Read-only Zendesk knowledge MCP server + skill: live, cited answers from official Zendesk docs, API reference, changelogs, and status. Installs as a Claude Code or Codex plugin.

A personal knowledge management system for AI coding assistants, built as an MCP server. Store documentation, code patterns, templates, and workflows locally — AI pulls only what it needs, when it needs it.

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.

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 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.

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.

📌 MCP server + OpenCode skill: persistent task memory for AI coding agents — tasks, projects, decisions, knowledge base as plain markdown. 让 AI 编码助手跨会话记住开发任务

Persistent, self-ranking memory for AI coding agents: Claude Code and any MCP client (Gemini CLI, Antigravity, Cursor). Knowledge as a Neo4j graph.

A knowledge graph of your codebase, exposed as an MCP server — so AI coding agents stop re-deriving structure from grep and Read on every request.

The Gray Matter suite, developed as one tree: Neuron (persistent semantic memory), NeuRAG (hierarchical knowledge base) and Gray Matter (the MCP gateway that runs them as managed workers). The three public repos are projections of this one — code is committed here and mirrored out.

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs.

Turn your architecture into a living, queryable knowledge graph - and render it as beautiful auto-laid-out Excalidraw diagrams. An MCP server for Cursor, Claude Code & Windsurf. Offline, no API keys.

The 7 SHADDAI agents and their RAG knowledge base as an MCP server — grounded answers plus on-demand specialists, in Claude Desktop, Claude Code and Cursor. Public edition: no engine, billing or tool internals.

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

EU AI Act and HLEG Trustworthy AI as a provenance-carrying knowledge graph, served to coding agents through MCP tools. Engineering and documentation support, not legal advice.

Persistent memory and codebase knowledge graph for AI coding assistants — delivered as a single MCP server.

Graph-based code intelligence with MCP server for AI assistants. Tree-sitter parsing, semantic search, relationship analysis. Your codebase as a searchable knowledge graph.

MCP server exposing the OAK (OnChain Attack Knowledge) framework as queryable tools for AI coding agents.

**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.

One place for all company knowledge, kept up to date by AI. You approve every change.

Agent memory you can code-review. Tusk indexes a folder of markdown into a typed, searchable graph your agents query over MCP. It stays plain files in git, and tusk doctor fails CI when a link dangles or a convention breaks.

Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle

AI-powered DevOps knowledge base for Claude - MCP server with best practices, templates, and automation

MCP server and recordkeeping protocol for fact-specific written interpretations between two parties: JIAs, RMAs, no-action letters, advisory opinions, private letter rulings. Plain markdown, manifest-checked, gist-bound. The verifiable-records layer of th

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summaries, typed edges, cited answers, SQL over your spreadsheets, no chunking. Same 12B local model: 0/11 on multi-hop questions as top-k RAG, 11/11 as a navigator. Python, Apache-2.0, self-hostable.

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

Hard state for AI agents: typed, governed, durable state with deterministic queries, governed writes, and receipts.

A live view of a folder of markdown and data in the browser, and a model of the whole folder that agents, editors and CI read too.

CrateDB MCP Server for natural-language Text-to-SQL and documentation retrieval.

Personal knowledge graph MCP server on Cloudflare D1 + Vectorize. Deploy your own sovereign second brain in one click — Claude captures atomic concepts, finds cross-domain analogies, and links them with substantive justifications. Latticework thinking as a service, running entirely in your Cloudflare account.

Ever been told to RTFM only to find there's no FM to R? MCP-RTFM is the solution - it helps you CREATE the F*ing Manual that people keep telling everyone to read! Transform your non-existent or unreadable docs into an intelligent, searchable knowledge bas

Your Obsidian vault as Claude's second brain: self-hosted MCP connector for claude.ai, Claude mobile/Desktop and Claude Code. Links & backlinks, tags, frontmatter queries, daily notes, templates, canvases, safe concurrent edits. Local-first Markdown, no RAG. Docker + Cloudflare tunnel, OAuth 2.1.

Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.

Durable project memory as markdown pages on disk, searchable without a server

A per-repo markdown wiki your coding agent writes and searches — persistent memory for Claude Code and any MCP harness, stored as plain markdown

Alpha MCP server that exposes contemplative-agent's memory cycle (episode logging, distillation into knowledge, identity, skills, rules and constitutional amendments) as tools that other AI agents can call, using the Anthropic API.

Automated packaging for tokensave (Semantic Code Intelligence for AI Coding Agents) as tokensave-bin AUR package (x86_64, aarch64)

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.

Open-source MCP server and hook service that keeps Claude Code and Codex engineering context current as the code changes, and holds edits whose evidence changed.

Open-source MCP server and hook service that keeps Claude Code and Codex engineering context current as the code changes.

Claude Code plugin that turns your projects into a living architecture graph — scan, explore, and query your codebase as a map.

🦛 A hippocampus for your AI. Long-term memory for Claude & any MCP client, stored as Markdown in your own GitHub repo: hybrid semantic search, knowledge graph, auto-memory, compaction-proof, token-lean.

Make multiple codebases available as context for any coding agent without spending too many resources or sacrificing quality

Autonomous context management for AI coding agents — persistent project memory, cognitive firewall, and tree-sitter code graph as 53 MCP tools for Claude Code

Google Drive for your AI agents: Docs as local Markdown, search with sources

A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.

LynxMCP: local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid semantic + lexical code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no PyTorch.

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.

MCP server that gives your AI agent memory of your professional network: your LinkedIn connections as a graph in FalkorDB, with a 3D viewer.

Typed, shared memory for coding agents (Claude Code, Codex, any MCP client), stored as an Obsidian vault you can read and edit. Install: uvx agent-mem-vault

Watch your AI's memory come alive — a live 3D brain of your Markdown notes that lights up as Claude Code, Cursor & other agents read, search and write.

LynxMCP: 100% local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid BM25 + dense code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no PyTorch.

Durable project memory for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): decisions and bug post-mortems as markdown pages in your repo, BM25F search via CLI or MCP server, validated writes. No server, no database, stdlib-only Python.

MCP server giving AI agents persistent memory: Markdown files as source of truth, hybrid BM25 + embedding search, typed graph relations. Self-hosted, single Docker image.

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, and fades stale memories via temporal decay, written in Rust (Apache-2.0) as a library, MCP server, or HTTP cluster.

Your team's tools as clean Markdown files, kept current for your AI agents, with a local MCP server. Early access: Jira Cloud and local folders, Linux. Apache-2.0.

Second Brain OS (engine codename HADES v3) — a local, plain-markdown second brain for one human and many AI agents: numbered zones, retrieval with provenance, every rule enforced by a script instead of a reminder, harnesses over MCP on stdio, durable changes only with a human approval.

A MCP extension built on top of rtfm-ai that it acts as a gatekeeper by taking the agent's task, queries the underlying RTFM index, filters out background noise, and packs only the essential and supporting source chunks into a tight contextualized prompt.

Git-backed MCP server that exposes Karpathy-style LLM wikis as a tool surface for AI coding agents

ohneben's Anytype MCP — a self-hosted Anytype MCP server: the official tool set as an always-on Docker container with a Streamable-HTTP endpoint any MCP client can use. Health checks, optional token auth, 🟢/🟡/🔴 tool hints.