CPU task-specific context preparation and explicitly saved local project notes through MCP.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Mimir long-term memory for OpenCode sessions
Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP.
Semantic search over a 200-chunk ACLM lifestyle medicine knowledge base.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
Read-only offline MCP server over a curated Shopware developer knowledge base
Local persistent memory for Claude Code: tracks mistakes and decisions via hooks, searches session history, detects loops and warns before edits.
Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Self-hosted long-term memory gateway for AI clients: runs on your own Cloudflare account (Workers + D1 + Vectorize), captures conversations, consolidates them overnight, and recalls them across Chatbo
Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent attribution, on SQLite, PostgreSQL or Supabase.
Official HTTP TypeScript & Node.js SDK for / ml (https://api.slashml.ai)
Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket.
On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.
Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handles consolidation and extraction.
Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an append-only event log and per-project scoping.
MCP server for Ordali memory: SQLite-backed project memory and governance traces.
Persistent memory for Claude via weighted, interconnected knowledge nodes.
MCP server for persistent, semantic memory across AI sessions
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
Read-only MCP server for Stet (stet.md): search and navigate the knowledge base from agents.
Local-first audio analysis: BPM, musical key, production profile, and CLAP vibe embeddings.
Semantic search over MINDSET's brand strategy topic database, plus its system prompt.
Fast, local, low-token long-term memory for AI coding tools (Claude Code, Kiro, VS Code, Cursor, OpenCode) over MCP.
Persistent semantic and graph-based agent memory in a single self-contained binary with embedded database and models.
Memorize Bible verses with spaced repetition: add verses, get quizzed, follow a daily reading plan.
Approved public professional expertise, credentials and job-requirement evidence for Gabor Harsanyi.
Search, chat, upload, and scrape a serverless RAGStack knowledge base on AWS.
Installer for the TRTC Agent Skills suite (Chat, Call, RTC Engine, Live, Conference) plus manual SDK runtime log troubleshooting and knowledge base, with one-command MCP setup for Claude Code / Cursor
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Persistent memory for coding agents: what one session learns, the next one is told. One local binary, no daemon, no LLM in the loop.
Ayatollah Khamenei corpus: fatwas, lectures, knowledge graph. Arabic/Persian. Research access.
MIND MCP Server — 48 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task → Checklist hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and c
On-device memory system for AI coding agents — dual-layer engine (distilled facts + lossless event ledger), automatically captured and injected, exposed over MCP. Shared across agents, persistent acro
Direktori lengkap
RAG, graf, dan memori jangka panjang agen. 2,624 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.