What is Meko?
Meko is the universal, self-learning context engine for agentic applications. It gives agents and people one governed place for shared context (memory, conversations, knowledge and decision traces), delivered over a remote MCP endpoint.
You don’t need to stand up and stitch together your own vector store, graph store, RAG pipeline, relational database and object store. Meko does that behind the scenes, so it works out of the box. Learn more about Meko.
What can Meko do?
Meko stores “context,” enables sharing across agents and harnesses. The exact contents of “agent context” are continually evolving. Meko currently stores and appropriately compresses and indexes information to enable users to:
- Save AI conversations as both searchable text and graph memory, so that previously asked questions don’t have to be asked by your LLM again.
- Upload documents into a hosted knowledge base, so that you don’t have to write complex data pre-processing pipelines.
- Allow resuming your personal context over time or switching between LLMs and IDEs, so you can pick up where you left off if you run out of tokens, an LLM goes down for a while, or you simply go on vacation and then need to get going again.
- Share agent memory and knowledge base documents with other agents or human teammates selectively, so all agents that work together learn from each other.
- Store agent traces in a visual portal, so you can see what the agent thought or did during the conversation
- Gain access through a remote MCP endpoint, so that any MCP-capable agent (Claude Desktop, Claude Code, Cursor, Codex, and others) can use it.
- Measure context quality, so every context search is scored for relevance, and weak results explain what information is missing.
How can Meko help me?
In a few ways:
- Remember shared context across agents, not just within one chat session.
- Share knowledge of what agents have said and done across a team, so people and agents stop rediscovering the same things independently.
- Reduce token spending by reusing what’s already been figured out, rather than reprocessing it from scratch every time.
- Decision trace all the way from the human-issued prompt to the LLM’s chain of thought.
How do software teams use Meko?
Software teams use Meko as shared context for the agentic development lifecycle (ADLC). Projects in flight keep one datapack that every coding agent and teammate works from, and development standards are layered at the organization, business-unit and project level, so agents follow the same conventions without being re-told. See Meko for ADLC.
How is Meko different from the memory built into Claude, ChatGPT or Gemini?
Built-in memory lives inside one vendor’s product and one agent’s context. Meko sits outside any single model or harness and is shared and selective: you decide what gets shared, with which agents, and with which teammates. That cross-agent,cross-vendor sharing (and the control over it) is the part that the built-in memory stores don’t do. Meko does not just persist memories, but the entire shared context (conversations, knowledge base, and decision traces), all encapsulated in a datapack that you can carry with you, regardless of the agentic SDK you use to build your agents, or if you just use a daily driver AI agent for your work life.
How is Meko different from Mem0?
Meko uses mem0 under the hood for memory extraction, so you get that capability, but Meko is the hosted, multi-tenant platform around it: graph memory, a shared knowledge base, conversation persistence, selective sharing, and observability. All this is built on YugabyteDB and exposed through a single MCP endpoint. You’re not running and scaling the infrastructure yourself.
How is Meko "AI native"?
The data primitives are built around how agents actually work. Agentic conversations, memory, and the actions they took are all context rather than a sprawl of many specialized databases (vector, graph, relational) bolted together to make that happen. That’s the distinction: the constructs (datapacks, memory, knowledge, conversations, decision traces) are shaped for agent workflows and the way humans interact with them.
Does Meko save me tokens and money?
Meko reduces repeated work. When one agent or teammate has already done something (and spent tokens to do it), the next one can reuse it by asking Meko for the information instead of reprocessing the same context. Lookups can be offloaded to our context platform instead of traversing everything through a frontier model every time. If you have your agent query Meko before it needs to search, it significantly reduces spend. You don’t have to create your own RAG in order for it to work; Meko’s infrastructure works out of the box.
How do I connect to Meko?
Meko is a remote MCP server, so you point your MCP client at the Meko endpoint and sign in. There are connection steps for Claude Desktop, Claude Code, Cursor, Codex, VS Code and other MCP clients in the Meko docs (Integrations → Connect to an AI agent).
What plans are there? Is Meko free?
Yes, Meko has a free plan. There are three plans:
- Free ($0, no credit card): 10 datapacks, 100 MB of knowledge storage and community support.
- Standard ($25/month): 50 datapacks, 5 GB of knowledge storage, larger files and email support.
- Pro (custom pricing): unlimited datapacks, custom limits, team sharing with role-based access, SSO and priority support.
See pricing for the full limits, or contact our team about Pro.
Can my agents write to the knowledge base?
Yes. Agents can add to a datapack’s knowledge base directly over MCP, as well as search it, so what one agent learns or produces becomes knowledge every agent in the datapack can use. People can still upload documents themselves in the Meko app.
Do you anonymize sensitive data (PII, healthcare)?
Meko stores what you send it. We don’t anonymize or strip names automatically. If you’re working with sensitive data, scope what you put into a datapack accordingly, and note that you can run a local model with Meko as long as it’s in a harness or chat app that can connect to a remote MCP server (most can).
Can Meko be deployed locally or in my own cloud?
Yes. Meko is open source, and the meko binary runs on your own machine: Linux (x64 or arm64) or macOS 14 or newer on Apple Silicon. See
Run Meko locally. If you’d rather not run anything, Meko Cloud at cloud.mekodata.ai runs on our infrastructure: connect your account through our remote MCP server and go. Bring-your-own-cloud deployments are on our roadmap for enterprise customers, so
reach out if that is something you want to explore.
Is Meko open source?
Yes. Meko’s source code is public under the Apache 2.0 license at
github.com/yugabyte/meko. Run it on your own machine, or use the hosted Meko Cloud.
