Work with memory
Meko's memory system gives agents persistent recall across sessions.
This guide covers per-agent memory operations you drive from a coding agent over MCP: add a memory, search for relevant memories, and list everything stored for a user or agent.
Meko can also move memories into shared, institutional knowledge through a separate review flow (learnings, collective memory, and shared knowledge). That lifecycle, including how candidates are identified and promoted from the Learnings tab in the Meko UI, is described in Learnings. For how extraction and dual storage (vectors + graph) work under the hood, see Memory.
Private memories are one part of a datapack's knowledge base. The other major component is source data, which includes unstructured files (text, PDFs, documents) and structured sources (databases, tabular data). See Knowledge bases.
Memories are stored in a semantic graph with graph edges for entity relationships (for example, John likes bananas) and document chunks with vectors for similarity search. That combination supports retrieval by relationship and by meaning, not only by exact text match.
Add memories
Via MCP (from your coding agent)
The simplest way to add memories is through natural language in your coding agent:
Please remember that I like to take vacations at tropical beach locations, on a budget
Remember this coding preference: I prefer Python type hints and use pytest for testing
The MCP server calls memory_add behind the scenes, which uses an LLM to extract entities and relationships from your text.
Search memories
Via MCP (from your coding agent)
With Meko connected through MCP, your agent can retrieve memories on its own when answering questions that clearly depend on stored preferences or facts. You do not have to name a tool for that to happen. When you want to inspect or force a lookup, for example, to confirm what was saved, ask in natural language, as in the following examples.
Example 1:
What are my vacation preferences?
Example 2:
What coding standards have I set?
The MCP server performs a semantic similarity search across your memories and returns the most relevant results with relevance scores.
How search works
Memory search combines two strategies:
- Vector similarity. Finds memories with semantically similar embeddings.
- Graph traversal. Finds related entities and relationships. For example, searching for "vacation" might also surface memories about "travel budget" through graph connections.
Results from both strategies are combined and ranked, allowing a memory to be retrieved not just by exact match, but by semantic similarity as well. For example, the memory "John likes bananas" can be surfaced in response to not only the query "who likes banana?" but also a semantic query like "Who likes fruits?"
View all memories
To see every memory Meko has stored for a user or agent, ask your coding agent in plain language. For example:
List every memory Meko has for me in my default datapack.
Show all stored memories for my cursor agent — I want the complete list, not just the top matches.
You should see the agent use the MCP tool memory_get_all to return the full list (not ranked like search), which is useful for auditing or building a memory dashboard.
Next steps
- Learn about memory
- Learnings — review, identification, and promotion to shared knowledge
- Work with knowledge bases