Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, projects and tasks.
Cognitive memory engine with knowledge modules, circadian rhythm awareness, emotional state tracking, hybrid PostgreSQL/Qdrant search and per-user isolation.
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge graph, hybrid search and keychain credential vault.
TwelveLabs MCP: video indexing, search, analysis, and embeddings for AI applications.
An AI agent's own long-term memory, on your machine. Needs a one-time: npx anairyspirit setup
Persistent engineering knowledge base with source-backed wiki, agent-runtime and repository-context tools, contradiction and staleness checks, and PIN-gated private scopes and writes.
CoreForge media tools: speech-to-text, document parsing, translation, embeddings. x402 pay-per-call.
Cybersecurity assessment of documents, questionnaires and reports: multi-format parsing, RAG knowledge base, risks, compliance gaps and remediations.
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Persistent memory for AI agents: save, search and connect context across tools and sessions.
Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
Long-term memory for each person your app serves: saves, recalls later, keeps facts current.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
An MCP server that provides persistent memory and context management across sessions
Seeds, governs and navigates a memory_bank knowledge base: gated writes, routing without reading, drift against the code
Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.
Add RAG-based AI chat to any website: local vector store, OpenAI, Anthropic or Gemini models, a self-contained chat server and an embeddable widget.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
MCP server for remote management of project memory banks
Shared Graph-RAG memory for AI agents: markdown vault, wikilink recall, tasks, messaging.
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.
An MCP server that validates content against MCP specification using semantic search and AI
Expose your Quickchat AI agent as an MCP server, giving AI apps real-time access to its knowledge base and conversational capabilities.
Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
Local semantic search and RAG over Apple Notes with on-device embeddings, full CRUD, folder management and fuzzy title matching.
Semantic search + connection-discovery across your own Apple Notes (bridges, synthesis).
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
전체 디렉터리
RAG, 그래프, 에이전트 장기 메모리. 서버 2,619개를 사용량이 많은 순으로 보여 줍니다. 각 항목은 게시자의 페이지로 연결됩니다.