🧠 Convo SDK — Persistent Memory for LangGraph Agents

LLMs forget everything.
Convo remembers — so your agents don’t have to.

Convo is a drop-in LangGraph checkpointer that gives your AI agents long-term memory, workflow traceability, and easy debugging.

It works out of the box with LangGraph. One import = state persistence for multi-agent setups.

🚀 Quick Start

npm install convo-sdk

1. Initialize

import { Convo } from "convo-sdk";
const convo = new Convo({ apiKey: "your-convo-api-key" });

2. Start or Reuse a Thread

const thread_id = await convo.newThread(); // Or reuse an existing one

3. Get the Checkpointer

const checkpointer = convo.checkpointer({ thread_id });

4. Plug into LangGraph

const graph = workflow.compile({ checkpointer });
await graph.invoke(state, {
  configurable: { thread_id }
});

🧠 Restore from Checkpoint

await graph.invoke(state, {
  configurable: {
    thread_id,
    checkpoint_id: "your-checkpoint-id",
  },
});

🍳 Cookbook & Examples

📘 Click here to open the cookbook →

Join our discord if you want to chat →

💡 Why Convo?

• ✅ Plug-and-play LangGraph checkpointer
• 🧾 Logs everything — human inputs, tool calls, AI messages
• 🧵 Built-in multi-thread management
• 🧠 Supports historical checkpointing and debugging
• ☁️ PostgreSQL-backed, cloud-native
• 📊 Workflow visualization (coming soon)

📘 API Reference

| Method | Description | |--------------------------------------------|-----------------------------------------| | await convo.init({ apiKey }) | Initialize SDK | | await convo.newThread() | Create a conversation thread | | convo.checkpointer({ thread_id? }) | Get LangGraph-compatible checkpointer | | graph.invoke(state, { configurable }) | Run with checkpointing + config | | convo.getThreadState(thread_id) | Fetch full state of a thread | | convo.listThreads() | View all your conversation threads |

🧩 Thread ID Options

You can either:

• Set at checkpointer creation
  Persistent across runs:

  const checkpointer = convo.checkpointer({ thread_id });

• Or pass dynamically during graph invocation
  Per-run control:

  await graph.invoke(state, {
    configurable: { thread_id }
  });

🔐 Get Your API Key

👉 Open the Convo Dashboard

🧠 Use Cases

Convo is ideal for:

• 🔄 Stateful multi-agent LangGraph workflows
• 🤖 LLM-powered chat apps with memory
• 🧪 Research and debugging agents
• 🕵️ Agent tracing, replay, and auditing

❤️ Built for LangGraph Developers

With just one import, Convo:

• Saves all messages, tool calls, and decisions
• Makes agent memory persistent and replayable
• Eliminates boilerplate and DB config

Build smarter agents. Persist their thoughts.
Convo makes stateful AI as simple as stateless.