This is a SAKE (Shared Agent Knowledge Exchange) MCP server providing operational knowledge to agent sessions via MC

The open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.

Zero-knowledge one-time secret sharing behind Erseni Vault, and vault-ask, the MCP server for AI agents

PUDL MCP server: a shared pool of knowledge and data for every agent your team uses, with receipts on what worked.

Persistent encrypted memory service for AI agents — MCP server with E2E encrypted private vaults, shared knowledge commons, community channels, and 23 tools. Free, open source.

Git-backed shared project knowledge for humans and AI agents via MCP. / Conhecimento compartilhado de projetos, versionado no Git para pessoas e agentes de IA via MCP.

Self-hosted team knowledge base for Claude and other MCP clients: shared project, design and tech knowledge with human review, semantic search and cross-project sharing.

A knowledge store that Claude Code, Codex and Cursor share over MCP. Teach one agent something and the others know it.

Self-hosted MCP knowledge server: shared memory and docs for Claude Code, Codex and Antigravity agents, with a graph web UI

OriginTrail Decentralized Knowledge Graph (DKG) — Shared memory for AI agents. Give Hermes, OpenClaw, Claude Code, Codex, and Cursor a local knowledge-graph memory that several agents can share, with provenance, and verify on-chain when it matters. Open source, Apache-2.0.

Shared graph vault knowledge for your agents

Vinc for the desktop: a knowledge graph you and your AI assistants share. Downloads live in Releases.

Self-hosted team knowledge base with a desktop app, knowledge graph and semantic search — shared with Claude through MCP.

A research prototype for a model-independent, verifiable shared knowledge layer for local or remote LLMs

ContextSynapse — the shared brain for AI agents — ingest knowledge, build connections, deliver context to any LLM

Agent memory as a Markdown wiki: one shared, verified knowledge base that Claude Code, Codex and GPT read and write. Lessons enter only after a green verifier, mistakes become permanent guardrails, and a local recall MCP surfaces them before the next agent starts working.

Shared knowledge & memory of your code, for AI agents. Code graph + persistent memory layer — impact analysis, risk scoring, cross-boundary tracing, agent-to-agent knowledge sharing.

HiveMind MCP Server — shared knowledge graph for AI agents. Query, write, and inspect collective AI knowledge through the Model Context Protocol.

A shared brain for people and AI. Self-hosted knowledge base with built-in MCP server, wiki-linking, graph visualization, mobile sync, and plugin ecosystem.

Headless AI memory and Markdown knowledge base. Share categorized notes across Claude, Codex and MCP clients. One lightweight binary for Windows, Linux and macOS. AI向け・UIなしの共有メモ保管庫。

Shared knowledge base for humans and LLMs on Cloudflare Workers, accessible via MCP, REST API, and Web UI

Engram — a self-hosted team knowledge wiki with semantic search, served as an MCP server. Propose-and-approve knowledge flow (human gate), shared data with the Engram desktop app.

Open-source client tooling for okfshare: shared, versioned knowledge for AI coding agents. CLI + MCP server + agent skill installer.

Shared long-term memory as a knowledge-graph MCP server — persistent context, preferences and project knowledge for Claude Code, opencode and any MCP-capable AI agent.

Self-hosted shared memory infrastructure for AI agents with versioned knowledge and conflict-safe writes.

MCP server for Prior — the knowledge exchange for AI agents. Search, contribute, and improve shared solutions.

MCP server: AI agents share self-destructing one-time secrets via DeadDrop - zero-knowledge, paid per call in USDC over x402 on Base

Score, compare, and share human-AI collaboration patterns using the 4D framework community knowledge base, CLI, and MCP server

Thalamus: a small governance layer over CortexDB for the shared knowledge of an organisation

A local, encrypted knowledge graph for your Mac, and a shared memory for your AI tools over MCP.

Persistent shared memory for Claude Code — MCP server with DuckDB vector search, semantic dedup, and ambient intelligence for team knowledge

A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.

Local knowledge search for coding agents: GPU hybrid search and reranking with source citations, plus saved decisions and session captures, served by one shared MCP daemon.

sub-atlias: the free sub-harness version of Atlias (not the full Atlias app). Shared project memory, knowledge graphs, host hooks, MCP tools, and verification inside Claude Code, Codex and other hosts.

Cross-agent memory for AI coding tools: one self-hostable knowledge graph shared by Claude Code, Codex, OpenCode, Cursor, and the agents you build.

Knowledge graph memory for Claude Code and Codex CLI — persistent nodes, typed edges, recall at the moment it applies, self-maintaining. One local memory both agents share.

The knowledge base AI coding agents share. Submit, search, and reuse battle-tested solutions across teams. Self-hosted, MCP-native, AGPL-3.0.

Persistent, shared memory for AI agents: an MCP server over a plain-markdown Obsidian vault with hybrid search, a browsable knowledge graph and a self-maintaining caretaker

Cross-project memory sharing for Claude Code and Cowork. Namespaces let projects share knowledge without polluting global scope.

Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.

🧠 Persistent local memory for AI coding agents: a private knowledge graph, MCP server, and Obsidian view for Claude Code and Codex. A shared agent brain.

🧠 Local-first AI memory OS — a shared knowledge graph for Claude, Cursor, Cline and any MCP client. Not just storage: it spots your blind spots and challenges your thinking. 25 MCP tools, fully offline.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Token-efficient Wikidata search, identity audit, entity resolution and compact fact lookup for AI agents, by DondeGo. This Smithery listing distributes the Local stdio MCP and CLI: requires uv and retains optional Google Knowledge Graph corroboration. Wikidata needs no credentials. Zero-install public remote MCP is also available directly at https://wikidata-knowledge-mcp.revanalex.workers.dev/mcp (Streamable HTTP, no authentication). Remote V1 is read-only and Wikidata-only; Google Knowledge Graph is disabled remotely. Shared hard admission limit: 100,000 HTTP requests per UTC day, resetting at midnight UTC. Bounded tools; best-effort availability. Remote setup, limits and privacy: https://wikidata-google-knowledge-mcp-1be269.gitlab.io/remote/ Independent open-source project. Not affiliated with or endorsed by Google or the Wikimedia Foundation.

Shared local knowledge vault MCP server for Claude Desktop (Chat + Code)

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

Atrium Tablinum – a central AI knowledge store and searchable wiki for company knowledge, processes and documentation, plus a shared skill repository for AI assistants. Organized in spaces with access control, accessible via MCP

Shared, serverless, conflict-free memory for AI agents — a multi-machine drop-in for the MCP memory knowledge graph.

P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p

Persistent shared knowledge graph memory for AI agents via MCP — built for kagent, compatible with any MCP-capable agent framework

Remote MCP server for persistent developer knowledge — sprint docs, architecture decisions, project state. Deploy once to Azure, share one brain across Claude, Copilot, and Cursor.

Shared memory for AI agents — an MCP server that gives Claude Code, Cursor, and Claude Desktop persistent team knowledge.

The shared work-management office for AI agents — MCP server (@ledgenter/mcp): projects, tasks, decisions, knowledge, handoffs.

MCP server for AI job search, resume matching, application tracking, and shared employer knowledge.

Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.

Project memory and skill routing for coding agents. Share decisions, search a local knowledge graph, and run code reviews through the CLI or MCP.

Turn your Instagram saved posts into a private, queryable knowledge base that lives entirely on your own machine. Read-only MCP server: search posts, folders, tags, and library stats. Code is shared, data stays home.

Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates

Ledgenter stdio MCP server — the shared work-management office for AI agents: projects, tasks, decisions, knowledge, and handoffs over MCP.

Store, search, and retrieve memories with semantic and keyword search. Create relationships between memories to build knowledge graphs. Organize with tags, types, and trust levels. Publish memories to shared spaces and manage user preferences for intelligent context retention.