hindsight-langgraph

LangGraph and LangChain integration for Hindsight — persistent long-term memory for AI agents.

Provides three integration patterns:

• Tools — retain/recall/reflect as LangChain @tool functions for agent-driven memory. Works with both LangChain and LangGraph.
• Nodes (LangGraph) — pre-built graph nodes for automatic memory injection and storage
• Memory Instructions — pre-fetch memories into a system prompt string. Works with any LangChain model, no graph needed.

Prerequisites

• A Hindsight Cloud account or a self-hosted Hindsight instance
• Python 3.10+

Installation

pip install hindsight-langgraph

Quick Start: Tools

Bind Hindsight memory tools to your LangGraph agent so it can store and retrieve memories on demand.

from hindsight_langgraph import create_hindsight_tools
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

# Set HINDSIGHT_API_KEY env var to authenticate
tools = create_hindsight_tools(bank_id="user-123")

agent = create_react_agent(
    ChatOpenAI(model="gpt-4o"),
    tools=tools,
)

result = await agent.ainvoke(
    {"messages": [{"role": "user", "content": "Remember that I prefer dark mode"}]}
)

Dynamic Bank IDs with Tools

If you build the agent once and serve multiple users, omit the static bank_id and resolve it per request from config["configurable"]:

tools = create_hindsight_tools(bank_id_from_config="user_id")
agent = create_react_agent(ChatOpenAI(model="gpt-4o"), tools=tools)

result = await agent.ainvoke(
    {"messages": [{"role": "user", "content": "Remember that I prefer dark mode"}]},
    config={"configurable": {"user_id": "user-456"}},
)

Passing bank_id="user-123" still pins all tool calls to that bank and takes precedence over bank_id_from_config.

Quick Start: Memory Nodes

Add recall and retain nodes to your graph for automatic memory injection before LLM calls and storage after responses.

from hindsight_langgraph import create_recall_node, create_retain_node
from langgraph.graph import StateGraph, MessagesState, START, END

recall = create_recall_node(bank_id="user-123")
retain = create_retain_node(bank_id="user-123")

builder = StateGraph(MessagesState)
builder.add_node("recall", recall)
builder.add_node("agent", agent_node)  # your LLM node
builder.add_node("retain", retain)

builder.add_edge(START, "recall")
builder.add_edge("recall", "agent")
builder.add_edge("agent", "retain")
builder.add_edge("retain", END)

graph = builder.compile()

Dynamic Bank IDs

Use bank_id_from_config to resolve the bank per-request from the graph's config:

recall = create_recall_node(bank_id_from_config="user_id")
retain = create_retain_node(bank_id_from_config="user_id")

# Bank ID resolved at runtime
result = await graph.ainvoke(
    {"messages": [{"role": "user", "content": "hello"}]},
    config={"configurable": {"user_id": "user-456"}},
)

Quick Start: Memory Instructions

Pre-fetch memories and inject them into a system prompt. Works with any LangChain model — no graph needed.

from hindsight_langgraph import memory_instructions
from langchain_openai import ChatOpenAI

get_instructions = memory_instructions(
    bank_id="user-123",
    base_instructions="You are a helpful assistant.",
)

# Each call re-fetches memories, so it stays up to date
instructions = await get_instructions()
response = await ChatOpenAI(model="gpt-4o").ainvoke([
    {"role": "system", "content": instructions},
    {"role": "user", "content": "What do you know about me?"},
])

Configuration

Global config

from hindsight_langgraph import configure

configure(
    api_key="your-api-key",  # or set HINDSIGHT_API_KEY env var
    budget="mid",
    tags=["source:langgraph"],
)

Self-hosted instance

To connect to a self-hosted Hindsight instance instead of Hindsight Cloud:

configure(
    hindsight_api_url="http://localhost:8888",
)

Or pass hindsight_api_url directly to any factory function:

tools = create_hindsight_tools(bank_id="user-123", hindsight_api_url="http://localhost:8888")

Per-call overrides

All factory functions accept client, hindsight_api_url, and api_key to override the global config.

Requirements

• Python 3.10+
• langchain-core >= 0.3.0
• hindsight-client >= 0.4.0
• langgraph >= 0.3.0 (only for nodes pattern — install with pip install hindsight-langgraph[langgraph])

Documentation

• Integration docs
• Cookbook: ReAct agent with memory
• Hindsight API docs