workflowstacks
ai-agent

cocoindex: Power Real‑Time Data Indexing for Long‑Horizon AI Agents

Boost your AI agent’s context and knowledge graph with cocoindex’s incremental engine—ideal for founders building long‑term, data‑driven agents. 12k+ GitHub stars.

From the repo · “Incremental engine for long horizon agents 🌟 Star if you like it!”

11,740 stars+34★ this week921 forksRustGuide quality 8/10 · reviewed Oct 7Updated 10/22/2026100% free · open source
What it does

Cocoindex provides an incremental engine for long horizon agents, allowing founders to build AI agents with enhanced power and efficiency

When to use it
  • •Building autonomous agents that require prolonged operation
  • •Developing AI systems that need to learn from experience over time
  • •Creating agents that must adapt to changing environments or conditions
Ready-to-paste prompt
cargo run --example basic_agent -- -c config.toml
Heads up: Ensure you have the latest version of Rust installed (1.64 or higher) to avoid compatibility issues with Cocoindex
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/cocoindex && curl -fsSL https://workflowstacks.com/api/skills/cocoindex/claude-skill -o ~/.claude/skills/cocoindex/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How cocoindex: Power Real‑Time Data Indexing for Long‑Horizon AI Agents works
Codeflow
Free to inspect

Cocoindex: Power Real‑Time Data Indexing for Long‑Horizon AI Agents is a very large Rust project (~119k lines across 424 code files, plus 171 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~119k lines · 424 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Rust · Python
No API keys detected
Rust 51%Python 48%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    Cargo.toml
    Dependencies and the commands it exposes
  4. 4
    skills/cocoindex/SKILL.md
    Inside skills/ — an example of what the AI is told to do
  5. 5
    examples/AGENTS.md
    A worked example — copy this to get going
What's in each folder
skills/Prompts, skills & agent definitions6 files
examples/Examples you can copy413 files
docs/Documentation168 files
rust/Folder243 files
python/Folder231 files
dev/Folder21 files
benchmarks/Evaluations & benchmarks20 files
.github/CI / automation (GitHub Actions)15 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
cocoindex-io
Language
Rust
Category
ai-agent
Published
3/3/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/cocoindex.svg)](https://workflowstacks.com/skills/cocoindex?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,577
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,154
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,161
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 1,501
connectonion: Build Collaborative AI Agents Fast
Leverage connectonion’s Python framework to orchestrate multiple LLM agents that work together, ideal for founders building AI‑driven products. 1.5k+ GitHub stars.
ai-agent★ 1,717
tt-metal: Accelerate AI Kernel Development with Proven Library
tt-metal gives founders a high‑performance TT‑NN operator library and low‑level kernel model to speed up GPU‑based AI workloads. Ideal for teams building LLMs, diffusion or video generation on Tenstorrent hardware. 1.7k+ GitHub stars.
ai-agent★ 40,592
Simplify AI Context with OpenViking
Unify AI agent context management with OpenViking, designed for startup founders, backed by 26k+ GitHub stars