cocoindex
With CocoIndex, users declare the transformation, CocoIndex creates & maintains an index, and keeps the derived index up to date based on source update, with minimal computation and changes.
Decision gist · record as of 2026-08-14
Yes, if you are building AI agents or LLM applications that need fresh context and want to avoid the cost and latency of full re-indexing on every update. The incremental engine, Rust-backed performance, and Apache 2.0 license make it production-ready. Install friction is moderate due to dependencies, but wheels are widely available. No security vulnerabilities are known. Not necessary if your data is small, infrequently updated, or you don't need real-time freshness.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.11 or later; async/await syntax required; depends on external connectors (e.g., PostgreSQL) for target storage.
- Medium install friction due to 8 runtime dependencies including numpy and psutil, but wheels are available for modern Python versions (3.11–3.14) across macOS, Linux, and Windows.
- Package is actively maintained with a release just 2 days old.
License · maintenance · safety
permissive license (permissive) — Licensed under Apache 2.0 (permissive), which allows commercial use, modification, and distribution with minimal restrictions—suitable for both open-source and proprietary projects.
last release 2026-08-12 (2 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 102,206 downloads/mo, #12,884 on PyPI
Alternatives
Verify before relying
pip install cocoindex
import cocoindex as coco
from cocoindex.connectors import localfs, postgres
from cocoindex.ops.text import RecursiveSplitter
@coco.fn(memo=True)
async def index_file(file, table):
for chunk in RecursiveSplitter().split(await file.read_text()):
table.declare_row(text=chunk.text)
@coco.fn
async def main(src):
table = await postgres.mount_table_target(PG, table_name="docs")
await coco.mount_each(index_file, localfs.walk_dir(src).items(), table)
coco.App(coco.AppConfig(name="docs"), main, src="./docs").update_blocking()- Whether the Rust engine and incremental computation actually reduce re-embedding cost in practice for large corpora.
- Performance characteristics and scalability limits when processing petabyte-scale stores.
- Availability and maturity of connectors beyond localfs and postgres.
- Whether the package is suitable for real-time streaming or primarily batch-oriented workflows.
What it is and what it does
CocoIndex is a Python library that builds and maintains live indexes of source data—codebases, documents, PDFs, Slack messages, and videos—for AI agents and LLM applications. Rather than re-processing entire datasets on each update, it uses an incremental engine to identify and recompute only the changed portions (the delta), keeping derived indexes fresh without the overhead of full re-embedding or re-indexing cycles. The library is built on a Rust core for production-grade performance and includes connectors for common sources (local filesystems, databases) and targets (PostgreSQL, vector stores).
You declare your transformation logic in Python using decorators and async functions, then CocoIndex handles the incremental scheduling, change propagation, and state management. It's designed for data engineering workflows in AI—particularly RAG pipelines and agent context management—where stale or incomplete data undermines agent reasoning. The package supports modern Python (3.11–3.14), runs on macOS, Linux, and Windows, and carries no known security vulnerabilities.
Use it for
- Keep a RAG vector store continuously fresh as source documents change, re-embedding only modified or new chunks.
- Maintain a live codebase index for AI coding agents, updating only files that have changed since the last run.
- Build an incremental ETL pipeline that transforms and loads data into a data warehouse, processing only deltas.
- Index meeting notes and Slack messages in real-time for agent context without re-processing the entire conversation history.
- Reconcile changes across joined or looked-up records in a data pipeline without touching unchanged rows.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building AI agents or LLM applications that need fresh context and want to avoid the cost and latency of full re-indexing on every update.
The incremental engine, Rust-backed performance, and Apache 2.0 license make it production-ready. Install friction is moderate due to dependencies, but wheels are widely available. No security vulnerabilities are known. Not necessary if your data is small, infrequently updated, or you don't need real-time freshness.
Install
cocoindex on PyPI
Before you install
Medium install friction due to 8 runtime dependencies including numpy and psutil, but wheels are available for modern Python versions (3.11–3.14) across macOS, Linux, and Windows. Package is actively maintained with a release just 2 days old.
Requires Python 3.11 or later; async/await syntax required; depends on external connectors (e.g., PostgreSQL) for target storage.
License in practice
Licensed under Apache 2.0 (permissive), which allows commercial use, modification, and distribution with minimal restrictions—suitable for both open-source and proprietary projects.
Quickstart
pip install cocoindex
import cocoindex as coco
from cocoindex.connectors import localfs, postgres
from cocoindex.ops.text import RecursiveSplitter
@coco.fn(memo=True)
async def index_file(file, table):
for chunk in RecursiveSplitter().split(await file.read_text()):
table.declare_row(text=chunk.text)
@coco.fn
async def main(src):
table = await postgres.mount_table_target(PG, table_name="docs")
await coco.mount_each(index_file, localfs.walk_dir(src).items(), table)
coco.App(coco.AppConfig(name="docs"), main, src="./docs").update_blocking()Verify before relying
- Whether the Rust engine and incremental computation actually reduce re-embedding cost in practice for large corpora.
- Performance characteristics and scalability limits when processing petabyte-scale stores.
- Availability and maturity of connectors beyond localfs and postgres.
- Whether the package is suitable for real-time streaming or primarily batch-oriented workflows.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.11 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 8 packagestyping-extensionsclickrichpython-dotenvwatchdognumpypsutilmsgspec |
| Maintenance | Actively maintained 2 days since the last release |
| First released | |
| Downloads | 102,206 / month, #12,884 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseNatural Language :: EnglishOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: Free Threading :: 2 - BetaProgramming Language :: RustTopic :: Software Development :: Libraries :: Python ModulesTopic :: Text Processing :: IndexingTyping :: Typed |
Evidence: cocoindex-1.0.20-cp311-abi3-macosx_10_12_x86_64.whl; cocoindex-1.0.20-cp311-abi3-macosx_11_0_arm64.whl; cocoindex-1.0.20-cp311-abi3-manylinux_2_28_aarch64.whl; cocoindex-1.0.20-cp311-abi3-manylinux_2_28_x86_64.whl; cocoindex-1.0.20-cp311-abi3-win_amd64.whl; cocoindex-1.0.20-cp314-cp314t-macosx_11_0_arm64.whl; cocoindex-1.0.20-cp314-cp314t-manylinux_2_28_aarch64.whl; cocoindex-1.0.20-cp314-cp314t-manylinux_2_28_x86_64.whl; cocoindex-1.0.20-cp314-cp314t-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “incremental indexing for ai agents”
- cocoindexCocoIndex maintains a live, incrementally-updated index of codebases,…
- code-review-graphBuilds a structural knowledge graph of your codebase using…
- memsearchMemsearch builds a searchable semantic memory index from markdown…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also graphiti-core · llama-index-vector-stores-chroma · haystack-ai · llama-index-core · llama-index-vector-stores-milvus · composio-core · llama-index-vector-stores-qdrant · qwen-agent · google-agents-cli · chroma-mcp