Vibhor7-7

Vibhor7-7 / Cortex-CxC

Public

Cortex is a 3D visual memory layer for AI chats that summarizes relevant past conversations using Hydrid search (keyword + semantic) and feeds relevant content to the LLM via Custom MCP so users never start a chat from scratch again.

15
3
100% credibility
Found Feb 13, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
HTML
AI Summary

Cortex is a local application that imports AI chat histories, visualizes them in interactive 3D clusters, and helps generate context-aware prompts or integrate memories directly into new chats.

How It Works

1
🔍 Discover Cortex

You hear about a tool that turns your scattered AI chat histories into a beautiful 3D memory map, so you never repeat yourself again.

2
🚀 Launch locally

Download and start the app on your computer—it runs everything privately without needing accounts or online services.

3
📤 Upload chat exports

Drag in HTML files from your ChatGPT or Claude conversations, and watch them magically organize themselves.

4
✨ See your memory galaxy

Your past chats appear as glowing points in 3D space, grouped into colorful clusters by topic, ready to explore.

5
Find relevant memories
💡
Generate smart prompt

Pick key chats to create a perfect starting message for your next AI session.

🤖
Feed to your AI

Connect directly so your AI assistant pulls in the right context automatically.

🎉 Chats that remember

Your AI conversations now flow seamlessly with full context from the past—no more starting from scratch.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 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 Cortex-CxC?

Cortex-CxC turns scattered AI chat histories into a searchable 3D visual memory layer, letting you upload HTML exports from ChatGPT or Claude, summarize conversations with hybrid keyword+semantic search, and visualize them as clustered nodes in a WebGL space mimicking cortex visual areas like V1-V4. It feeds relevant past context to new LLMs via a custom MCP server, so chats pick up where you left off—built in Python with FastAPI backend, Ollama for local embeddings/summarization (qwen2.5, nomic-embed-text), and JS frontend. No cloud APIs needed; everything runs locally.

Why is it gaining traction?

The 3D cortex github visualization hooks users tired of flat lists—zoom through chat clusters like a visual cortex MRI, with smooth animations and topic-based naming. MCP integration slots it directly into Claude or ChatGPT workflows (cortex github llm, cortex github app), while hybrid search beats pure semantic misses on specifics. Local-first setup with Ollama means instant privacy, no vendor lock-in.

Who should use this?

AI researchers juggling long-term projects across chats, like cortex github minecraft modders or cortex github nvidium tinkerers needing persistent context. Devs building cortex github integration for local agents, or power users analyzing chat patterns (cortex visual elon musk ideas, again chat histories). Skip if you want zero setup—needs Ollama models pulled first.

Verdict

Early alpha (15 stars, 1.0% credibility score) with solid docs and seed data scripts, but test coverage lags—run init_db.py and ingest a few exports before production. Worth forking for personal cortex github debug or thehive-like memory if you live in AI chats; otherwise, watch for polish.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.