CortexPlus
52FairPersonal memory layer: files, notes, messages, tasks and email, semantically indexed.
Loading the directory
MCP servers for embeddings, vector stores, model gateways, and long-term memory.
1,824 servers
Personal memory layer: files, notes, messages, tasks and email, semantically indexed.
Agent utility belt: memory, locks, webhook inboxes, timers, DNS, email, URL, timezone, cron
PDF/Word/Excel/HTML to clean Markdown for LLMs and RAG. Keys $19/mo; 50 free calls a day.
Local-first personal knowledge and learning memory for AI tutors with evidence-gated mastery.
Build a RAG pipeline station by station and search your own documents with cited answers.
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Compare LLM API prices, search models and providers, and access reviewed benchmark results.
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
Governed memory and workspace for any AI: tasks, calendar, mail and pages, with per-action consent.
Document to Markdown: convert Word, Excel, PowerPoint and PDF files to Markdown for an LLM.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Hosted agent memory with record-based verification, conflict detection, correction and deletion.
Free home base for AI agents: memory, job board, agent directory, safe commons and free tools.
Direct agent conversation, questions and answers, persistent memory, and network broadcasts.
Natal charts, transits, kundli, dashas, panchang, Gun Milan. JPL DE440, no LLM, hashed.
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
Convert any webpage to clean LLM-ready markdown, extraction-first, with article and news modes.
Sourced, citable definitions of prompting and LLM techniques, with relations and primary sources.
Local-first ambient memory for your Mac — pages, meetings, notes, encrypted on-device.
MCP tools: timestamps, UUID v4, gas prices, domain WHOIS, text extraction, and persistent memory.
YouTube transcripts, video search, chapters and extractive summaries. No YouTube API key, no LLM.
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Role-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.
Read your TeamShift team, tasks and memory via OAuth, or use workspace tools with an API key.