thought-mcp is an open-source toolkit that implements a local Model Context Protocol (MCP) memory server with bi-temporal graph, vector, and temporal layers. Below are 28 ai & ml apps with similar functionality to thought-mcp, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
memory-bridge-mcp is an open-source Python package that provides a unified MCP memory server, bridging Mind (concept graph) and Honcho (semantic vector) memory systems. It supports episodic timelines and LLM synthesis, enabling agent framework developers to manage and integrate multiple memory types in their AI agents.
projectmind-mcp is an open-source local MCP server that equips AI coding assistants with persistent memory, hybrid code search, AI-generated annotations, and an AST symbol graph. It runs entirely locally, requiring no API keys, and is aimed at developers seeking privacy and advanced code intelligence features.
mnemo-mcp is an open-source MCP server that provides persistent memory and embedded synchronization for AI agents. It is designed for developers building agentic systems requiring long-term memory and context management.
Memanto is an open-source, on-premises memory agent designed to provide persistent semantic memory for AI agents. It addresses the challenge of enabling AI agents to retain, organize, and recall information across sessions, helping them avoid forgetting decisions, conventions, and context between interactions. The tool is built on an information-theoretic search engine and is structured to run entirely on a user's local machine, requiring no API keys, vector databases, or external backend services. Memanto supports instant ingestion of information, with memories becoming searchable immediately after being written, and boasts recall latency of under 90 milliseconds. It implements features such as conflict resolution, semantic categorization into 13 types, verifiable memory sources, deterministic search, temporal queries, and info-theoretic scoring. The system is designed to prioritize freshness, ensuring that new facts outrank outdated ones, and automatically resolves conflicting data as it is ingested. The platform offers a range of integrations, supporting over 17 different agents and frameworks, including Claude Code, Cursor, Codex, GitHub Copilot, Gemini, and others. Users can manage agents, store memories, and perform retrieval-augmented generation (RAG) directly from the command line interface. Additionally, Memanto provides a local interactive dashboard for managing agents and memories, viewing conflicts and connections, and migrating from other memory solutions. Embeddings and answers are processed locally, ensuring that no data leaves the user's laptop. Installation is streamlined through a single pip install command, and users can choose between cloud and on-premises backends, with the on-premises option requiring Docker and running on localhost. Memanto is positioned as a solution for developers and teams building or operating AI agents who require reliable, persistent, and private memory infrastructure. The tool is offered completely free of charge under an open-source license.
mcp-brain is a command-line and MCP server framework for multi-agent cognitive processing. It enables developers and researchers to coordinate and execute complex agent-based workflows, supporting advanced automation and distributed AI tasks.
ithz-mcp is an open-source library that offers local-first, deterministic project memory for AI coding agents and Model Context Protocol workflows. It is designed for developers building autonomous agent systems and coding assistants.
A Claude Code MCP plugin that audits and cleans up your AI memory store
personal-memory-mcp is an open-source CLI tool that runs a local MCP server to extract and store personal memory from AI chat histories. It is intended for users and developers who want to manage their AI interaction data locally and securely.
second-brain-mcp is an open-source MCP server that transforms an Obsidian vault into a semantic memory resource for coding agents. It enables retrieval-augmented generation and memory for agent frameworks, supporting local deployment and integration with Obsidian.
mcp-external-memory is an open-source MCP server that provides large language models with persistent and searchable semantic memory. It enables AI developers to enhance LLM capabilities by integrating long-term memory and efficient retrieval into their applications.
evermemos-mcp is an open-source Model Context Protocol (MCP) server that brings long-term memory capabilities to AI coding tools through integration with EverMemOS. It is intended for developers building or extending AI-powered development tools that require persistent context management.
forgetful-ai is an open-source MCP server that provides persistent, semantically-searchable memory for AI agents. It enables developers to integrate long-term memory and retrieval capabilities into their agent architectures.
codebase-memory-mcp is an open-source, fast code intelligence engine designed for AI coding agents. Distributed as a single static binary MCP server, it enables local analysis of codebases for agent frameworks and research. It is suitable for developers building AI-powered code tools and workflows.
MCP server for Link local agent memory — remember, recall, search, context, and graph traversal
imagine-mcp is an open-source MCP server that enables image and video understanding and generation using multiple AI models, including Gemini, OpenAI, and Grok. It supports multimodal tasks and integrates with the Model Context Protocol.
yourmemory is an open source Python package that provides persistent memory capabilities for Claude-based and MCP-native AI agents. It features semantic deduplication, Ebbinghaus forgetting curve support, and integrates with SQLite and PostgreSQL. Designed for developers building advanced AI agent workflows.
Persistent memory MCP server for Claude Code, Codex CLI, Cursor and any MCP client: 46 tools — knowledge graph, temporal facts, procedural memory, episodic memory, AST ingest, pre-edit guard, auto-consolidating error capture
cctx-mcp is an open-source MCP server designed for AI agents, offering structured code analysis that significantly reduces token usage. It integrates with Tree-sitter and is aimed at developers building efficient AI-powered code tools.
contextl-mcp is an open-source MCP server designed for AI coding agents. It provides repository intelligence, code search, and integrates with the Model Context Protocol, allowing developers to build advanced AI-powered code tools. Distributed under the MIT license.
mcp-remlezrd is an open-source server implementing the Model Context Protocol (MCP) for AI agents. It allows developers to manage, exchange, and serve context for AI workflows, supporting integration with agent frameworks and research projects.
june-mcp is an open-source MCP server for the Junê ecosystem, enabling MCP agents to access a shared, cited knowledge-graph memory. It facilitates memory sharing and context management for agent-based applications. Designed for developers building advanced AI agents.
AI agent memory system with SQLite+FTS5, MCP integration, and quality gates
compos-mcp is an open-source MCP server designed for integrating Compos architectural memory into AI and LLM workflows. It provides a model context protocol implementation, allowing developers to manage and serve contextual memory for advanced AI applications. Suitable for AI developers and researchers building memory-augmented systems.
MCP server that gives LLMs persistent graph-structured memory
nucleus-mcp is an open-source agent operating system designed for AI agents, offering persistent memory, governance, and compliance features. It is suitable for developers building autonomous AI agents that require robust memory and regulatory support.
global-memory-mcp is an open-source Python library and CLI tool that offers local-first, project-aware durable memory through a versioned Model Context Protocol (MCP) interface. It is designed for developers building AI agents or applications that require persistent, structured memory with semantic search capabilities.
graphite-mcp is an open-source MCP server that connects the Graphite Financial Knowledge Graph to MCP-compatible clients such as Claude Code and Codex CLI. It enables structured financial data access for AI-powered tools.
cambium-mcp is an open-source Python package that implements the Model Context Protocol (MCP) for managing the lifecycle of knowledge events. It enables distillation and recall of agent and context-keeper events across projects, supporting local, team, and organizational memory workflows. Designed for developers building AI agent systems.
