DAKERAStop rebuilding context on every agent call
Your LangChain, CrewAI, or LlamaIndex agents lose everything when a session ends — users re-explain preferences, bots repeat the same questions, multi-agent workflows restart from scratch. Install the Dakera integration and your agents recall context in under 50ms across sessions, with no embeddings running locally and no data leaving your server.
MCP Clients
Connect Dakera to any MCP-compatible AI tool — zero code changes, 14 core memory tools available instantly (86+ via profiles for power users).
Cursor
Persistent memory for AI coding — your assistant remembers project architecture, decisions, and debugging context across every session.
Add to .cursor/mcp.json
Claude Desktop
Give Claude persistent cross-session memory — preferences, project context, and knowledge that survives restarts.
Add to claude_desktop_config.json
Windsurf
Persistent memory for Cascade AI — remembers project architecture, coding decisions, and debugging context across every Windsurf session.
Add to ~/.codeium/windsurf/mcp_config.json
Python integrations
LangChain
DakeraMemory for persistent conversation chains. DakeraVectorStore for server-side RAG — no local embedding model needed.
pip install langchain-dakera
CrewAI
DakeraStorage as CrewAI's long-term memory backend. Your crews accumulate knowledge across every run — session-persistent, semantically recalled.
pip install crewai-dakera
LlamaIndex
DakeraMemoryStore for agent memory. DakeraIndexStore replaces local vector indices — server-side embedding, no OpenAI API key needed for RAG.
pip install llamaindex-dakera
AutoGen
DakeraMemory plugs directly into AutoGen's memory list. Agents and multi-agent teams share persistent, decay-weighted memory across sessions.
pip install autogen-dakera
Strands Agents
A dakera_memory tool plus a drop-in DakeraMemoryStore for the Strands agent loop — decay-weighted recall, ranked by importance × recency × relevance.
pip install strands-dakera
PraisonAI
A drop-in "dakera" memory provider alongside mem0, chroma, and mongodb. Short-term (working) and long-term (episodic) tiers with importance-weighted recall.
pip install "praisonaiagents[dakera]"
Agent Squad
DakeraRetriever grounds agents in server-side semantic search over a Dakera namespace — no local embedding model. Ships in three languages.
pip install "agent-squad[dakera]"
JavaScript / TypeScript
LangChain.js
DakeraMemory and DakeraVectorStore for LangChain.js chains. Full TypeScript types, compatible with Node.js ≥ 20.
npm install @dakera-ai/langchain
Vercel AI SDK
Cross-session memory via the AI SDK's two extension points — language model middleware and tools. No model or provider changes required.
npm install @dakera-ai/ai-sdk
Platforms
No-code and low-code agent platforms — add Dakera memory without writing an SDK integration.
Dify
Six memory tools — store, recall, search, get, update, forget — for Dify Agent, Chatflow, and Workflow apps. Install from the Marketplace, point it at your server, done.
Dify Marketplace → Dakera Memory
Governance
Persistent governance state for LLM applications — policy decisions, cost tracking, and delegation audit trails backed by Dakera's decay-weighted memory engine.
TealTiger
DakeraCostStorage and DakeraDecisionStore for persistent governance state. Cost tracking, policy decisions, and delegation audit trails — all decay-weighted and semantically recalled.
pip install dakera[tealtiger]
How integrations work
Every integration is a thin adapter between the framework's memory or vector-store interface and the Dakera REST API. No embeddings run locally — the Dakera server handles them with its built-in ONNX inference engine.
| Feature | What Dakera provides |
|---|---|
| Embedding | On-device ONNX model on the server — zero external API calls |
| Vector search | HNSW with IVF + SPFresh, BM25 hybrid reranking |
| Memory decay | Access-weighted importance, configurable half-life |
| Sessions | Per-session memory grouping and lifecycle management |
| Cross-agent network | Agents share knowledge via the cross-agent graph API |
Prerequisites
All integrations require a running Dakera server. The fastest way to get one running:
docker run -d \
--name dakera \
-p 3300:3300 \
-e DAKERA_ROOT_API_KEY=dk-mykey \
ghcr.io/dakera-ai/dakera:latestFor persistent storage, see the Deployment guide. Then pick your framework above and follow the integration docs.
Your first integration in under 10 minutes
One Docker command starts the server. One pip install adds the integration. Your LangChain or CrewAI agents start remembering — no embedding service, no external database, no data leaving your infrastructure.
Get Started Free → Join Cloud WaitlistFurther reading: Multi-Agent Memory Systems · Memory Patterns Library · API Reference
Give your AI agents persistent memory
Self-host free today — or join the Dakera Cloud waitlist for managed hosting, SLA & founder pricing.