AutoGen integration

autogen-dakera (0.3.0) gives AutoGen agents persistent semantic memory on a Dakera server. DakeraMemory adds and queries one agent's memories, which survive restarts, so agents keep long-term context across conversations. This page is for Python developers building AutoGen agents.

Quick start

pip install autogen-dakera

Requires Python ≥ 3.10, dakera>=0.13.1 (installed automatically) and a running Dakera server. Works with Dakera server v0.12.0 and v0.11.108.

from autogen_dakera import DakeraMemory

memory = DakeraMemory(
    api_url="http://localhost:3000",
    api_key="dk-mykey",
    agent_id="autogen-assistant",
)

memory.add("User is building a chatbot for customer support.")
results = memory.query("what is the user building?")

Features

DakeraMemory — persistent semantic memory with importance scoring
DakeraSessionManager — session lifecycle for conversation tracking
DakeraKnowledgeGraph — entity-relationship graph operations
DakeraEntityExtractor — automatic entity extraction
DakeraNamespaceManager — multi-tenant namespace isolation

Examples

Basic agent memory

import os
from autogen_dakera import DakeraMemory

memory = DakeraMemory(
    api_url=os.environ.get("DAKERA_API_URL", "http://localhost:3000"),
    api_key=os.environ.get("DAKERA_API_KEY", ""),
    agent_id="autogen-assistant",
    recall_k=3,
    importance=0.8,
)

memory.add("User is building a chatbot for customer support.")
memory.add("The chatbot should handle returns, refunds, and order tracking.")
memory.add("Preferred tech stack: Python backend, React frontend.")

results = memory.query("what is the user building?")
for r in results:
    print(f"  [{r['score']:.3f}] {r['content']}")

Conversation history across sessions

from autogen_dakera import DakeraMemory

memory = DakeraMemory(
    api_url="http://localhost:3000",
    api_key="dk-mykey",
    agent_id="autogen-chat",
    recall_k=5,
    importance=0.7,
)

# Store conversation turns
memory.add("Human: What's the capital of France?\nAI: Paris.")
memory.add("Human: I'm planning to visit.\nAI: Great! Paris has amazing museums.")

# Later session — recall relevant context
results = memory.query("travel plans")
for r in results:
    print(f"  [{r['score']:.3f}] {r['content']}")

API reference

DakeraMemory options

Parameter	Type	Default	Description
`api_url`	str	—	Dakera server URL
`api_key`	str	`""`	API key
`agent_id`	str	—	Agent identifier
`recall_k`	int	`5`	Results per query
`min_importance`	float	`0.0`	Minimum importance of returned memories
`importance`	float	`0.7`	Default importance for stored memories

Configuration

The package does not read environment variables. To keep the URL and key out of source code, read them yourself:

import os
from autogen_dakera import DakeraMemory

memory = DakeraMemory(
    api_url=os.environ["DAKERA_API_URL"],
    api_key=os.environ.get("DAKERA_API_KEY", ""),
    agent_id="autogen-assistant",
)