Every Dakera instance ships a built-in MCP server. Point Claude Desktop, Cursor, or any MCP-compatible agent at it and your agent gets full persistent memory — store, recall, search, decay, sessions, and knowledge graphs — with zero additional configuration.
Most AI agents forget everything when the conversation ends. The Model Context Protocol (MCP) gave agents a way to call external tools — but most MCP memory implementations are thin wrappers: store a string, retrieve a string, done. That works for a shopping list. It breaks down for agents that need to recall user preferences from three weeks ago, reason across dozens of past sessions, or surface a fact from session 12 while answering a question in session 47.
Dakera was built specifically for this problem. The MCP server is not a feature added on top — it is one of the primary interfaces into the same engine that scores 87.6% on the LoCoMo long-context memory benchmark.
Most MCP memory servers expose three operations: remember, recall, forget. Dakera exposes 83, organized into functional groups that cover the full lifecycle of agent memory:
The breadth matters because real agent workloads are not uniform. A coding assistant needs different memory patterns than a customer support agent. A research agent needs cross-session entity linking that a short-lived task agent does not. Dakera's 83 tools let agents express exactly the memory operations they need — not work around a lowest-common-denominator API.
Start a Dakera instance (binary or Docker) and add it to your Claude Desktop config:
{ "mcpServers": { "dakera": { "command": "dakera", "args": ["mcp"], "env": { "DAKERA_API_KEY": "your-key", "DAKERA_URL": "http://localhost:3300" } } } }
Restart Claude Desktop. You now have 83 memory tools available in every conversation. Claude can store anything important, recall context from months ago, and maintain structured knowledge about people, projects, and decisions — automatically.
No embeddings API required. Dakera runs built-in embedding models (MiniLM, BGE, E5) via the Candle runtime. Semantic search works out of the box — no OpenAI API key, no external service, no additional cost.
Cursor and Windsurf both support MCP servers. Add Dakera as an MCP server in Cursor's ~/.cursor/mcp.json or Windsurf's MCP configuration, and your coding agent gets persistent memory across projects:
~/.cursor/mcp.json
When an agent calls dakera_store through MCP, Dakera does more than write a record to disk:
dakera_store
When an agent later calls dakera_recall, hybrid search (HNSW + BM25, RRF fusion) surfaces the most relevant memories regardless of how they were phrased — not just exact matches.
dakera_recall
Every memory stored through Dakera's MCP server stays on your infrastructure. There is no call home, no cloud sync, no telemetry of memory content. Pull the Docker image, set your API key, and every memory operation happens entirely within your stack.
This matters for developers and organizations that cannot send conversation content to third-party services — a constraint that makes fully-managed cloud memory vendors a non-starter for many production workloads.
The LoCoMo benchmark evaluates long-context memory recall across 50 conversation sessions and 1,540 questions — temporal reasoning, multi-hop facts, implicit references, and entity tracking. Dakera scores 87.6% on the full dataset using standard single-pass evaluation with no LLM post-processing step.
Many memory systems use a second LLM call (reranking, synthesis, or "justify" steps) to boost benchmark scores. This improves numbers but adds latency and cost to every recall operation. Dakera's score comes from the retrieval engine alone.
For reference: systems like Hindsight (89.61%) achieve their top score with Gemini-3 Pro as a cross-encoder — a cloud API call on every recall. Their self-hosted OSS-120B variant scores 85.67%, which is below Dakera's 87.6% in standard evaluation.
Full benchmark methodology — How we run the evaluation, what each question category tests, and how to reproduce our results against your own Dakera instance: Dakera on LoCoMo →
Dakera is in public alpha. The MCP server is available now — no waitlist required. To get started:
If you are building an agent framework and want to evaluate Dakera for production use, reach out on GitHub — or join the sign up for updates for managed deployment with SLA support.
More on how the memory engine works: Hybrid Retrieval and Importance Decay →
DAKERA