Setup
Set your connection env vars — all framework integrations pick them up automatically:CrewAI
Add SenseLab tools to your CrewAI agents:LangGraph
Use SenseLab as a checkpointer for LangGraph:LangChain
Use SenseLab as chat memory for LangChain:AutoGen
Use SenseLab as a memory store for AutoGen agents:Strands Agents
Add memory to a Strands agent as a plugin:amfs_read, amfs_write, amfs_search, amfs_recall, amfs_list, and amfs_record_context — and also records the agent’s other tool calls into the causal chain, so decision traces cover the whole session rather than only the memory operations. Pass AMFSPlugin(mem, auto_trace=False) to register the tools without that tracing.
If you’d rather have one action-based tool than the full plugin, amfs_memory handles store, retrieve, search, and list, and takes its agent identity from AMFS_AGENT_ID:
Building Your Own Integration
All integrations are thin wrappers around theAgentMemory API. To build your own:
- Accept an
AgentMemoryinstance in your constructor - Map your framework’s memory/tool API to
mem.read(),mem.write(),mem.list(), etc. - Use
entity_pathto scope data (e.g., per-conversation, per-task, per-agent)
What’s next
Python SDK
The full
AgentMemory API that every integration wraps.Core Concepts
Understand versioning, provenance, and causal graphs in SenseLab.
