langchain-ai/agents-from-scratch-ts
LangGraph Typescript Agents Notebooks: email, human in the loop, memory
This project helps software developers build AI assistants that can automatically triage and respond to emails. It shows how to construct an agent that takes incoming email content, processes it, and then drafts replies or performs other actions. Developers, particularly those working with TypeScript and large language models, would use this to implement email automation.
No commits in the last 6 months.
Use this if you are a developer looking to build intelligent email agents that can understand, classify, and respond to emails, potentially with human oversight.
Not ideal if you are an end-user simply looking for an out-of-the-box email assistant; this project is a developer toolkit, not a ready-to-use application.
Stars
30
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
May 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/langchain-ai/agents-from-scratch-ts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langchain-ai/deepagents
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with...
kyopark2014/langgraph-agent
It shows case studies of the LangGraph agent.
ArcadeAI/SlackAgent
An assistant for Slack built with Arcade and Langgraph. Interact with Google Calendar, Mail,...
codingforentrepreneurs/django-ai-agent
Learn how to create an AI Agent with Django, LangGraph, and Permit.
assada/agent_template
FastAPI-based boilerplate for building LangGraph-powered agents with streaming, observability,...