dakera-deploy
Active·★ 19·NOASSERTION·Updated 2026-10-19
Dakera Deployment provides production-ready infrastructure to deploy the Dakera AI agent memory platform across various environments like Docker, Kubernetes, or Helm. It offers persistent, session-aware, and cross-agent memory capabilities, including vector search, knowledge graphs, and session management, all within a self-hosted Rust binary with no external dependencies.
#AI Agents#Memory Management#Vector Database#RAG#Kubernetes#Docker#Helm#Deployment
01
Features
01Agent-native memory platform purpose-built for AI agents requiring persistent, session-aware, and cross-agent memory.
02Comprehensive memory features: vector search, hybrid retrieval (BM25 + HNSW), knowledge graphs, session management, and built-in embeddings.
03Self-hosted Rust binary with zero external dependencies, ensuring data stays on your infrastructure and achieving high performance (88.2% on LoCoMo benchmark).
04Flexible deployment options including Docker, Docker Compose, Kubernetes with kubectl manifests or Helm charts, and VS Code Devcontainers.
05Production-ready features: high availability (HA) cluster mode with load balancing, configurable tiered storage, authentication, and integrated monitoring with Prometheus and Grafana.
02
Compatibility
Docker
Containerization
Verified via docs
Kubernetes
Orchestration
Verified via docs
Helm
Package Manager
Verified via docs
VS Code / Cursor
Development Environment
Verified via docs
Python
SDK
Verified via docs
Node.js
SDK
Verified via docs
03
Quick start
1
$ git clone https://github.com/dakera-ai/dakera-deploy
2
$ cd dakera-deploy/docker
3
$ docker compose -f docker-compose.local.yml up -d
04
Use cases
↳Local development and testing of AI agents using in-memory storage or MinIO-backed persistence via Docker Compose or Devcontainers.
↳Deploying a single-node, production-grade AI agent memory system with MinIO storage, caching, and health checks for staging or smaller production environments.
↳Establishing a high-availability (HA) cluster with multiple Dakera nodes and a Traefik load balancer for robust production environments.
↳Cloud-native production deployments of the Dakera memory platform using Kubernetes with `kubectl` manifests or Helm charts for scalability and orchestration.
↳Integrating observability into Dakera deployments with Prometheus and Grafana for monitoring request rates, latency, cache performance, and cluster health.
05
Alternatives
enquire-mcp★ 34
The most advanced Obsidian MCP — long-term memory for AI agents. Hybrid retrieval (BM25 + ML + BGE rerank, RRF-fused), HNSW live-update, agentic RAG (HyDE + sub-question), Obsidian Bases, PDFs+OCR. For Claude Code/Desktop, Cursor, ChatGPT, Codex, OpenClaw. MCP-native, MIT, SLSA L2.
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
montycat-mcp★ 28
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
fava-trails★ 26
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
Comments
Log in to leave a comment
No comments yet. Be the first!