DAKERAIntegrations
Dakera provides official integration packages for the most popular AI/agent frameworks. Each integration wraps the Dakera REST API into framework-native components — memory backends, vector stores, and session managers.
Supported Frameworks
| Framework | Package | Language | Memory | VectorStore | Sessions | Graph |
|---|---|---|---|---|---|---|
| LangChain | langchain-dakera |
Python | ✓ | ✓ | ✓ | ✓ |
| LangChain.js | @dakera-ai/langchain |
TypeScript | ✓ | ✓ | ✓ | ✓ |
| CrewAI | crewai-dakera |
Python | ✓ | ✓ | ✓ | |
| LlamaIndex | llamaindex-dakera |
Python | ✓ | ✓ | ✓ | ✓ |
| AutoGen | autogen-dakera |
Python | ✓ | ✓ | ✓ |
Getting Started
All integrations follow the same pattern:
- Run Dakera — start the server with Docker or from source
- Install the package —
pip install <package>ornpm install <package> - Configure — set
DAKERA_API_URLandDAKERA_API_KEYenvironment variables - Use — import the framework-native class and pass it to your chain/agent
Choosing an Integration
Using Claude Desktop or Cursor? Use the Cursor MCP guide or Claude Desktop MCP guide — connect Dakera's 14 core memory tools directly to your IDE without writing any code.
Building a conversational chain? Use LangChain or LangChain.js — they provide both BaseMemory and VectorStore implementations.
Multi-agent orchestration? Use CrewAI or AutoGen — they provide per-agent memory isolation with cross-agent recall.
RAG pipeline? Use LlamaIndex — the DakeraIndexStore integrates directly with LlamaIndex's ingestion pipeline.
LLM governance (cost tracking, policy decisions)? Use TealTiger — DakeraCostStorage and DakeraDecisionStore for decay-weighted governance state.
Common Configuration
All integrations accept these environment variables:
| Variable | Description | Default |
|---|---|---|
DAKERA_API_URL | Dakera server URL | http://localhost:3300 |
DAKERA_API_KEY | API key for authentication | (none) |
All Integrations
- Cursor (MCP) — 14 core memory tools for Cursor IDE via MCP protocol
- Claude Desktop (MCP) — persistent memory for Claude Desktop via MCP
- LangChain (Python) — DakeraMemory + DakeraVectorStore
- LangChain.js (TypeScript) — DakeraMemory + DakeraVectorStore
- CrewAI — DakeraStorage for persistent crew memory
- LlamaIndex — DakeraMemoryStore + DakeraIndexStore
- AutoGen — DakeraMemory for multi-agent conversations
- TealTiger (Governance) — DakeraCostStorage and DakeraDecisionStore
Pick your stack and start
Every integration runs against the same self-hosted Dakera binary — one deployment, every framework. Start with the Quickstart to get the server running, then drop in whichever integration fits your stack.