News, technical deep-dives, and updates from the CortexDB team.
v0.5.1 ships CortexDB as a Docker image and stripped Linux binaries — the same engine that powers CortexDB Cloud, now runnable inside your own VPC, your homelab, or your laptop. One command, no signup.
The A-MEM paper applies the Zettelkasten principle to AI agent memory: dynamic indexing, explicit links, and progressive knowledge refinement. A review of the paper and the production implications.
CortexDB shipped lossless event-sourced memory, 4-channel hybrid retrieval, asynchronous extraction, 53 integrations, and 93.8% on LongMemEval-S. The roadmap covers retrieval accuracy gains, temporal queries, more connectors, enterprise governance, and community-driven development.
V1 ships today. 93.8% on LongMemEval-S (beating Mem0's 93.4%), 86.9% on LoCoMo, the five-layer memory model, hierarchical scopes, PASETO auth, and 53 integrations — built in 8 weeks.
A controlled internal comparison of CortexDB against an LLM-rewrite-on-write baseline across five production-scale scenarios. CortexDB reports 84.2% retrieval accuracy against the baseline's 31.8% at 1/337th the daily write-path cost.
CortexDB and Mem0 take different approaches to AI agent memory. CortexDB ships lossless event-sourced memory. Mem0 defaults to LLM-extraction on writes.
CortexDB ships lossless event-sourced memory with 4-channel hybrid retrieval. Zep builds temporal knowledge graphs from chat and business data. Architecture, knowledge graph, and multi-tenancy compared.
A single-run 93.8% on LongMemEval-S (469 of 500), running against the production CortexDB server with no in-memory shortcut. Pipeline walkthrough, per-category scores, leaderboard, and cost and latency analysis.
OpenClaw turns Claude into a desktop coworker with eyes and hands. CortexDB gives that coworker a memory that survives restarts, machines, and weeks.
A walkthrough of using CortexDB as a long-term memory provider for NousResearch's Hermes Agent -- with persistent recall, background writes, and prefetching.
A step-by-step guide to building an AI companion that remembers everything — preferences, past conversations, decisions, and context — using OpenAI and CortexDB.
Why we built an event-sourced memory system for AI agents — durable memory, connected context, 53 integrations, and production-ready scalability.
