by openmemind
Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.
# Add to your Claude Code skills
git clone https://github.com/openmemind/memindLast scanned: 5/9/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-09T06:15:55.262Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}memind is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by openmemind. Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance. It has 901 GitHub stars.
Yes. memind passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/openmemind/memind" and add it to your Claude Code skills directory (see the Installation section above).
memind is primarily written in Java. It is open-source under openmemind on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh memind against similar tools.
No comments yet. Be the first to share your thoughts!
Memind achieves state-of-the-art results across all three mainstream long-memory benchmarks: LoCoMo, LongMemEval, and PersonaMem.
Memind is an open-source, self-evolving memory and context engine for AI applications and agents.
It is not a vector-store wrapper. Memind captures raw context from conversations, documents, images, audio, tool calls, agent timelines, and resolved tasks, then turns it into structured user memory, reusable agent experience, evolving insights, connected memory graphs, and task-aware memory threads.
At retrieval time, Memind assembles the right context across these memory layers and exposes it through REST APIs, HTTP MCP tools, SDKs, Java runtime APIs, and first-party agent integrations.
Memind keeps the raw source, extracted memory, structured understanding, graph relationships, and task timelines connected. This lets AI systems retrieve both precise evidence and higher-level context instead of relying on flat snippets alone.
Memind is a general memory and context layer for almost any AI system that needs long-term context. Common use cases include:
| Scenario | What Memind remembers |
|---|---|
| Coding agents | Project context, tool experience, resolved tasks, durable instructions |
| Local personal agents | User preferences, long-running timelines, local workflows |
| Chatbots and companions | User profiles, relationships, behavior patterns, life events |
| Workflow agents | Directives, playbooks, operational context, task history |
These are only examples. Memind can also support copilots, enterprise assistants, support automation, research tools, knowledge workers, and any AI application that needs to remember users, tasks, documents, decisions, tools, timelines, and previous outcomes across sessions.
For deeper architecture, configuration, rawdata plugins, MCP tools, SDKs, and agent integrations, see docs.openmemind.com.
Choose the path that matches how you want to use Memind:
memind-server and the admin UI with one command.memind-server and memind-ui directly from source..envCreate a local .env file:
cp .env.example .env
For the default setup, edit these values first:
OPENAI_API_KEY=your-api-key
OPENAI_BASE_URL=https://openrouter.ai/api
OPENAI_CHAT_MODEL=openai/gpt-4o-mini
OPENAI_EMBEDDING_MODEL=openai/text-embedding-3-small
The default openai client can point to OpenAI or any OpenAI-compatible endpoint by changing
OPENAI_BASE_URL and the model names. OpenRouter, DeepSeek, GLM, SiliconFlow, and similar
providers can be used through the same openai provider path when they expose an
OpenAI-compatible API.
Model names are provider-specific. The default values use OpenRouter-style model names. If you use
OpenAI directly, use OpenAI model names such as gpt-4o-mini and text-embedding-3-small.
docker compose up -d --build
After the containers start:
http://localhost:8080http://localhost:8366/open/v1/healthhttp://localhost:8366/open/v1http://localhost:8366/admin/v1http://localhost:8366/mcpcurl http://localhost:8366/open/v1/health
The health endpoint verifies that the server is running. Model credentials are validated when Memind performs extraction, retrieval, embedding, or rerank calls.
The UI container proxies /open/* and /admin/* to memind-server, so the browser can use the
UI as a same-origin local admin console.
# View logs
docker compose logs -f memind-server
docker compose logs -f memind-ui
# Stop containers but keep persisted memory data
docker compose down
# Stop containers and remove persisted memory data
docker compose down -v
By default, memind-server stores SQLite data and the fallback file vector store in the Docker
volume memind-data, mounted at /app/data inside the container.
The Compose setup is intended for local development and inspection. The admin UI has no built-in authentication, so do not expose it directly to public networks.
Memind has two AI configuration layers:
| Layer | Purpose |
|---|---|
spring.ai.* |
Provider defaults, API keys, base URLs, and model options |
memind.ai.* |
Named chat/embedding clients and slot routing inside the memory pipeline |
The default server configuration defines one chat client and one embedding client:
memind:
ai:
chat:
default-client: openai
clients:
openai:
provider: openai
embedding:
client: opena