</>MCP Agents Market
Plugin

memind

by openmemind898JavaUpdated 2026-08-13

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

Claude CodeCodexOpenClawHermes

Memind is a Java-based cognitive memory and context engine for AI agents that provides persistent, evolving memory across sessions. It captures conversations, documents, tool calls, and agent timelines, then organizes them into structured memory graphs, insight trees, and task threads. The system achieves state-of-the-art performance on LoCoMo, LongMemEval, and PersonaMem benchmarks while keeping retrieved context compact enough for production use. Memind integrates with AI agents through first-party plugins (Claude Code, Codex, OpenClaw, Hermes), an HTTP MCP server, REST APIs, and native SDKs in five languages.

Key Features

State-of-the-art performance ranking #1 on LoCoMo, LongMemEval, and PersonaMem long-memory benchmarks
Insight Tree architecture that distills raw memories into evolving Leaf → Branch → Root intelligence hierarchies
Dual USER and AGENT memory separation for preserving both user profiles and agent directives/tool experience
Multi-layer retrieval across Insight Trees, Memory Graphs, Memory Threads, vector search, BM25, and optional deep retrieval with reranking
Memory Graphs connecting entities, mentions, semantic/temporal/causal links to recover context beyond vector similarity
Memory Threads grouping related items into durable task timelines with lifecycle state and enrichment
Ingestion of conversations, documents, images, audio, tool calls, and agent timelines with typed processors
11+ MCP tools, 5 SDKs (TypeScript, Python, Java, Go, Rust), and first-party plugins for popular agents

Use Cases

  • 01Coding agents that need project context, resolved tasks, and tool experience across sessions
  • 02Personal AI assistants remembering user preferences, timelines, and local workflows
  • 03Chatbots and companions maintaining user profiles, relationships, and life events
  • 04Workflow agents preserving directives, playbooks, and operational task history
  • 05Enterprise assistants and copilots requiring long-term context and decision memory
  • 06Research tools and knowledge workers needing document memory and evolving insights

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

memind — FAQ

What is Memind?+

Memind is an open-source, self-evolving memory and context engine for AI agents that turns raw context from conversations, documents, tool calls, and timelines into structured memory graphs, insight trees, and task threads. It integrates via Claude Code plugin, MCP server, REST APIs, or native SDKs.

How do I install the Claude Code plugin for Memind?+

First start the Memind server locally via Docker Compose or direct installation, then connect Claude Code to the MCP endpoint at http://localhost:8366/mcp using 'claude mcp add --transport http memind http://localhost:8366/mcp'.

Which AI clients and agents does Memind support?+

Memind provides first-party plugins for Claude Code, Codex, OpenClaw, and Hermes. It also works with any MCP-compatible client through its HTTP MCP server, and can integrate with custom agents via REST APIs and SDKs in TypeScript, Python, Java, Go, and Rust.

What are the prerequisites and API keys needed?+

Memind requires Java 21, Docker (for Docker Compose setup), and API keys for a chat model and embedding model. The default configuration uses OpenAI-compatible providers (OpenAI, OpenRouter, DeepSeek, etc.) configured via OPENAI_API_KEY and OPENAI_BASE_URL environment variables.

Is Memind free and open source?+

Yes, Memind is released under the Apache License 2.0 and is completely free and open source. You will need to provide your own API keys for the underlying chat and embedding models.

How does Memind compare to other memory systems?+

Memind ranks #1 among listed baselines on all three mainstream long-memory benchmarks (LoCoMo, LongMemEval, PersonaMem) while using fewer context tokens than competitors like EverMemOS. It's the first Java-native memory engine to achieve state-of-the-art performance.

How do I install memind?+

Open the source repository on GitHub and follow its README. memind is a plugin — MCP Agents Market links you directly to the official repo.

Is memind free?+

memind is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Knowledge & Memory PluginsDeveloper Tools PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories