Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed clo
Memori is an agent-native memory infrastructure that provides persistent, structured memory for AI assistants and agents. It transforms agent conversations and tool executions into queryable state that persists across sessions, eliminating the need for agents to forget context between interactions. The system works as an LLM-agnostic layer that integrates with existing infrastructure through SDKs, framework plugins, and an MCP server interface. Memori automatically captures and structures memories at entity, process, and session levels, enabling agents to recall user preferences, coding patterns, project conventions, and interaction history without manual prompt engineering.
Key Features
Use Cases
- 01Persist coding patterns and project conventions so AI coding assistants remember team standards across sessions
- 02Enable customer support agents to recall user preferences and interaction history without re-reading transcripts
- 03Store tribal knowledge and architectural decisions that new team members can query through their AI assistant
- 04Maintain context in multi-step agent workflows where decisions from early steps inform later actions
- 05Reduce prompt engineering overhead by letting the system automatically surface relevant historical context
- 06Share learned conventions across team members using the same agent process ID
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Memori — FAQ
What is Memori and how does it work with AI assistants?+
Memori is a memory infrastructure layer that automatically captures and structures information from AI agent conversations and actions, then makes that context available for recall in future sessions. It works by wrapping your LLM client or connecting via MCP, capturing interactions in the background, and injecting relevant memories when needed.
How do I connect Memori to Claude Code or other MCP clients?+
Run 'claude mcp add --transport http memori https://api.memorilabs.ai/mcp/' with headers for your API key, entity ID, and process ID. For other clients like Cursor, Codex, or Warp, add the same MCP server endpoint to your client's configuration file as documented in the MCP client setup guide.
Do I need a Memori API key to use the service?+
Basic functionality works without an account but is rate-limited by IP address. For production use, sign up at app.memorilabs.ai to get a free API key with increased quotas. Set the MEMORI_API_KEY environment variable to authenticate.
Which AI clients and LLM providers does Memori support?+
Memori works with MCP-compatible clients including Claude Code, Cursor, Codex, Warp, and Antigravity. It supports OpenAI, Anthropic, Gemini, DeepSeek, Grok, and Bedrock LLM providers through SDK integrations, plus frameworks like LangChain and Pydantic AI.
Is Memori free to use for developers?+
Yes, Memori Advanced Augmentation is always free for developers. The managed Memori Cloud service provides a free tier with API key-based quotas, and you can also self-host using the bring-your-own-database option with Apache 2.0 licensed code.
What are entity ID and process ID used for?+
Entity ID identifies who is interacting (a user, team, or workspace), while process ID identifies the agent or workflow (e.g., 'claude-code' or 'support-agent'). This attribution allows Memori to scope memories appropriately and share context across team members using the same process.
How do I install Memori?+
Open the source repository on GitHub and follow its README. Memori is a mcp server — MCP Agents Market links you directly to the official repo.
Is Memori free?+
Memori is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.