From the Dakera team

Latest Post

Engineering 2026-06-01 8 min read

Memory Decay Is a First-Class Feature in Dakera, Not an Afterthought

Why AI agents need built-in memory lifecycle management — and how Dakera ships native decay curves, importance weighting, and automatic cleanup without a single pip install.

Read post

Benchmarks 2026-05-16 8 min read

AI Agent Memory Benchmarks 2026: LoCoMo, MTOB, and Beyond

Comprehensive guide to AI memory benchmarks in 2026. Compare LoCoMo, MTOB, and evaluation methodologies for agent memory systems with real score breakdowns.

Read post

Architecture 2026-05-14 10 min read

Building Multi-Agent Memory Systems: Architecture Patterns

Architecture patterns for sharing memory between AI agents. Learn namespaces, sessions, and cross-agent retrieval for multi-agent systems.

Read post

Engineering 2026-05-12 11 min read

Knowledge Graphs for AI Agents: From Entity Extraction to Traversal

Build knowledge graphs that AI agents can traverse. Learn entity extraction, relationship modeling with 4 edge types, and graph-enhanced memory retrieval.

Read post

Tutorial 2026-05-10 10 min read

MCP Protocol Explained: How AI Tools Communicate with Memory Servers

Complete guide to the Model Context Protocol (MCP) for AI agent memory. Learn how MCP tools enable LLMs to read, write, and search memory servers directly.

Read post

Tutorial 2026-05-09 12 min read

The Complete Guide to Self-Hosted AI Memory

Deploy private AI agent memory on your own infrastructure. Complete guide to self-hosted memory with hybrid retrieval, encryption, and zero cloud dependencies.

Read post

Engineering 2026-05-08 9 min read

Temporal Memory for AI Agents: How Decay and Importance Scoring Work

Deep dive into temporal memory systems for AI agents. Learn how memory decay, importance scoring, and recency weighting create human-like recall patterns.

Read post

Architecture 2026-05-11 9 min read

Vector Databases vs Agent Memory: Why They're Not the Same Thing

Vector databases store embeddings. Agent memory understands time, relationships, importance, and decay. Learn why Pinecone and Weaviate aren't enough for AI agents.

Read post

Analysis 2026-05-13 12 min read

Best AI Agent Memory Frameworks in 2026: Compared and Ranked

Compare the top AI agent memory frameworks in 2026 — Dakera, Mem0, Letta, Zep, and Hindsight. Benchmarks, architecture, deployment model, and when to use each.

Read post

Tutorial 2026-05-13 7 min read

Dakera MCP Memory Server: Setup Guide for Claude, Cursor, Windsurf

Step-by-step guide to installing and configuring Dakera as a persistent MCP memory server for Claude Desktop, Claude Code, Cursor, and Windsurf. Docker setup, MCP config, and first recall in under 10 minutes.

Read post

Benchmarks 2026-05-07 9 min read

How We Benchmark Memory: Dakera on LoCoMo

A complete breakdown of how Dakera benchmarks long-context agent memory using LoCoMo — our methodology, 88.2% score, category analysis, and how to reproduce the results yourself.

Read post

Engineering 2026-05-07 5 min read

Dakera as an MCP Memory Server: 14 Core Tools for Persistent Agent Memory

Dakera ships a native MCP server with 14 core tools (86+ available via profiles) — store, recall, search, and manage persistent memory from any MCP-compatible AI agent, Claude Desktop, Cursor, or Windsurf. Zero configuration.

Read post

Engineering 2026-05-07 7 min read

What's Open in Dakera's Open Core — SDKs, CLI, and MCP Are MIT. The Engine Is Not.

Dakera is open at the edges, closed at the core. SDKs, CLI, and MCP server are MIT-licensed. The memory engine and dashboard are proprietary. Here's the exact breakdown.

Read post

Engineering 2026-05-07 9 min read

Why Rust for AI Memory: Performance, Safety, and a Self-Hosted Memory Server That Fits in 44 MB

Dakera is a Rust-native AI memory engine: single binary, ~44 MB, no GC pauses, no runtime dependencies, and 88.2% on LoCoMo. Here is why Rust is the right language for an always-on agent memory server.

Read post

Engineering 2026-05-06 8 min read

How Agent Memory Actually Works: Hybrid Retrieval and Importance Decay

A technical deep-dive into Dakera's retrieval engine — HNSW vector search, BM25 full-text, hybrid scoring, and importance decay with half-life scheduling.

Read post

Launch 2026-05-06 6 min read

Introducing Dakera: Production Memory Infrastructure for AI Agents

We're launching Dakera: a single Rust binary that gives your AI agents persistent memory, hybrid retrieval, knowledge graphs, and built-in embeddings. Self-hosted, MIT-licensed SDKs, no external services required.

Read post