Upgrade OpenClaw's memory search from basic SQLite to QMD — a local hybrid search engine combining BM25, vector search, and LLM re-ranking for better AI memory.
Search LibGen, the Pirated-Books Database That Meta Used to Train AI
Millions of books and scientific papers are captured in the collection’s current iteration.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti—a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep’s capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep’s effectiveness for deployment in real-world applications.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti—a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep’s capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep’s effectiveness for deployment in real-world applications.
Design intuitive search experiences - WWDC26 - Videos - Apple Developer
Explore new patterns and best practices when implementing search in your app. Discover how search plays a key role in helping people find...
Oxmgr — Rust Process Manager
42× faster crash recovery, 20× lower memory than PM2. Written in Rust.
Fixing Search
Search on the web, for most people, has become a deplorable experience. It is such a key function that it can feel unfixable, but by treating search as an architectural component of the web (which it effectively is) and working our way through the issues it creates, we can define an alternative that is both realistic and superior.
kerim/zotero-mcp-skill
Claude Desktop skill for comprehensive, multi-strategy searching of Zotero libraries via MCP server with semantic search
LettaBot - Your personal AI that remembers
Your personal AI with living memory. Remembers everything. Runs on your computer. Grows with you.
‘Doom Loop’: OpenAI and Microsoft Admits LLMs Are Destroying the Web and Built on Theft
"Millions of people around the world will soon consider large models ‘hoovering up’ all their work to be an astonishing theft of unprecedented proportions."
DuckDuckGo Lite: Fast, Lightweight Private Search
The lightest weight version of DuckDuckGo private search. Loads fast on slow connections and compatible with text-based browsers.
Cursor: AI coding agent
Built to make you extraordinarily productive, Cursor is the best AI coding agent.
What happened after 2,000 people tried to hack my AI assistant — Fernando Irarrázaval
I built hackmyclaw.com, where anyone could email Fiu, my OpenClaw assistant, and try to make it leak the contents of a secrets.env file.
OSINT Navigator
Find the right OSINT tool for your investigation. AI-powered recommendations from 17 curated toolkits.
Researchers published in NEJM about using OpenAI’s o3 DeepResearch to discover strong leads in 18 previously unsolved rare diseases o3 produced *explanations* of old lab results (not diagnoses), which researchers vetted and took to the lab AI is not just a black box openai.com/index/diagnose-rare-childhood…
Using AI to help physicians diagnose rare genetic diseases affecting children
openai.comatproto-aware concept search engine
wesleyfinck.org
