cognee

Open Source Memory Platform for Agents

[cognee @cognee_]

Agents forgetting everything once the room closes bugged us too.
We fixed it together with @band_hq
See you at the hackathon in SF 🚀

[Band @band_hq]

Restart an agent and three weeks of decisions disappear with it. @cognee_'s new integration gives any BAND agent a memory that outlasts the room. Each BAND room becomes a Cognee session: before your agent answers, it recalls what's relevant, and after it answers, the exchange is stored and later consolidated into a knowledge graph. It wraps the adapter you already have, so LangGraph, Anthropic, CrewAI, and Pydantic AI agents get it without touching their prompts.

The memory is also shared. Tell Claude Code something in your terminal, let it sync, then ask your BAND agent in a room. It knows.

We wrote it up with the Cognee team, including why a memory outage should never come out as "I have no record of that." Read now: https://t.co/a4fDve4sAz

[cognee @cognee_]

Hackathon in SF on Saturday, Nov 14:
Hive Mind, building agent teams

Build a team of agents that finishes a real task, using @hcompany_ai, @superlinked, @band_hq and @cognee_

$2k + credits, food provided :)
Spots are filling up quickly, so apply soon: https://t.co/9icpGyd3f1

[cognee @cognee_]

Check new a16z report!

[Justine Moore @venturetwins]

Messaging -
1) Phone numbers: @thelinqapp, @sendbluehq, @blooio_messages, @Cherthq, @zerosettle, @inkbox_ai, @PhotonHQ
2) Email & inbox: @resend, @openmailsh, @agentmail, @agentemailco, @nylas

Memory & personalization -
@mem0ai, @supermemory, @honchodotdev, @zep_ai, @tryrollup, Tastegraph, @cognee_, @Qloo, @LangChain, @Data_Cloud_, @Redisinc, Configure, @Vectorizeio, @EgoistMachines

(cont ⬇️)

[cognee @cognee_]

@venturetwins @omooretweets @descript @TownAI @wabi @instinct @Muse @ExaAILabs @thelinqapp @resend @agentcardhq @bot @OpenAI @instinct_inc @interaction @tomo @nozomioai @hark_labs @wajo_ai @itsdazzleai @thesznai @kickerai @orchid_hq @humansand @try_caddy @boski @meetlucasai @UnderdogAI @AsmiAIOriginal @tryorbits @ohaidotai @GoogleLabs @fambotAI @textdotai @sendbluehq @blooio_messages @Cherthq @zerosettle @inkbox_ai @PhotonHQ @openmailsh @agentmail @agentemailco @nylas @mem0ai @supermemory @honchodotdev @zep_ai @tryrollup Thanks for the mention!

[cognee @cognee_]

🗽 LOCALHOST NYC: Sovereign AI Hackathon

No one should own your AI except for you!

We are excited to bring together builders, researchers, and AI enthusiasts in NYC to explore the future of sovereign AI!

Partners:
@superlinked
@TinfoilAI
@darkbloomai
@variantfund

Organizers:
@DistributedMarz
@BrennerSpear

📍 The School, Brooklyn, NYC
💰 $10K in prizes + infrastructure credits
Let's build the future of open and sovereign AI together!
🔗 Register: https://t.co/hbqzTawQ1g

[cognee @cognee_]

That's a wrap on the @bot Community Engineering Hackathon in London, where cognee was one of the technology partners.

130 people checked in and built 49 projects for real community problems in one evening.

Top 3:
• Offpeak by Daniils Petrovs
• After Glow by @lukadadiani
• Lumap by Francesco Coccia

Organised by @frankterpo, @lnv007 and @keanucz, with help from @benln and @sunrao.

Venue partner
• @Expedite_Now, made possible by William Schulz

Technology partners
• @supabase (Isabelle Roser)
• cognee (@KovacVeljko & Luca Stromann)
• @zero_gtm (Mariia Nedelkina)
• @NotionHQ (Waseef Mohammad Khan)
• SpaceXAI Community (@frankterpo)

Community partners
• @unicorn_mafia (@CharlieCheesma1)
• @basedfounderseu (@fatemallk)
• @kickstartldn (@ilyavencjuns)
• Hackradar (Keanu)
• @UKAIagents (@may_tohoku & Minghan Xiao)
• @UseCorgi (@claudiaamaggi)
• Night Office (Oli Kingshott & Shreyas Raghu)
• @hackcollective (Louis)
• United Italian Societies (@belluzzoumberto)
• @outpostcrew (@Andy_AJT & @oscarfalll)
• AI Pilled (Nuan Zhang & Yiran Qin)
• @ICEntrepreneurs
• Other (@ZakeeAbdi, @fergomg)

Judges: Charlie, Fatema, May, Claudia, Shreyas, Louis, Umberto, Oscar, Andy, Nuan, @HelaHalas and Luca

Food by Ambuca Bakery

Thanks to everyone who joined. Looking forward to the next one!

[cognee @cognee_]

We'll be there!

[dmarz ⚡️🤖 @DistributedMarz]

People keep asking me where the open source AI and private AI people in New York 🗽 are. Instead of a million group chats, I'm bringing them together for a day of hacking and discussion on Saturday November 7th. No one should own your AI except for you. Welcome to LOCALHOST ⬇️

[cognee @cognee_]

Always great to see our ambassadors working on cool projects!

[cognee @cognee_]

Use @cognee_ as the memory layer for your @n8n_io workflows!

[n8n.io @n8n_io]

Every LLM call starts from zero. Agent memory fixes that. Our new guest post with @cognee_ breaks down memory architectures, their trade-offs, and how to give n8n agents persistent, shared memory. https://t.co/x73jdd83o8

[cognee @cognee_]

@n8n_io hosted their first conference, In the Loop, in Berlin. It was an amazing event, and a pleasure to meet everyone who joined, talk to the organizations attending and have so many great chats with you.

Thanks to the @n8n_io team for having us, and to everyone who stopped by. Looking forward to future collaborations!

[cognee @cognee_]

Join our webinar on Wednesday 4 November.

As soon as several agents and teams work on the same memory, permissions stop being an afterthought.

Our founder and CEO @tricalt will show you how @cognee_ handles permissions for agent memory.

Wednesday 4 November, 18:00 to 19:00 CET
9:00 AM PT / 12:00 PM ET
Online, on Zoom
For teams running AI agents on shared company data

Register here: https://t.co/kyplpXAUEj

[cognee @cognee_]

A memory system can top a benchmark and still not help your agent finish its tasks.

The benchmarks guide points to MemoryArena, which found that "systems performing well on benchmarks such as LoCoMo can still have low task-completion rates." Recall is not the same as useful recall.

The useful test is the boring one: memory on vs memory off, on your own workload.

DoorDash ran that test over a 7-day production window for its Ask DoorDash assistant and reported:
• ~24% higher relative checkout conversion in grocery
• ~15% higher relative conversion on restaurant-assistant queries
• ~33% less likely to misunderstand user intent

Public benchmarks are a sanity check. The number that matters is what your agent does differently with memory than without it.

[cognee @cognee_]

RAG and agent memory get used as synonyms. They aren't.

RAG reads from a corpus that someone else wrote: docs, a wiki, a product catalogue. The agent only reads.

Agent memory starts when the agent writes back:
→ a preference the user mentioned
→ the outcome of a task it just finished
→ a correction someone made to its answer

Writing back changes the problem. You now decide what is worth keeping. You merge the new fact with what's already stored, and you handle the old fact it contradicts.

Cognee's agent memory guide puts it in one line: "The moment your system starts writing back — capturing facts, recording previous interactions, or storing the outcomes of its own work — you've moved beyond RAG into agentic memory."

Read-only retrieval is a search problem. Read-write retrieval is a data-management problem.

Read more here: https://t.co/cShlEjAlxa

[cognee @cognee_]

@hackcollective with @lnv007
United Italian Societies with @belluzzoumberto
@outpostcrew with @Andy_AJT and @oscarfalll
plus Night Office, AI Pilled and @ZakeeAbdi

Credits and prizes from @bot, @cursor_ai, @supabase, @zero_gtm and @cognee_ (@KovacVeljko)

[cognee @cognee_]

@bot LDN Community Hack is this Thursday, and @cognee_ is a tech partner.

Come build with @grok + @cognee_ this Thursday.

@bot LDN Community Hack by @frankterpo, with @supabase, @zero_gtm and @cursor_ai as tech partners and @Expedite_Now hosting.

Eleven London communities are taking part.

Free, last spots open:
https://t.co/Do3PGfmPtT

[cognee @cognee_]

Also organised by @lnv007 and @keanucz, together with these communities:

@unicorn_mafia with @fergomg and @CharlieCheesma1
@basedfounderseu with @fatemallk
@kickstartldn with @ilyavencjuns
Hackradar with @keanucz
@UKAIagents with @may_tohoku
@UseCorgi with @claudiaamaggi

[cognee @cognee_]

How cognee + scalekit hack went recently

[Tamilselvi Ramasamy @Tamil_2399]

this was @scalekitinc's 5th hackathon for the year, and i think we're getting better at figuring out how much people can actually build in less than 4 hours!

a little late, but here's a recap from our SF @Techweek_ hackathon with @cognee_ and @RespanAI!

the challenge: build a company brain that could pull context from different tools, remember things, and actually take action with the right access.

we had 8 solid submissions by the end of the evening, and some really fun demos. thanks to everyone who showed up and built with us. and to @tricalt and @HendrixLiu29208 for putting this together with us!

[cognee @cognee_]

Four corners in the ring this Saturday: @Claude_Memory, @helixdb, cognee, and whatever memory setup you bring.

Same scenarios for every system, results live. Mem-Off, San Francisco, Sat 17 Oct.

Free: https://t.co/76dazKtv68

[cognee @cognee_]

It's coming, people.

[Vasilije @tricalt]

Sneak-peek of the new Cognee UI