🥥CocoIndex
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
momentum
durability
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
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 8k 2026-05-06
- 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.
- 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
-
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.