Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 250 |
| 2026-08-01 | 250 |
| 2026-08-02 | 250 |
| 2026-08-06 | 250 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LangGraph Memory Service [](https://github.com/langchain-ai/memory-template/actions/workflows/unit-tests.yml) [](https://github.com/langchain-ai/memory-template/actions/workflows/integration-tests.yml) ## Motivation [Memory](https://langchain-ai.github.io/langgraph/concepts/memory/) lets your AI applications learn from each user interaction. It lets them become effective as they adapt to users' personal tastes and even learn from prior mistakes. This template shows you how to build and deploy a long-term memory service that you can connect to from any LangGraph agent so they can manage user-scoped memories.  ## Quickstart Create a `.env` file. ```bash cp .env.example .env ``` Set the required API keys in your `.env` file. <!-- Setup instruction auto-generated by `langgraph template lock`. DO NOT EDIT MANUALLY. --> ### Setup Model The defaults values for `model` are shown below: ```yaml model: anthropic:claude-3-5-sonnet-20240620 ``` Follow the instructions below to get set up, or pick one of the additional options. #### Anthropic To use Anthropic's chat models: 1. Sign up for an [Anthropic API key](https://console.anthropic.com/) if you haven't already. 2. Once you have your API key, add it to your `.env` file: ``` ANTHROPIC_API_KEY=your-api-key ``` #### OpenAI To use OpenAI's chat models: 1. Sign up for an [OpenAI API key](https://platform.openai.com/signup). 2. Once you have your API key, add it to your `.env` file: ``` OPENAI_API_KEY=your-api-key ``` <!-- End setup instructions --> ### Try it out [Open this template](https://langgraph-studio.vercel.app/templates/open?githubUrl=https://github.com/langchain-ai/memory-template) in LangGraph studio to get started and navigate to the `chatbot` graph. _If you want to deploy to the cloud, [follow these instructions to deploy this repository to LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/) and use Studio in your browser._  Try chatting with the bot! It will try to save memories locally (on your desktop) based on the content you tell it. For instance, if you say "Hi I'm will and I like to hike.", it will treat that content as worthy of remembering. If you pause the conversation for ~10-20 seconds, the long-term-memory graph will start. You can click the "Memories" button at the top of your studio (if you've updated your app to a recent version) to see what's been inferred. Create a _new_ thread using the `+` icon and chat with the bot again. The bot should have access to the memories you've saved, and will use them to personalize its responses. ## How it works An effective memory service should address some key questions: 1. When should memories be formed? 2. What should each memory contain? 3. How should memories be updated? The "correct" answer to these questions can be application-specific. We'll address these challenges below, and explain how this template lets you flexibly configure what and how memories are managed to keep your bot's memory on-topic and up-to-date. First, we'll talk about how you configure "what each memory should contain" using memory schemas. ### When to save memories Our memory service uses **debouncing** to store information efficiently. Instead of processing memories every time the user messages your chat bot, which could be costly and redundant, we delay updates. Here's how debouncing works in this template: 1. After each chatbot response, the graph schedules memory updates for a future time using the LangGraph SDK's `after_seconds` parameter. 2. If the chatbot receives another message within this scheduled interval, the initial update is **cancelled.** 3. A **new** memory update request is then scheduled based
Excerpt of 24,588 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:13a7acebea006a48, llm:Repository name 'langchain-ai/memory-template' suggests a template for memory components in LangChain (agent/assistant memory management). No topics or README provided.
matched fp:13a7acebea006a48, llm:Repository name 'langchain-ai/memory-template' suggests a template for memory components in LangChain (agent/assistant memory management). No topics or README provided.
matched fp:13a7acebea006a48, llm:Repository name 'langchain-ai/memory-template' suggests a template for memory components in LangChain (agent/assistant memory management). No topics or README provided.
