Загрузка видео...

Не удалось загрузить видео

На главную

Knowledge graphs are insanely good at giving agents human-like memory! Today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. It's built using a real-time knowledge graph. 100% open-source and self-hosted.

156,446 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Tech stack: - @zep_ai's Graphiti as a memory layer - @neo4j to store the knowledge graph - @Docker to self host the MCP server Find all the code here:

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

@neo4j @Docker If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️ For more insights and tutorials on LLMs, AI Agents, and Machine Learning!

Фото профиля Coral AI News
Coral AI News2 лет назад

Coral AI is the most powerful AI for documents. See the difference yourself:

Фото профиля Avi Chawla
Avi Chawla1 год назад

This is much needed functionality to work across multiple MCP hosts. Great way to solve it. Thanks Akshay

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Absolutely! 💯 You don't have to switch context while switching apps!

Фото профиля Sumanth
Sumanth1 год назад

Memory layer that can be shared across all the AI apps. This is Incredible. Thanks for sharing Akshay, Great demo!

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Thank You Sumanth! 🙏

Фото профиля guille
guille1 год назад

The downside to using knowledge graphs is that there aren't any good graph databases on the market. Neo4j is expensive, power-hungry, and not very flexible, good open source alternatives are needed

Фото профиля ultravioleta🔺
ultravioleta🔺1 год назад

this is savage

Фото профиля Arindam Majumder 𝕏
Arindam Majumder 𝕏1 год назад

Wow! This is Amazing

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

Glad you liked it Arindam!

Похожие видео

RAG might already be becoming obsolete. A month ago, Andrej Karpathy dropped a simple GitHub gist called “LLM Wiki.” Now the comments section looks like the birth of an entirely new AI category. 5000+ stars later, developers are rapidly building: • persistent AI memory systems • self-maintaining knowledge bases • multi-agent research environments • contradiction detection engines • AI-native company operating systems • local-first memory architectures • graph-based reasoning layers • evolving second brains And the craziest part? Most of them were built in DAYS. Because the core idea is insanely powerful: Instead of AI repeatedly retrieving raw chunks like traditional RAG… …the model continuously maintains a living knowledge system. Not temporary context. Persistent synthesis. The shift sounds subtle until you realize what it changes: RAG: retrieve → answer → forget LLM Wiki: ingest → synthesize → evolve That one architectural difference is causing an explosion of experimentation right now. People are already building: • agent memory operating systems • AI-maintained engineering documentation • self-healing knowledge graphs • persistent research environments • conversational memory architectures • contradiction-aware wikis • context compression engines • machine-readable company systems The comments section alone feels like watching an ecosystem form in real time. One developer built deterministic contradiction detection using sheaf cohomology Another built “sleep consolidation” for AI memory systems inspired by human memory formation Another created persistent multi-agent vault conversations Another turned entire repositories into continuously maintained AI wikis Another built local-first memory systems with audit trails, provenance, graph exports, and MCP integration This is the important part: Karpathy didn’t launch a product. He introduced a pattern. And patterns are what create ecosystems. The same way: • transformers created modern AI • RAG created AI retrieval startups • agents created orchestration frameworks LLM Wikis may create persistent AI memory infrastructure. That’s why this moment feels different. For years, AI systems have been stateless. Now developers are trying to build systems that actually accumulate understanding over time. And once knowledge compounds instead of resetting… …the entire interface layer of AI changes. (Link in comments)

Suryansh Tiwari

141,154 просмотров • 1 месяц назад