An MCP server that provides long-term memory and semantic search using Qdrant and OpenAI embeddings, with tools for storing, searching, and managing knowledge.
Provides long-term memory for AI coding agents, enabling facts like stack, conventions, and decisions to be recorded once and recalled across sessions.
Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.
Provides tools for Chain of Consciousness provenance logging and Agent Rating Protocol reputation scoring to establish trust and accountability for AI agents. It enables tamper-evident activity tracking, integrity verification, and bilateral reputation management.
Knowledge graph for token-efficient code reviews. Builds a structural map of your codebase with Tree-sitter, tracks changes incrementally, and gives AI agents precise context via MCP tools. Features fixed multi-word search, qualified call resolution, dual-mode embedding (ONNX local + LiteLLM cloud), and output pagination.
Enables querying a compressed knowledge graph of the NVIDIA AI developer stack, allowing users to traverse declared dependencies, prerequisites, and relationships across 20 domains via read-only MCP tools like query_ckg, get_prerequisites, and search_concepts.
Provides a shared knowledge base MCP server for coding agents to read and leave one-sentence lessons, tagged by technology stack, to avoid repeated mistakes across sessions.
Make it easy for agents to build their context about your projects over time
The server provides a set of tools to help agents accumulate knowledge about a project over time in a structured way.
A Stack Overflow for Claude Code agents — a shared pool of solved-problem fixes.An agent hits an error, calls ask_pool for ranked prior fixes; solves something new, calls post_solution. Semantic search + write-time content shield. Free, Apache-2.0.
An MCP server providing 82 tools for persistent memory, governance, and consciousness continuity for AI instances. Enables local-first, runtime-reflexive operation with cross-device access and recursive self-awareness.
An MCP server that provides Claude Code with 99 methodology skills, seed patterns, decision logging, and memory tools to improve software development decisions. It acts as a cognitive scaffold layer, enabling better working methods rather than just additional data.
Connects coding and chat agents to a cloud API for searching and managing conversational memories, indexing repositories, finding code by behavior, and ranking likely bug locations from symptoms or stack traces.
Provides a traversable knowledge graph of the NVIDIA NemoClaw stack, enabling deterministic queries over its architecture, dependencies, and policies via MCP.
Enables coding agents to query and expand a personal tech-stack knowledge vault via MCP tools for searching notes, recommending stacks, retrieving practices and checks, and proposing changes to an inbox for approval.
A lightweight MCP sidecar exposing safe, read-only Anchor note tools to ChatGPT via a tunnel client in the same Docker stack. It currently supports listing, searching, reading notes, tags, and attachment metadata without exposing Anchor's private API or database.
A minimal, tag-free personal memory system that syncs across all Claude interfaces (mobile, web, desktop, Claude Code). Built on Cloudflare's edge stack for zero-maintenance serverless operation.
Gives AI coding agents persistent, structured memory of a software project across sessions — goals, architecture, tech stack, decisions, and progress — stored locally in an embedded SQLite vault. Agents recall and update that context automatically through MCP tools whenever they open the project.
Unified FastAPI server exposing 18 tools across 7 domains for the DOME-HUB sovereign stack, including E8 lattice, AMMA monitor, Akashic Records, and more.
Local-first MCP server providing a shared, AES-256-GCM encrypted SQLite ledger of structured user state (stack, projects, preferences) that any MCP-aware tool can read/write, with user-held keys and optional zero-knowledge sync.
A fully local AI stack that provides OpenAI/Anthropic-compatible LLM API, embeddings, mem0 memory, and second-brain RAG via MCP tools, all running independently with no cloud dependencies.
A persistent memory system using a local knowledge graph that enables Claude to remember information about users across chats, with advanced search, graph traversal, and filtering capabilities for entities, relations, and observations.
Provides persistent, cooperative memory for LLMs via MCP, with SQLite storage and tools for capturing, recalling, consolidating, crystallizing, and forgetting memories across sessions.
Farnsworth gives Claude persistent memory and autonomous agent capabilities. It runs locally and provides Hierarchical Memory (Working -> Episodic -> Archival), a Multi-Model Swarm (combining Ollama models for better reasoning), and specialized agents for Web Browsing, Vision (CLIP), and Voice (Whis
Enables querying and retrieval of structured video summaries from a SQLite knowledge base through Claude or Cursor, supporting search, precise matching, and tag-based filtering.
Gives every AI agent a shared, persistent memory by ingesting Obsidian vaults, code, transcripts, bookmarks and terminal sessions into a three-tier SQLite FTS5 store, then serving token-optimized hybrid retrieval, classification, promotion and cross-source synthesis over MCP and REST. This lets multiple agents read from and write to one compounding brain so each session starts with better context than the last.
Exposes a developer's local context (communication preferences, stack, repos, memory models) to AI agents via MCP tools and resources, enabling them to bootstrap with local guidelines and reduce context hallucination.
A minimal, tag-free personal memory system that syncs across all Claude interfaces. Built on Cloudflare's edge stack for zero-maintenance serverless operation.
An advanced contextual memory server for agent orchestration providing chronological history, semantic vector search via Redis Stack, and temporary scratchpad storage. It also enables context compression through history rollups and facilitates inter-agent communication using a Redis-based Pub/Sub system.
MCP server with intelligent memory management and file monitoring that enables context-aware AI assistance across multiple LLM providers (Grok, OpenAI, Claude, Ollama) with persistent memory of interactions and real-time file system changes.
Enables parsing of messy multi-turn Slack and WeChat Work troubleshooting threads into validated Q&A resolution pairs, stripping duplicate organizational knowledge and synthesizing structured Markdown SOP runbooks. Exposes this curation capability as MCP tools over JSON-RPC 2.0 stdio, with zero external dependencies.
Local dashboard and MCP server that maintains a live project registry and skill library, enabling coding agents to pull project context and automatically update status, stack, and next steps.
Enables Claude Code to store and recall persistent cross-session memories using a self-hosted stack of Qdrant, Neo4j, and Ollama, backed by Anthropic or a local LLM. Exposes 11 tools for adding, searching, updating, and deleting memories plus knowledge-graph entities, with optional session hooks that auto-inject context on startup and save summaries on exit.
A drop-in replacement for mcp-memory-duckdb with full concurrent access support using Redis Stack. Enables persistent knowledge graph storage with full-text search and multi-session concurrent access.
Enables Claude Code to store and retrieve persistent memories across sessions using a self-hosted stack of Qdrant, Neo4j, and Ollama, with either Anthropic or local Ollama as the main LLM. Exposes 11 tools for adding, searching, updating, and deleting memories plus knowledge-graph entity and relationship queries, along with session hooks that auto-inject context on start and save summaries on exit.
Universal FastMCP bridge into a hybrid memory stack, enabling MCP-capable agents to save, search, read, and recall memories using OpenViking and Honcho backends.
Persistent project context for Google Gemini. 12 MCP tools for .faf
Project DNA — auto-detect your stack, validate, score, and sync across CLAUDE.md, GEMINI.md, and AGENTS.md. Python/FastMCP. IANA-registered format (application/vnd.faf+yaml). 183 tests. One file, every AI platform.
Provides AI agents with a persistent, live-synchronized memory bank for a builder's identity, projects, tech stack, snippets, vision, and bio materials, allowing them to read and update this context across sessions. Supports cloud-backed Neon PostgreSQL storage, encrypted secrets, and optional local-only operation.
Local workspace memory for Claude Desktop.
Indexes documents into a vector store with hybrid search, cross-session memory, auto-learn, and knowledge graph.
A local SQLite-backed MCP server that gives AI coding agents persistent cross-session memory and invariants, Turn-0 workspace grounding with spin-loop and output-defect guards, and two-phase-commit staging so file edits are audited and applied atomically. It also exposes AST symbol/call-graph search, bounded page memory, and workspace document retrieval, letting agents work safely across sessions without any cloud dependency.
Exposes Dify knowledge base retrieval capabilities via MCP for use in Cursor and other MCP-compatible clients, enabling semantic search and document browsing.
OpenZIM MCP Server provides AI models structured, offline access to ZIM format knowledge archives (Wikipedia, Wiktionary, Stack Exchange, Kiwix Library) via a Model Context Protocol server with smart namespace navigation, full-text search with suggestions, structure-aware retrieval (sections, tables of contents, related articles), link-graph extraction, archive-type presets, and both Simple (single natural-language tool) and Advanced (8 specialized tools) modes with streamable HTTP transport, bearer auth, and per-entry resources with subscriptions.
Cross-session memory for AI coding agents: six tools (save/search/list/get/update/delete) over a local-first SQLite store with human-readable Markdown mirror, semantic search, background consolidation, and human-reviewed conflict resolution. Requires the dsh-mneme DSH plugin running locally.
A remote MCP server enabling semantic memory across multiple AI platforms like Perplexity Comet and Claude Desktop, with vector embeddings for intelligent retrieval.
An MCP server that captures and retrieves team decisions and facts from Slack with provenance, supporting search, remember, and forget operations, while integrating with external tools via MCP client.
A long-term memory system built for AI Agents. Agent wakes up already knowing who he is, not querying "who am I?" every session. Every turn calling back accurate memory context. Achieving accurate memory hits while also preventing memory from expanding at scale. No compression, no forgetting.
A Model Context Protocol (MCP) server for interacting with MongoDB stock data to provide portfolio recommendations and market insights, exclusively for the Indian stock market (NSE/BSE).