Skip to main content
Connectors
Agent Framework
LangGraph

LangGraph

Identity-aware Python connector for LangGraph agents: transient Context Bundle, scoped MCP tools, and idempotent top-level Thread capture without replacing checkpoints.

Start with the setup prompt or connection guide. Open the guide for detailed steps.

Agent shortcut

Ask your agent to set it up

Copy the setup prompt. Your agent will open this guide, use the recommended path, and verify the setup.

Memory For The Agent, Not The Graph Engine

LangGraph keeps owning checkpoints, interrupts, and execution. Nowledge Mem adds the state that should survive beyond one graph or deployment: Agent context, governed Memory, cross-tool recall, and searchable Threads.

Command
pip install nowledge-mem-langgraph
export NMEM_LANGGRAPH_APP_ID=customer-support

Use NowledgeMiddleware with LangChain create_agent, and load the bounded Mem tool set with await NowledgeClient().tools().

Identity That Survives Deployment Changes

  • agent_id selects the portable Mem AI Identity.
  • host_agent_id records LangGraph graph/assistant provenance.
  • space_id scopes recall and writes.
  • The API key authorizes access; identity fields never do.
  • LangGraph thread_id identifies the conversation. assistant_id does not.

Pass invocation-specific values under context.nowledge. The connector enforces the same values on every MCP request, so model-authored tool arguments cannot switch Agent or Space.

One Thread Across Subagents

Nested subgraphs share the parent LangGraph Thread and get a nested checkpoint namespace. Mem captures the completed top-level conversation once and skips nested copies. Independently addressable subagents should use their own LangGraph thread_id and Mem Agent identity.