Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Guru knowledge base search and collections.
Persistent memory for AI agents. Hosted cloud connector or local Windows install.
TPermanent memory layer for AI agents. Mint moments to the Polygon blockchain via MCP.
Shared local memory for coding agents with semantic recall, knowledge graph, and code navigation.
IWE: a Markdown knowledge base you and your AI agent work on together. CLI, LSP server and MCP server.
Local-first non-linear memory operating system for AI operators.
Persistent, self-evolving memory for AI agents. Gives Claude Code, Codex CLI, OpenCode, and pi a knowledge graph that grows from conversations.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
ContextMap IA para pi: memoria viva del proyecto (brief para agentes, vault de Obsidian y Second Brain) con su servidor MCP listo para usar.
Session memory for AI coding agents. Search past sessions, extract rules, and track what works.
The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
Persistent 6-DoF SE(3) spatial world state, object trajectories, and affordances for robotics.
Local markdown notes: ranked + semantic search, tags, todos, and a wiki-link knowledge graph.
Long-term memory for Claude: Markdown in a git repo you own. Survives context compaction.
Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
MemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Local-first RAG engine with MCP server for AI agent integration.
Agent long-term memory with search, recording, and hot injection for AI coding agents
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.
Typed AI framework for TypeScript: provider routing and failover, durable agent graphs and workflows, retrieval over any vector store, MCP, evals, guardrails, and cost control
Compare GPU specs and cloud rental offers, check CUDA support, and estimate Qdrant resources.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Expert-structured medical ontologies, relationships, and evidence for AI research and reasoning.
FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge graph (graphify…
FastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…
Store and retrieve text in a Qdrant vector database by similarity search.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Persistent knowledge graph: entities, relations, and observations for agents.
Explore and evolve TigerGraph schemas, run GSQL and Cypher, load data, and search vector embeddings.
Local-first product graph for AI coding agents.
Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.
ディレクトリ全体
RAG、グラフ、エージェントの長期メモリ。 2,624 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。