Vasilije

We raised $7.5M to scale our knowledge engine that gives AI systems memory. LLMs are powerful, but they’re stateless — once a session ends, context is gone. Companies have their own context, rules and practices. There are no solutions out there that can bring this knowledge reliably to the LLMs. At @cognee_, we’re building a knowledge engine that allows AI systems to retain context, understand relationships, and dynamically update the knowledge over time. We raised $7.5M in seed funding led by @pebble_bed — founded by @pam_vagata (ex-founding engineer, @OpenAI) and @keithmadams (founder, @Facebook AI Research Lab) and @tammiesiew - with participation from @42Cap1 and @vermilionfund and angels like @JanOberhauser from @n8n_io, Charles Dolan, @alexcrdean, @matthausk, and @RomanStanek to scale up engineering, accelerate research, and increase number of cognee deployments to clients like @Bayer from 70+ to 700+. I want to thank the team, the open source community, and to our investors for the trust. If you are struggling with memory, our devs can get cognee running with your data in 7 days. Don’t hesitate to reach out to us.

Proud to announce @cognee_ has joined Berkeley Xcelerator-> rdi.berkeley.edu/xcelerator

@hanghuang_ If you are flying, why not rent in San Jose?

We left a comfortable life in Seattle to pay $7,000/mo for a 2-bedroom in Dogpatch and give up 7% of our company to YC. Founders who obsess over the "cost" miss the whole point: 1. The Pressure Cooker: In Seattle, we sprinted. In YC, we're flying. Accountability from our group partner and fellow batchmates have shaved months off our timeline. 2. The Network: Between YC and SF, the density is crazy. You can collison install 3 new users, interview a top 1% engineer, and meet with Tier-1 VCs for coffee all in one day. 3. The Brand: The day we launched on YC, the inbound from investors and founders was insane. It opens doors that no cold email ever could. There are a lot of ways to spend equity in a startup. But the 7% to YC is the highest ROI in the game.

@kenwuuuu Claude code

so what is the current industry standard to build agents? do people still use langchain/langgraph?

@craigzLiszt It can be quite harmful to label people that way if you are not qualified to do so

i have yet to meet a founder who is not a narcissist or narcissist leaning

@amruthapotnuru What is windian?

planning a meet up for only windian couples in Dolores Park. dm for info

Do agents dream of electric Dario Amodei and his post-labor visions?

Works like OpenClaw, kinda...

A guy just stopped me on the street in Soma to tell me that you can never stop authenticity and that true one always comes out

@utekkare Write us! social@cognee.ai

@tricalt this is so good. I could talk about this for hours. would love to chat!

@pistachiomatt You are such a Pistachio, Matt

@tricalt well done, this was a very, very well written ad. i clicked through!

to anyone wondering what my extraordinary ability is… im retarded (extraordinarily)

@kzitouni1 For e-commerce, sure

hot take: your idea is only cool if your revenue numbers say so.

@karpathy is LLM Wiki now known as Anthropic Wiki? We built 28 last weekend in Pebblebed office👇 github.com/topoteretes/co…

@michael_chomsky Cognee

I need a remote place I can store and manage my skills. What should I use?

@ivanburazin Use cognee

Memory and learning remain among the most important unsolved problems in the agent stack. Right now, the best solution is dumping things into markdown files. That's embarrassingly primitive for the problem we're trying to solve. And models don't actually learn on the job. You can give them context and compress their history, but they don't get better from the experience the way a human colleague does. Even if you do something five times, they can still mess it up on the sixth, leaving a huge gap between context and actual learning.

Anthropic and OpenAI seem to have hired everyone

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

@yoheinakajima Great read!

@sujaldkl Congrats. Now the fun starts

I was funded for my startup within 48 hours of the first intro. Before that, multiple VCs had passed on us. Here’s what I did differently: