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.
Build an email assistant with human-in-the-loop and memory
| Date | Stars |
|---|---|
| 2026-08-05 | 2054 |
| 2026-08-06 | 2054 |
| 2026-08-07 | 2056 |
| 2026-08-08 | 2056 |
| 2026-08-09 | 2056 |
| 2026-08-10 | 2059 |
| 2026-08-11 | 2061 |
| 2026-08-12 | 2062 |
| 2026-08-13 | 2062 |
| 2026-08-14 | 2061 |
| 2026-08-16 | 2062 |
| 2026-08-17 | 2064 |
| 2026-08-18 | 2101 |
| 2026-08-19 | 2116 |
| 2026-08-20 | 2123 |
| 2026-08-21 | 2125 |
| 2026-08-22 | 2133 |
| 2026-08-23 | 2145 |
| 2026-08-24 | 2147 |
| 2026-08-25 | 2149 |
| 2026-08-26 | 2155 |
| 2026-08-27 | 2157 |
| 2026-08-29 | 2161 |
| 2026-08-30 | 2160 |
| 2026-08-31 | 2161 |
| 2026-09-01 | 2165 |
| 2026-09-02 | 2166 |
| 2026-09-03 | 2168 |
| 2026-09-04 | 2179 |
| 2026-09-05 | 2180 |
| 2026-09-06 | 2181 |
| 2026-09-07 | 2181 |
| 2026-09-08 | 2193 |
| 2026-09-09 | 2206 |
| 2026-09-10 | 2212 |
| 2026-09-11 | 2213 |
| 2026-09-12 | 2216 |
| 2026-09-13 | 2217 |
| 2026-09-14 | 2220 |
| 2026-09-15 | 2221 |
| 2026-09-16 | 2225 |
| 2026-09-17 | 2228 |
| 2026-09-18 | 2229 |
| 2026-09-19 | 2231 |
| 2026-09-20 | 2290 |
| 2026-09-21 | 2306 |
| 2026-09-22 | 2310 |
| 2026-09-23 | 2311 |
| 2026-09-24 | 2315 |
| 2026-09-25 | 2317 |
| 2026-09-26 | 2318 |
| 2026-09-27 | 2319 |
| 2026-09-28 | 2324 |
| 2026-09-29 | 2324 |
| 2026-09-30 | 2325 |
| 2026-10-01 | 2326 |
| 2026-10-02 | 2338 |
| 2026-10-03 | 2346 |
| 2026-10-04 | 2348 |
| 2026-10-05 | 2358 |
| 2026-10-06 | 2365 |
| 2026-10-07 | 2362 |
| 2026-10-08 | 2372 |
| 2026-10-09 | 2375 |
| 2026-10-10 | 2378 |
| 2026-10-11 | 2380 |
| 2026-10-12 | 2383 |
| 2026-10-13 | 2384 |
| 2026-10-14 | 2389 |
| 2026-10-15 | 2390 |
| 2026-10-16 | 2392 |
| 2026-10-17 | 2397 |
| 2026-10-18 | 2399 |
| 2026-10-19 | 2402 |
| 2026-10-20 | 2404 |
| 2026-10-21 | 2406 |
| 2026-10-22 | 2412 |
| 2026-10-23 | 2413 |
| 2026-10-24 | 2415 |
| 2026-10-25 | 2416 |
| 2026-10-26 | 2418 |
| 2026-10-27 | 2418 |
| 2026-10-28 | 2418 |
| 2026-10-29 | 2421 |
| 2026-10-30 | 2423 |
| 2026-10-31 | 2430 |
| 2026-11-01 | 2431 |
| 2026-11-02 | 2432 |
| 2026-11-03 | 2434 |
| 2026-11-04 | 2435 |
Today
+1 stars today
This week
+17 stars this week
This month
+77 stars this month
Momentum
6.0
growth rate 0.70%/day
# Agents From Scratch The repo is a guide to building agents from scratch. It builds up to an ["ambient"](https://blog.langchain.dev/introducing-ambient-agents/) agent that can manage your email with connection to the Gmail API. It's grouped into 4 sections, each with a notebook and accompanying code in the `src/email_assistant` directory. These section build from the basics of agents, to agent evaluation, to human-in-the-loop, and finally to memory. These all come together in an agent that you can deploy, and the principles can be applied to other agents across a wide range of tasks.  ## Environment Setup ### Python Version * Ensure you're using Python 3.11 or later. * This version is required for optimal compatibility with LangGraph. ```shell python3 --version ``` ### API Keys * If you don't have an OpenAI API key, you can sign up [here](https://openai.com/index/openai-api/). * Sign up for LangSmith [here](https://smith.langchain.com/). * Generate a LangSmith API key. ### Set Environment Variables * Create a `.env` file in the root directory: ```shell # Copy the .env.example file to .env cp .env.example .env ``` * Edit the `.env` file with the following: ```shell LANGSMITH_API_KEY=your_langsmith_api_key LANGSMITH_TRACING=true LANGSMITH_PROJECT="interrupt-workshop" OPENAI_API_KEY=your_openai_api_key ``` * You can also set the environment variables in your terminal: ```shell export LANGSMITH_API_KEY=your_langsmith_api_key export LANGSMITH_TRACING=true export OPENAI_API_KEY=your_openai_api_key ``` ### Package Installation **Recommended: Using uv (faster and more reliable)** ```shell # Install uv if you haven't already pip install uv # Install the package with development dependencies uv sync --extra dev # Activate the virtual environment source .venv/bin/activate ``` **Alternative: Using pip** ```shell $ python3 -m venv .venv $ source .venv/bin/activate # Ensure you have a recent version of pip (required for editable installs with pyproject.toml) $ python3 -m pip install --upgrade pip # Install the package in editable mode $ pip install -e . ``` > **⚠️ IMPORTANT**: Do not skip the package installation step! This editable install is **required** for the notebooks to work correctly. The package is installed as `interrupt_workshop` with import name `email_assistant`, allowing you to import from anywhere with `from email_assistant import ...` ## Structure The repo is organized into the 4 sections, with a notebook for each and accompanying code in the `src/email_assistant` directory. ### Preface: LangGraph 101 For a brief introduction to LangGraph and some of the concepts used in this repo, see the [LangGraph 101 notebook](notebooks/langgraph_101.ipynb). This notebook explains the basics of chat models, tool calling, agents vs workflows, LangGraph nodes / edges / memory, and LangGraph Studio. ### Building an agent * Notebook: [notebooks/agent.ipynb](/notebooks/agent.ipynb) * Code: [src/email_assistant/email_assistant.py](/src/email_assistant/email_assistant.py)  This notebook shows how to build the email assistant, combining an [email triage step](https://langchain-ai.github.io/langgraph/tutorials/workflows/) with an agent that handles the email response. You can see the linked code for the full implementation in `src/email_assistant/email_assistant.py`.  ### Evaluation * Notebook: [notebooks/evaluation.ipynb](/notebooks/evaluation.ipynb)  This notebook introduces evaluation with an email dataset in [eval/email_dataset.py](/eval/email_dataset.py). It shows how to run evaluations using Pytest and the LangSmith `evaluate` API. It runs evaluation for emails responses using LLM-as-a-judge as well as evaluations for tools calls and triage decisions. 
Lance Martin
152
26
Seán
2
1
1
1
Bagatur
1
1
William FH · LangChain
1
Vadym Barda · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4813e6bdb14e5322, topic:agents
matched fp:4813e6bdb14e5322, topic:memory