MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
mcp-learning-memorygithub.com/nulone/mcp-learning-memoryupdated this year
MCP server for AI agent memory that learns from feedback
npm -
kiro-learngithub.com/brendangeck/kiro-learnupdated this year
Continuous learning for Kiro agent sessions on AWS. Passive tool-use capture, LLM extraction, and synchronous context injection — inspired by claude-mem, aligned with Bedrock AgentCore Memory.
npm Apache-2.0 -
synaptic-memoryupdated this year
Human-like neural memory system - Neuron-based persistent memory with Hebbian learning for AI agents
npm MIT -
Local-first personal knowledge management (PKM) MCP server and learning memory for every AI tutor—goal trees, a reusable knowledge graph, and evidence-gated mastery.
mcpb Apache-2.0 -
long-term-memorygithub.com/ihwoomil/long-term-memoryupdated this year
Long-term memory system for AI assistants — persistent, searchable, self-organizing memory powered by semantic search, knowledge graphs, and reinforcement learning
pypi MIT -
Self-learning issue memory for Codex using MCP. Automatically captures reusable bug fixes and reuses them across sessions with local-first, low-token SQLite storage.
MIT -
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
npm Apache-2.0 ★ 30 -
An agent memory server that learns from feedback which memories are worth returning. Go, with Python/LangChain/MCP adapters.
MIT -
mindkeg-mcpgithub.com/carloluisito/mindkeg-mcpupdated this year
A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings per repository.
npm MIT -
Decentralized AI Memory Network (DAMN) — a persistent learning and memory-sharing infrastructure for autonomous agents. Blockchain + IPFS-based memory layer enabling cross-agent experience reuse and scalable distributed intelligence.
★ 1 -
Long-term memory MCP server for OpenCode and other harnesses — stores preferences, lessons, and usage history in a single local SQLite file (100% local, no external API) so the AI can "remember and adapt" to the user through context-based learning.
npm MIT ★ 3 -
claude-soulgithub.com/DomDemetz/claude-soulupdated this year
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory
MIT ★ 94 -
Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.
MIT ★ 190 -
adb-mcp-server-progithub.com/tiendung2k03/adb-mcp-server-proupdated this year
A powerful Model Context Protocol (MCP) server for Android control via ADB with self-learning, UI memory, vision-enhanced, and macro support.
MIT ★ 1 -
Cerebrogithub.com/Professor-Low/Cerebroupdated this year
The open-source memory engine behind Cerebro. Persistent memory, learning and reasoning for Claude Code and any MCP client. Local-first.
pypi NOASSERTION ★ 2 -
Hierarchical memory + habit learning for Shesh (MCP)
GPL-3.0 -
ainl-cortexgithub.com/sbhooley/ainl-cortexupdated this year
Graph-native memory and self-learning for Claude Code. Every session remembered, every pattern learned, every agent connected — powered by AI Native Lang.
pypi NOASSERTION ★ 4 -
Local-first project intelligence and learning middleware for AI coding agents. CentR builds project memory, reusable learning, code intelligence, and context so agents can solve tasks with less redundant exploration.
npm MIT -
Personal English-learning app that ChatGPT uses as its memory over MCP + OAuth 2.1 (Next.js 16, Better Auth, Neon, Vercel)
MIT -
MCP server for Ragionex Memory - self-learning memory for AI agents.
npm MIT -
☀️Helios MCP: Give your AI permanent memory & personality! Install once, AI remembers forever. No more repeating context through versioned memory, behavioral & pattern learning, and multi-agent sync. UV-powered FastMCP server to teach your AI preferences and working styles that evolve through usage. Not a RAG system! Try today!☀️
MIT ★ 2 -
iflow-mcp_enhanced-mcp-memorygithub.com/cbunting99/enhanced-mcp-memoryupdated this year
Enterprise-grade MCP server with sequential thinking, project convention learning, and intelligent memory management
pypi MIT -
style-memory-mcpgithub.com/hexingyuofficial/style-memory-mcpupdated this year
A tiny local MCP server that learns how you talk — catchphrases, dialect, tone — without storing private memories. Local-first, no LLM calls.
MIT ★ 2 -
Bayesian memory that learns from feedback for LLM agents
pypi MIT ★ 9 -
Living memory system for AI assistants — SQLite + MCP with decay, learning, and knowledge graph
npm MIT ★ 1 -
ace-mcp-servergithub.com/rocky007cn/ace-memoryupdated this year
Ace MCP Server — Free AI memory that learns. Zero cloud, zero API keys, zero cost.
pypi BSL-1.1 -
SuperMemorygithub.com/YashvantHange/SuperMemoryupdated this year
SuperMemory: an MCP-first learning memory layer for Claude, Cursor, and agent workflows
pypi MIT ★ 2 -
Verified, scoped, retractable memory for coding agents — learns from code review, resists poisoned advice, human-governed. MCP server.
MIT ★ 1 -
A multimodal memory MCP server for made that your AI assistant learn from you and itself. DIGIO Alchemai Project
go MIT ★ 11 -
One MCP gateway that gives AI agents a real browser and a memory per website: lessons, fixes and the site's internal API, learned from real traffic
MIT -
claudebot-memorygithub.com/solan/claudebotupdated this year
MCP Server for persistent bot memory — stores learnings, preferences, skills and workflows in a local JSON store. Works with any MCP-compatible client (Claude Code, Claude Desktop, Cursor, etc.)
npm MIT -
extremisgithub.com/ashwanijha04/extremisupdated this year
Persistent, learning memory for AI agents — RL-scored retrieval, intelligent forgetting, MCP-native. Works with Claude Code, Cursor, OpenAI.
MIT ★ 1 -
alaya-mcpgithub.com/securityronin/alayaupdated this year
Alaya MCP Server — a memory engine for AI agents that remembers, forgets, and learns
npm MIT -
Transform GitHub Copilot into a sophisticated AI learning partner with meta-cognitive awareness, persistent memory, dual-mind processing, and cross-project knowledge sharing. VS Code extension.
npm NOASSERTION ★ 4 -
instinct-mcpgithub.com/yakuphanycl/instinctupdated this year
Self-learning memory for AI coding agents — pattern detection, confidence scoring, auto-promotion via MCP
pypi MIT -
onelampgithub.com/onelampai/onelampupdated this year
Shared memory across your AI. Teach one, they all learn.
Apache-2.0 -
roampalgithub.com/roampal-ai/roampalupdated this year
Memory that learns what works.
NOASSERTION ★ 126 -
Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.
npm Apache-2.0 -
Lasting memory for Claude Code — session memory + a git-tracked knowledge wiki, searched as one, with a self-learning loop. Local-first, OAuth-only, no API key.
MIT ★ 1 -
repomemorygithub.com/DanielGuru/repomemoryupdated this year
Persistent, structured memory for AI coding agents. Your repo remembers what every session learned.
npm MIT ★ 2 -
Shared, git-tracked memory for AI agents on the same codebase. What one Claude/Cursor/Cline learns, the next one picks up. No DB, no SaaS — just files in your repo. CLI + MCP server.
pypi MIT ★ 1 -
Persistent memory MCP server (MemoryIndustry) — self-growing knowledge graph that works without MCP sampling, poisoning quarantine, PostgreSQL + pgvector, bitemporal facts, BM25+RRF hybrid search, graph metrics/communities, Hebbian learning, episodic memo
npm Apache-2.0 -
Self-improving long-term memory for AI agents in Rust. Safety-gated procedural learning, MCP server, Python/Node SDKs, and durable memory.
NOASSERTION ★ 2 -
Experimental always-on runtime for AI coding agents: 5-tier memory, pattern learning, MCP server, Telegram + webchat.
MIT -
Persistent memory for AI agents, over MCP. Local-first, negative learning, hybrid recall. Docs and community home (source is maintained privately).
npm NOASSERTION ★ 3 -
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
pypi Apache-2.0 ★ 323 -
Knowledge engine for AI agents — persistent memory, vault, and brain that learns
npm Apache-2.0 ★ 6 -
Persistent memory for Claude Code: a Claude Code plugin with an MCP server on Postgres/pgvector that learns across sessions and projects
MIT -
Agent memory with a recall button - Every memory knows its sources. Recall a bad source, and everything learned from it goes too
Apache-2.0 ★ 6 -
YantrikDB — Cognitive memory for AI agents. Persistent semantic recall, knowledge graph, contradiction detection, and procedural learning. Ships as embeddable engine, network database, or MCP server.
pypi MIT -
recall-memory-mcpgithub.com/ashleyevz89-hue/recall-memory-mcpupdated this year
Relevance-gated, self-improving procedural memory for AI agents, as an MCP server. Loads only the lessons relevant to the task, learns from failures, prunes what it never uses. ~99% less context per task.
MIT -
MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution
MIT ★ 6 -
shadowgithub.com/andresgomezfrr/shadowupdated this year
Local-first memory, observation, and autonomy layer for Claude. A background daemon that learns from your sessions.
NOASSERTION ★ 8 -
clinotesgithub.com/karthyick/clinotesupdated this year
Project memory for AI coding agents - git-native, MCP-ready. Decisions + learnings as Markdown in your repo.
pypi MIT -
Long-term memory for LLM agents: hybrid BM25 + vector retrieval that learns from use, a measured retrieval benchmark, and a from-scratch MCP server. Standard library only.
MIT -
correxgithub.com/ozoz5/correxupdated this year
Specific intelligence for one person. MCP server that turns every correction you make to Claude into persistent, injectable memory — with an autonomous Ghost engine that learns from rejection.
NOASSERTION ★ 2 -
Federated memory for BB coding agents. Threads bridge into a Noema cortex over Streamable HTTP MCP, so what an agent learns outlives the session.
★ 1 -
Memory, a task runner, time tracking, shared rules and learned preferences for coding agents. MCP server, Claude Code plugin and mod, optional Cloudflare Worker.
MIT ★ 1 -
Mnemoverse Agent Memory for VS Code and Cursor: persistent memory for your coding agent that learns from outcomes, with shared rooms. Browser sign-in, no key to paste. MIT.
MIT ★ 1 -
A zero-dependency SQLite memory layer for AI agents that learns what works: patterns graduate to proven preferences via a built-in experiment loop.
pypi MIT