AI loses context. CortexDB fixes that. Durable memory for agents, copilots & assistants. SDKs, APIs & MCP-ready. By @pmalik

Joined March 2026
RAG retrieves history. Memory maintains continuity.
🤖 Made with AI
1
2
4
405
cortexDB stores memory as an append-only event log, so a wrong answer comes with a source, not a shrug.
🤖 Made with AI
2
3
140
coding agents forget everything between sessions. give them one shared memory instead. local and inspectable, built for agent fleets. cortexdb.ai/download
15
13
122
1,696,756
CortexDB.ai by creator of Cassandra retweeted
Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇
720
1,764
1,280
14,988
6,435,234
5/6 this is becoming procurement, not a feature. 88% of orgs hit an ai-agent incident last year, only 21% could see what their agents were doing. eu ai act article 12 makes event logging mandatory for high-risk systems in aug 2026.
1
1
100
6/6 trust used to be asserted: a benchmark, a brand, a promise. traceable memory makes it queryable. "show me the events under this conclusion." cortexdb is that bet: every input stored as an immutable event, never rewritten, everything else derived on top.
67
4/6 the honest limit: reading the memory store is not reading the model. we can see what the agent knew. we can't fully see why it acted. a wrong belief is auditable. a wrong action built on correct beliefs is not, yet.
1
56
2/6 every belief humans hold comes with a story assembled after the fact. the chain that actually produced it was never stored anywhere we could read. agent memory is the first tech that stores it.
1
65
3/6 so the first cognitive system whose reasoning can actually be read won't be human. it's readable precisely because it lacks the interpreter that fills our gaps silently. ask why a belief is held and either the chain is there or it isn't. the absence is visible.
1
52
TLDR: 1/6 ask anyone why they did something and you get a fluent, confident answer. it can be entirely made up. the split-brain work showed it at the wiring level: the brain invents a reason, reports it as the cause, and never knows it's inventing.
3
1
1
210
2/ labs are building memory into the model. chatgpt memory doesn't leave chatgpt. claude can't see across projects. vertex needs gemini to extract. frameworks are building it into the framework.
1
1
603
3/ vector dbs are building it into the database. pinecone just shipped an entirely new product because raw vector search isn't the right shape for memory. they're conceding the layer in public. memory is infrastructure. that's the side that wins.
1
208
1/Most AI memory systems flatten everything into one layer. When the agent tells you what it believes, you can't ask why. The chain of reasoning has been compressed away. Here's what memory looks like when you don't do that
1
1
1
147
7/What the structure unlocks: → Evidence traceability: walk a Belief down through Facts → Episodes → raw Events → Safe schema evolution: rebuild derived layers under a better extraction model, from the Events you already have → Genuine temporal reasoning: "What did we believe on day X, as of day Y?"
1
1
1
72
8/Memory is the substrate on which an agent's continuity of self is built. If it can't distinguish observation from inference, can't preserve evidence, and can't reason about time — the agent on top will be confidently wrong in ways its operators can't diagnose. Five layers isn't a feature. It's the minimum.
1
61