turbopuffer x Pragmatic Engineer
Vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable.
LiveUpdated 2026-09-19 16:51 UTC
RAG & memory
RAG & memory scores 47/100 on the AI Radar money board (#15), with 143 posts and 4.4M views on X over the last 14 days.
It moved down 2 places in the last 24 hours. 13 new tools appeared in this market over the last 7 days, and 45 posts were published about it in the last 72 hours. Jev also rates the room for a newcomer here 1.58/4.
Top RAG & memory tools
weknora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. - Tencent/WeKnora
pixelrag
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/ - StarTrail-org/PixelRAG
Vercel
Mem0 is now available on the Vercel Marketplace. Install the native integration to add long-term memory to your AI agents, with automatic provisioning and…
obsidian-second-brain
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and…
brainapi2
BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search,…
semantica
Graph-Native Infrastructure for Context and Accountable AI Systems - semantica-agi/semantica
Sign in
In the meantime, if you do have use cases for gnarly extraction from extremely complex documents, come check out our LlamaParse product demo below 🙂
flybrain-pollard-vl-cnsv1
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Developer Documentation
come check out our high-effort scores!
llm_wiki
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of…
Knowledge that can show its work
Knowledge that can show its work.
Hornet
The unreasonable effectiveness of BM25 for agentic search: @jobergum
SID AI
Where RL Will Take Search: @maxrumpf
pipeshub-ai
PipesHub is an open-source platform for securely connecting enterprise knowledge to AI. Give AI agents trusted context and your team permission-aware search…
agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes. - GiovanniPasq/agentic-rag-for-dummies
hermes-zvec-memory
Local-first Hermes memory provider on zvec-grep (hybrid BM25+vector RRF over Markdown vault) - r0b0tlab/hermes-zvec-memory
arkon
Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect…
omniparse
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks - adithya-s-k/omniparse
supermemory
Agents need memory. supermemory is building the default engine for memory and continual learning for agents.
Redis
Developers love Redis. Unlock the full potential of the Redis database with Redis Enterprise and start building blazing fast apps.
quant-mind
QuantMind is an open source agent-native knowledge extraction and retrieval framework for quantitative finance. - LLMQuant/quant-mind
turbovec
A vector index built on TurboQuant, written in Rust with Python bindings - RyanCodrai/turbovec
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN - unclecode/crawl4ai
FAQ
Is there money in rag & memory?
Jev rates buyer spend 2.85/4, search demand 3.35/4, sponsor budgets 2.39/4 and growth 3.1/4. Overall market score: 47/100 (#15 of 19).
What are the newest rag & memory tools?
turbopuffer x Pragmatic Engineer, weknora, pixelrag, Vercel, obsidian-second-brain. Updated 2026-09-19 16:51 UTC.
How is this ranked?
35% money (Jev judgment), 25% traction on X, 20% momentum over 72 hours, 10% new tools, 10% room for newcomers. See methodology.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:51 UTC. Full method.