meitarbe

meitarbe / cognetivy

Public

The open-source state layer for AI coding agents. Turn chaotic agent sessions into structured, traceable workflows with a local workspace for runs, events, and collections.

github.commeitarbecognetivy agents ai workflows
33
2
100% credibility
Found Mar 02, 2026 at 33 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Cognetivy creates a local workspace to define workflows, track AI agent runs and events, and organize structured collections for coding assistants like Claude Code and Cursor.

How It Works

1
📁 Open your project folder

Head to the folder where you want a smart helper for your AI coding buddy.

2
🚀 Start with one click

Run a simple starter command to wake up the helper.

3
🤖 Pick your AI friend

Choose Claude Code, Cursor, or your favorite AI assistant from the friendly picker.

4
✨ Setup happens automatically

It builds your personal memory space and opens a beautiful dashboard in your browser.

5
💬 Chat with your AI

Tell your AI to plan steps and run a task, like exploring ideas on a topic.

6
📊 Watch results organize

See workflows track, data neatly collected, and everything become easy to review.

✅ Unlock repeatable AI power

Enjoy structured, traceable sessions you can rerun, compare, and perfect anytime.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 33 to 33 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is cognetivy?

Cognetivy is a TypeScript CLI tool that acts as an open source state layer for AI coding agents like Cursor, Claude Code, and OpenClaw. It transforms chaotic agent sessions into structured workflows, tracking runs, events, and schema-backed collections in a local .cognetivy/ workspace. Run `npx cognetivy` to init, define workflows via CLI or MCP, visualize in Studio UI, and persist data without LLMs or cloud.

Why is it gaining traction?

This open source state machine framework stands out by enforcing DAG workflows with topological execution, traceability fields like citations and derived_from, and MCP integration for agent tools. Unlike ephemeral GitHub Copilot chats, it offers self-hosted auditability and a read-only Studio for diffs, events, and collections—key for repeatable agent tasks in open source GitHub alternatives.

Who should use this?

Agent-heavy devs using Cursor or Claude Code for structured coding/research workflows, teams auditing AI outputs in regulated domains, or Cursor users wanting an open source GitHub Copilot alternative with persistent state machines over chaotic sessions.

Verdict

Promising early open source state machine tool (33 stars, 1.0% credibility score) with clear docs and CLI/MCP APIs—prototype it for agent traceability now. Maturity lags (low adoption, no tests visible), so pair with stable editors before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.