Skip to content
repository radar
Agents & Orchestration

🥥CocoIndex

ACTIVE BREAKOUT

cocoindex-io/cocoindex · homepage ↗

Incremental engine for long horizon agents 🌟 Star if you like it!

⭐ Very popular: 11k stars, gaining about 103 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
language Rust
license Apache-2.0

momentum

total stars 11k
stars added last week +103
used by 53 repos & packages
commits / week 11 cooling · -58% vs prior mo
issues closed 87% ~4d to close, median
contributors 89
release cadence weekly
last activity 3d ago

durability

backing community / independent independent
openness permissive
bus factor 2 concentrated
top-author share 43% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 890/mo (+11%/mo) · + 3k total since PR#33

why it's a big deal

  • Keeps AI agents and LLM apps working from continuously fresh context by transforming sources like codebases, meeting notes, Slack, PDFs, and video into indexed data.
  • Reprocesses only the delta on each change rather than re-indexing everything, which cuts the cost and latency of keeping large corpora current.
  • Aimed at developers building RAG systems, code indexing, and knowledge graphs who need indexes to stay in sync with changing source data.

under the hood

  • Models pipelines as target equals a function of source, a persistent-state-driven dataflow where you declare the desired target state and the engine keeps it in sync with source and code.
  • Core engine is written in Rust with a Python interface for declaring flows, and is designed to run parallel by default.
  • Ships connectors for targets including Postgres with pgvector, LanceDB, Neo4j, Kuzu, SurrealDB, and Kafka, and is licensed Apache 2.0 with about 11k stars.

Radar summary, generated from the project's public sources

star history

PR#33 · 8k11k now Mar 2025Aug 2026
  1. PR#33 8k 2026-05-06
  2. now 11k + 3k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Quietly building: more output than attention, for now.

+15 understory score output 84 · clout 69
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#33 2026-05-06 below the radar

    Data transformation framework for AI

similar projects

compare these →
  • 📚 Haystack

    Python · 2.3× the stars

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE
  • 🗜️ headroom

    Python · 5.9× the stars

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    66k ACTIVE
  • 🧠 LangGraph

    Python · 3.5× the stars

    Build resilient agents.

    40k ACTIVE

comments

Sign in with GitHub to add your blip on CocoIndex.

loading comments…