Memory, RAG & data
Give models memory, search your documents and get data into shape. 21 repos, most starred first.
firecrawl
Firecrawl is a web data API that searches, scrapes, crawls and maps websites, returning markdown, structured JSON or screenshots. Pick it when your AI app or agent needs live web content and you don't want to run proxies and headless browsers.
#2markitdown
Python tool that turns PDFs, Office files, audio and more into Markdown for LLMs
#3graphify
Maps a codebase and its docs into a knowledge graph your AI assistant can query
#4claude-mem
Saves what your coding agent does and feeds the useful parts back into later sessions
#5vectorize-io/hindsight
Memory server that lets AI agents store, search and learn from past interactions
#6OpenViking
A context database that stores agent memory, docs and skills as browsable files
#7open-notebook
Self-hosted research notebook that chats with your documents using any AI provider
#8WeKnora
Self-hosted platform that turns documents into RAG search, an agent and a wiki
#9supermemory
Memory layer that lets AI assistants and apps remember users across conversations
#10gbrain
A shared memory for AI agents that stores sourced facts and answers with citations
#11qmd
Local command-line search for your notes, docs and transcripts, with AI re-ranking
#12TencentDB-Agent-Memory
A shared memory server that lets AI agents reuse chats, skills, docs and code knowledge
#13agentmemory
Shared long-term memory for coding agents like Claude Code, Cursor and Codex
#14screenpipe
Records your screen and audio locally so you and your AI agents can search it
#15semantica
Python toolkit that turns messy data into a knowledge graph with decision audit trails
#16liteparse
Local PDF and Office document parser with Markdown, JSON and bounding-box output
#17PixelRAG
Search web pages and PDFs by rendering them as screenshots, not parsed text
#18honcho
Memory server that builds lasting profiles of users and agents from conversations
#19basic-memory
Local Markdown notes your AI can read, write and search through MCP
#20rta-smriti-brain
Local project memory for AI coding agents, with evidence labels on every claim
#21cortex_suite
Two local MCP servers giving coding agents live code structure and learned project memory