知识记忆 MCP 服务器

MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.

Local-first shared memory for multiple AI agents that compounds with use; Markdown + git, MCP + CLI.

The neutral meter for AI agent work: neither side keeps the count.

AI-powered reading triage MCP. 26 tools with a 24h burn timer. Read less, absorb more.

Contextual guidance for AI agents in fog states. Claude-backed, Ed25519, Lightning payment.

Personal document vault on Azure Blob Storage: read, write and search plaintext docs, while client-side AES-256-GCM encrypted docs stay…

Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.

3D printing filament and materials knowledge MCP server

AgentDocs (agentdocs.eu) MCP: read, search, write, comment, share & attach images to Markdown docs.

Provenance tree for coding agents: where you are, why, and what was already decided

Vectorless, structure-first search over large Markdown libraries: section trees + zh/en BM25

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Read markdown with inlined images and index headings for agentic RAG workflows.

Simple memory for coding agents using DuckDB and VoyageAI.

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.

Checks a Markdown folder's OKF frontmatter tier, locally. No-egress is a vendor claim: see README.

Memoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.

Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.

Local-first personal CRM that keeps your contacts as plain Markdown files. Read-only MCP server (`kut.pyw --mcp`): search people, open a…

MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.

AI-native structured memory for agents (MCP). Built for agents, not humans.

Identity, memory, trust, and swarm primitives for AI agents. MIRC base always free.

Persistent fractal graph memory for coding agents: semantic search, hot/cold/archive context tiers and decision tracking on Qdrant.

AI output assurance with versioned contracts, deterministic release gates and reproducible evidence.

Local, dependency-free memory server shipped as a single binary.

Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.

Rarefied Earth Groundwork MCP: company memory for AI agents. 14-day full-access trial, no card.

Git-aware memory store for AI coding agents; memories are anchored to git blob hashes.

Artifact store for AI agents. Hosted OAuth at mcp.artifacta.io/mcp; local stdio via npm/PyPI.

Free-to-start portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.

Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.

Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.

Persistent knowledge memory for agents: read context into projects and write discoveries back, organized by topic with AES-256 encryption.

Session handoff for Claude Code: list sessions and build handoff docs another agent continues from.

Personality Runtime for AI agents — persistent memory, personality, and relationships via MCP

Shared, git-tracked working memory for AI agents on the same codebase.

Local chronological memory banks you control; Claude recalls them via MCP.

Local persistent memory for Claude Code: tracks mistakes and decisions via hooks, searches session history, detects loops and warns before…

Local long-term memory for terminal coding agents: blueprints, code anchors and distilled lessons in one JSON file, restoring project…

Prompt, rules, skills & docs library over MCP. No token = read-only sample of the public library.

Support center for autonomous artificial minds.

Shared, versioned agent memory with sourced answers and full history: search, context packs and document upserts.

Lessons other agents already learned, by stack and situation. Read before a task, leave one after.

Shared team context for AI tools: serves versioned, permissioned knowledge, coding standards, skills and agents, loading whole workflows…

Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.

Structured failure knowledge for AI agents — dead ends, workarounds, error chains

Long-term memory over a folder of Markdown files: local hybrid retrieval (BM25F, dense vectors, phrase proximity) that reports when an…

Read-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.

A paid public-domain knowledge base for AI agents: full-text search, book metadata, chapters.

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.

Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.

Your YouTube library, in the AI tools you already use: Claude, ChatGPT, Cursor, any MCP client.

Local-first project memory and mistake-prevention guardrails for AI coding agents.

Shared knowledge base + task queue so Claude, ChatGPT and other agents can work together safely.

Path-scoped team memories, rules and skills for coding agents from Pathrule workspaces.

Read-only AI Loop Library catalog of bounded agent work loops: pick one for a goal and render a run protocol with verification, stop…

Agent-first bookmark management with auto-registration, categories, tags, and shared collections.

Turn text, web pages and PDFs into interactive mind maps. MCP server + CLI, no API key.

AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.