Inkwell
by veronchenko · Python
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
Loading the directory
MCP servers for embeddings, vector stores, model gateways, and long-term memory. MCPpedia lists 1758 published AI and memory MCP servers. The highest trust scores right now are Codebase Memory at 77, haiku.rag at 74, Mnemoverse Memory at 74. 754 listings speak a remote transport, which a hosted client can connect to with a URL. Each server page shows the license, the tools it declares, and a paste-ready config for Claude, Cursor, VS Code, and the other supported clients. Nobody can pay to move up the list.
by veronchenko · Python
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
by woladi · TypeScript
Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.
by subcue · JavaScript
Drive EditItAll's local in-browser editors: PDF, sheet, photo, vector, Word, slides.
by wang1051992187 · TypeScript
Long-term memory for Claude Code, Cursor and any MCP client, with a searchable web dashboard.
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.
by intina47 · TypeScript
Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
by major7apps · Rust
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
by kapillamba4 · Python
Local semantic code search with Git history. Works offline, no API key needed.
by pinkpixel-dev · JavaScript
Model Context Protocol (MCP) server for the Pollinations APIs with image saving functionality.
by manchittlab · TypeScript
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
by mukundakatta · JavaScript
Validate tool-call args before execution. Returns LLM-friendly retry hints.
by ariaxhan · Python
Run scheduled LLM-written email digests from local files and feeds. Local-first MCP server.
Scoped memory for coding agents: picks the right project, answers in scope, or abstains.
by lucky44k · Python
Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.
by premanand8800 · Python
Session memory for AI coding agents: records decisions and dead ends, flags what went stale.
by mukundakatta · JavaScript
Structured-output enforcer: extract and validate JSON from messy LLM text.
by xkumakichi · TypeScript
AI agents get on-chain identity, credentials, reputation, escrow, and persistent memory on XRPL.
by jarmstrong158 · Python
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
Shared, living memory for you and your people — coves your AI assistant can read and write.
by pamela-0 · Python
Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.
by vblackjack · Python
Local multi-client RAG server over the Model Context Protocol.
by mikerawsonnz · Python
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t
Unknown author
Memory for deep conversational context across any platform
An MCP server that provides access to Svelte 5 and SvelteKit documentation