocoIndex · @linghuaj

CEO and cofounder of CocoIndex. Writes about incremental data infrastructure, agents, and the engineering decisions behind the engine.