cognee
Memory for AI Agents in 5 lines of code
402 followers
Memory for AI Agents in 5 lines of code
402 followers
cognee is an open-source semantic memory layer for LLM agents, built on vector & graph databases. It constructs knowledge graphs from retrieved data, enabling AI agents & chatbots to deliver accurate, context-aware responses.
The 2025 state of AI Development
cognee
@anitakirkovska Thank you Anita for your support!
OpenSauced
Humans in the Loop
@bdougieyo framing this
Congrats on the launch! 🔥 Love the focus on structured memory — feels like a crucial piece for taking AI agents to the next level. Excited to see where cognee goes next! 🚀
cognee
@yuliya_fomina Thank you! Looking forward to your launch
I am so, so excited about cognee!
Memory is the biggest problem for AI agents and cognee is doing this right! We've been using it for the past couple of months and the results are sooo much better!
Thanks, @vasilije_markovic1 ! Good luck going forward!
Wow! This looks promising! Congrats on the launch!
@antdro have a look!
cognee
Thank you@michael_vavilov! @antdro don't hesitate to ask if you have any questions!
Congrats on the launch! Great to see open-source AI tools popping up! Dropped my upvote on that!
cognee
@hugo_pochet Thank you Hugo!
unmess
This is amazing. How does this compare against something like Mem0? Hope I'm not mixing things up too much hahaha
cognee
@periodawindsy Hi Anil! Have a look at our evals here, we compared against Mem0 and our tool is more accurate -> https://github.com/topoteretes/cognee/tree/main/evals
unmess
@vasilije_markovic1 oh that is interesting... for me, mem0 setup was a bit complex (deployment side, tbh mostly due to my stack) so will try cognee and see how it fares for unmess!