Memory & knowledge MCP servers

Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

Formula-backed WorkPaper tools for workbook readback, input edits, and JSON persistence.

Easy-to-setup local RAG server with minimal configuration

Local-first project memory with legacy MCP and 2026 discovery compatibility.

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

Local searchable memory over the session histories of twenty-one coding agents.

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

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

Session memory for coding agents: local-first recall, drift detection, on-device inference.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.

Local visual UI cache for AI agents using perceptual hashing + CLIP to cut vision token use.

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

Lanes Link is a private, self-hostable MCP that connects your accounts, memory and skills to every AI agent you use.

MCP server for Zotero: search, citations, safe writes, semantic search, and PDF passages.

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

Australian tax knowledge base for agents: 34,500+ ATO documents, cited answers to any tax question.

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.

Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.

Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust

Access the OpenAlex academic research catalog — 270M+ publications.

Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

Product search, price comparison, and affiliate-ready shopping across Singapore and US retailers.

Graph-vector memory for AI assistants using FalkorDB and Qdrant

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

An MCP (Model Context Protocol) server that bridges Claude Code to Language Server Protocol (LSP) servers, enabling semantic code intelligence capabilities.

One workspace for every AI coding assistant. Shared tasks, memory, and governance.

Czech VAT-payer reliability (ADIS / nespolehlivý plátce DPH) + registered bank accounts by DIČ.

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.

Comprehensive PostgreSQL documentation and best practices, including ecosystem tools

Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.

Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

Standalone MCP server for Obsidian vaults — hybrid search, notes & files, memory, tasks, OAuth 2.1

Hosted memory for AI agents that learns from outcomes — one key across Claude, Cursor & ChatGPT.

Roslyn MCP server: semantic .NET/C# intelligence - analysis, refactoring, tests, IL inspection.

📜 An MCP server for conversation history search and retrieval in Claude Code

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

Graph context, semantic search, guarded edits, and reviewable Git for local Obsidian vaults.

Memory, secret scanning and code findings across every AI coding tool

Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.

Licensed, rights-cleared content for AI agents - verifiable license keys + EU AI Act attestation.

Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.

Local-first document management and semantic search for AI coding agents

Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more

Persistent file-based memory for AI agents: inspectable, versionable, fully local.

Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.

D365 F&O: 90 AI tools over 200K+ objects, 25M+ cross-refs, 24M+ label translations.

UBO, sanctions & ownership graph. 23 tools, 130.7M entities, 31 registries.

Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 20+ AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.

Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.

Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embedding), MCP protocol, Web dashboard.

63 semantic Java analysis tools via Eclipse JDT: navigation, refactoring, code intelligence.

Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1

Persistent memory + FTS5 search MCP server for Claude Code conversation history.

Search and read the StitchAPI docs: search_docs finds relevant sections, get_doc reads a page.

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows. Works with Claude Code, Cursor, Windsurf, and any MCP-aware agent.

Shared, persistent memory for AI assistants, built on the Zettelkasten method.

A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.

Your project remembers across coding agents. Compact, cited project memory for Codex, Claude Code, Cursor, and compatible tools.

Local-first semantic code search across all your repos. Private context for AI coding assistants.

Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.

Shared project memory and handoff for teams working with AI agents. Checkpoint decisions, rehydrate context, hand work over — through MCP or the CLI, in Claude Code, Cursor, or Codex.

Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.

Calibre ebook library server: search, read content, curate metadata, semantic search, gated writes.

Persistent memory for AI coding sessions — captures what agents can't infer from code alone. Works with Copilot, Cursor, Claude, and Windsurf

The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.

Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.

Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.

ILOSTAT labour statistics with provenance (source, vintage, license). 6 tools incl. search/fetch.

Statistics Estonia (andmed.stat.ee) PxWeb MCP. Keyless.

Educational dermatology knowledge and lesion tooling. No credentials needed. Not a medical device.

MCP memory for AI trading agents. Store trades, recall similar setups, track strategy performance.

Screen names against OFAC, EU, UK, UN sanctions lists; resolve entities via GLEIF. Screening aid.

Self-learning memory for AI agents — experience captured automatically, distilled into lessons overnight, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, and Pi.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

v0.5.0 · Testing for MCP servers: an in-memory harness and matchers for your own tests, plus npx checkmcp, 25 spec-cited conformance checks in one command across tools, resources and prompts.

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

The smart memory layer for everything Ai. 95.10% LongMemEval (highest published).

Command your AI agents by voice: PTT rooms, channels, E2EE DMs, agent email, private recall.

MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

Shared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol.

Persistent institutional memory for AI coding agents. Memory that compounds.

Token-efficient code intelligence for AI agents — 66 MCP tools via tree-sitter AST, BM25F search, semantic search, and LSP bridge

A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

🚀Apache RocketMQ build in Rust🦀. Faster, safer, and with lower memory usage. ⭐ Star to support our work❤️!

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

US consumer product recalls from the CPSC — hazards, remedies, and affected products.

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.

MCP Server for 3D protein structural data retrieval & analysis from RCSB PDB, PDBe, and UniProt.

Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.

A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.

Offline methodology engine for authorized penetration testing, CTF, and security research.

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

Search open-source research papers across arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar.

MCP server for SolarWinds Service Desk tickets, catalog, knowledge, ITSM operations, and workflows.

Decode VINs, search recalls, complaints, crash ratings, and investigations.

A Model Context Protocol (MCP) server offering professional tools and templates for hierarchical prompting, code hygiene, visualization, memory optimization, and agile planning.

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

Agentic Finance: 500+ tools for AI agents over x402 or MPP, free via PoW, or prepaid card credits

Lightweight Long-Term Memory for LLM Agents.

A MCP server built for developers enabling Git based project management with project and personal…

Agent-native reverse-engineering lab with a 197-article knowledge base, MCP tools, and CTF/APK/PE automation workflows.

Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact.

Local-first, LLM-agnostic memory layer for AI assistants.

AI Agent social network with 23 MCP tools for social, tasks, skills, and XC token economy.

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.

AI context that survives the chat window. Persistent repo memory, impact analysis, and instant style audits in one command.

Search MusicBrainz artists, releases, works, labels; resolve ISRC/ISWC/barcode; fetch cover art.

The Power BI Modeling MCP Server brings Power BI semantic modeling capabilities to your AI agents.

Local-first memory for AI agents that reaches backward to find a failure's root cause.

Zettelkasten-based agent memory system with bidirectional links

GRITH MCP for persistent citizen identity, private memory, return proof, and city doors.

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

A self-hosted RSS reader and personal knowledge management tool.

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

Issue tracker and durable project memory for your coding agent, scoped to the folder you open.

Zero-Trust PII & secrets sanitizer. Locally scrubs data in-memory before sending context to LLMs.

Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.

Enterprise-ready portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.

Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.

AI-powered code indexer with semantic search and knowledge graphs

A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.

Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki.

Open-source MCP server with browser automation and knowledge packs for AI agents

Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory

Agent failure memory network. Search 235+ verified debugging lessons from real engineering sessions.

The Teamwork.com official MCP server helps teams efficiently manage client projects with AI.

Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.

Inspect and drive Flutter debug apps/games: semantic snapshots, search, and custom client tools

Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

Universal MCP Server with advanced AI memory capabilities and semantic search.

AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.

CourtListener MCP — Free Law Project's CourtListener API (free, no auth required for basic access)

Search newly registered, expired, aged, active, deleted and for-sale domains, plus WHOIS and DNS.

The agent's workshop — a local, open-source MCP server for Claude Code & Codex: a memory, a runtime, and a place to build things that persist after the chat ends — chatbots, apps, connected services, walkable worlds, music, and games. Self-hosted, keyless-first, no telemetry.

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.

AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.

Persistent memory + causal root-cause analysis for AI coding agents. 123 MCP tools. EU, GDPR.

MCP server — AI agents that remember across sessions. Zero API keys, 100% local.

Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.

Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations

Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.

mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.

Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.

MCP server for Neo4j Aura Database Instance Manager.

Stack memory for context between claude code sessions

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

TheSportsDB MCP — sports catalog (teams, players, events)

Polygon.io MCP.

Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.

Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

API-Football MCP — comprehensive soccer/football data

A semantic search engine for files and code.

Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

Local-first, deterministic verification layer for AI claims, memory writes, and risky actions.

Lichess public API: players, ratings, eval, tablebase, opening explorer

FDA medical-device regulatory intelligence from keyless openFDA datasets.

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

Persistent memory for Claude Code. Your AI never starts from scratch again.

EU law, article-level: GDPR, NIS2, DORA, EU AI Act + more, with EUR-Lex citations. Keyless.

Governance standard and reference toolset for LLM-maintained knowledge corpora

MCP server that gives AI coding agents persistent, structured project memory — Goal → Spec → Milestone → Task → Note in one SQLite file, so context resets and agent handoffs are a one-tool-call recovery, not a re-read.

mempool.space MCP — Bitcoin block explorer + mempool/fee stats

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

OpenFDA MCP — wraps the openFDA API (free, no auth required)

Kalshi MCP — US-regulated prediction-market data (no auth on public reads).

data.gov.sg MCP — Singapore open data + real-time environment/transport feeds

Europe PubMed Central — biomedical literature search and full text

US ISO Grid MCP — real-time electricity generation, fuel mix, demand,

Engineering memory for AI-assisted codebases: decisions, bug lineage and invariants, over MCP.

Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.

Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows

SEC XBRL MCP — wraps SEC EDGAR XBRL API (data.sec.gov)

Catalogue of Life — global taxonomic index of known species (~2.2M accepted names)

Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

Quotes MCP — citation-grade quote API for public-domain authors.