"Understanding How to Use a Browser" matching MCP servers:

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

A TypeScript-based MCP server that implements a simple notes system, allowing users to create, access, and generate summaries of text notes through Claude Desktop.

This server provides a note storage system with a custom URI scheme, allowing users to add and summarize notes, with adjustable summary detail levels.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

Private knowledge base with Markdown pages and assets, exposed via MCP for agent access.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.

Enables agents to perform read-only access to explicitly permitted chats on Telegram Web, including history, native search, post comments, photos and files, multi-chat context collection, and persistent local conversation history via a dedicated browser profile without Telegram API registration.

Proxies every Playwright MCP browser tool while automatically capturing what an agent learns on each site — fast paths, fixes, dead ends, and the site's observed internal API — and injecting it the next time any agent reaches that domain. Learned lessons and saved procedures become callable tools, so sessions start where previous ones stopped.

Proxies every Playwright MCP tool so agents drive a real browser, while automatically attaching per-site lessons, self-firing fixes, saved procedures and the site's observed internal API to each navigation. Later sessions on the same domain start where the previous one stopped, without anyone having to write or request the notes.

Turns GitHub repository history into a cited maintainer skill for coding agents, providing tools to collect evidence, query the knowledge graph, and inspect bundles.

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

Turn Obsidian notes into agent-ready context, preview-only plans, and safe repo handoffs.

Production-ready MCP server providing RAG, hierarchical memory, and 8+ tools for AI agents via the Model Context Protocol.

Enables AI agents to maintain persistent, searchable two-layer memory with 37 tools, hybrid search, knowledge graphs, and enterprise features like authentication and backups.

Project management and session memory for AI agents that provides 13 tools for tracking projects, tasks, and context during AI coding sessions.

Enables querying PDF documents using natural language with grounded answers and source citations via a local RAG pipeline.

A local-first RAG system that indexes personal documents and enables querying them via an MCP tool, keeping data private with local embeddings.

Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.

Enables MCP clients to search a Zotero library, read items, take notes, organize collections, and perform semantic search over PDFs.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

Enables converting PDF, EPUB, and TXT books into validated chapter analyses, guarded Obsidian notes, and installable Agent Skills that can be reused across Codex, Claude Code, or other MCP-capable clients.

MCP server that connects AI agents to Google NotebookLM, enabling natural language interaction with notebooks, including Q&A, source ingestion, and audio overview generation.

MCP server for integrating LightRAG with AI tools. Provides a unified interface for interacting with LightRAG API through the MCP protocol.

Enables AI clients to search a personal corpus, read relevant source passages, and answer questions with traceable evidence from imported sessions, notes, and articles.

Enables local-first knowledge management for Codex, providing tools for guided discussions, contextual recall, review, and daily topics.

Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying.

Enables context optimization for LLM-powered coding assistants by compressing prompts, injecting task protocols, and providing a 2nd Brain knowledge graph with tools for prompt compression, knowledge retrieval, metrics, and runtime configuration.

Enables AI assistants to persistently add, read, and summarize sticky notes through MCP-compliant tools, resources, and prompts.

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.

Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.

A self-hostable, open-source, semantically-searchable Agent Skills registry delivered over MCP, with a three-tier progressive disclosure architecture.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

A local memory engine any AI tool can use.

Enables any MCP-capable LLM to use a private, self-hosted persistent brain with categorized memory, skills, tools, devices, email, calendar, webhooks, scheduled jobs, encrypted secrets, and per-user areas.

A self-contained, in-memory graph database for AI Agents. Provides semantic code understanding through the Model Context Protocol (MCP).

MCP server for managing a task graph with live visualization. Enables Claude Code to create, update, and link nodes (tasks, subtasks, ideas, etc.) while a browser viewer displays the graph in real time.

Provides brain-inspired long-term memory for MCP clients, enabling persistent user understanding across sessions with Chinese-optimized hybrid retrieval and evolving user profiles.