Harrison Chase

hwchase17 starred langchain-ai/langgraph-gen-py: CLI to generate LangGraph stubs from a specification

CLI to generate LangGraph stubs from a specification. Stars: 108

hwchase17 pushed to hwchase17/harbor: code update

code update

hwchase17 pushed to hwchase17/harbor: code update

code update

hwchase17 pushed to hwchase17/harbor: code update

code update

hwchase17 starred beam-cloud/beta9: Ultrafast serverless GPU inference, sandboxes, and background jobs

Ultrafast serverless GPU inference, sandboxes, and background jobs. Stars: 1650

hwchase17 starred vonzosten/awesome-LangGraph: An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.

An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.. Stars: 1789

hwchase17 starred zamalali/DeepGit: Deep research agent to help you find the best GitHub repositories 🕵️!

Deep research agent to help you find the best GitHub repositories 🕵️!. Stars: 870

@BraceSproul I don’t think we support grok right?

we need more benchmarks! awesome work by harvey here, and excited to work with them

this deepagents deploy https://docs.langchain.com/oss/python/deepagents/deploy (or at least directionally where we want to take it) what's missing? give us feedback!

we want this to be deepagents deploy: https://docs.langchain.com/oss/python/deepagents/deploy whats missing? would love feedback!

please do, would love feedback!

say more? like you want to use langsmith key to access all models

Talked to @ramplabs Head of Applied Research Alex Shevchenko on the Max Agency podcast to learn how @Ramp Sheets was built, their internal agent Inspect, and so much more. YouTube: https://www.youtube.com/watch?v=trEM9OKr5Sc Apple: https://podcasts.apple.com/us/podcast/how-ramp-built-an-ai-agent-that-can-think-outside…

my posture is terrible but Alex's insights are great, so it evens out

Glad to hear!

ai coding is getting expensive use more open models!

hwchase17 starred aws-samples/langgraph-agents-with-amazon-bedrock:

langgraph-agents-with-amazon-bedrock. Stars: 187

hwchase17 pushed to langchain-ai/deepagents: code update

code update

hwchase17 pushed to langchain-ai/deepagents: code update

code update

hwchase17 starred souzatharsis/podcastfy: An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI. Stars: 6255

big theme of 2026 - cost of closed models is too high! really excited to make deepagents work exceptionally well with OSS models

.@MadrigalPharma is living in the (agentic) future. If you haven't heard of Madrigal, they are a pioneering biopharma company. Some months ago, they set out to solve the problem of integrating, searching, and synthesizing information from diverse datasets at scale. This lead to the creation of an enterprise multi-ag…

🚀DeepAgents deploy is a simple, configuration driven way to get an agent harness deployed to the cloud deepagents.toml is the file that configures it. It has four sections: - agent - sandbox - auth -frontend Here's what each one does 🧵

[agent] This is where you specify the name of the agent - this is the deployment name in LangSmith This is also where you specify the model name. We support a lot of models! Not only ones from OpenAI, Anthropic, Google, but also @OpenRouter @FireworksAI_HQ @baseten @nvidia and others Docs:

[sandbox] DeepAgents can connect to a sandbox to run! We integrate with @modal @daytonaio @RunloopDev Each provider has its own set of parameters, so be sure to check that! Docs: https://docs.langchain.com/oss/python/deepagents/deploy#sandbox

[auth] Part of deploying agents to production is deploying them in a multi-tenant way Auth is the way to do that! We support integrations with @clerk and @supabase

[frontend] UI/UX is a surprisingly big part of building agents! It takes a while to hook up streaming, thread history, all the endpoints We do it for you! Get a frontend you can expose to users out of the box

Checkout DeepAgents deploy here: https://docs.langchain.com/oss/python/deepagents/deploy We're shipping updates every week (almost every day). What would you like to see next?

good idea! i think you need a benchmark specific to the use case though, right?

one future trend i'm very excited by: models getting good enough where they can power agents that browse the web deepagents + @browserbase is a glimpse of that future See the full example here: https://github.com/browserbase/integrations/tree/main/examples/integrations/langchain/deepagents-browserbase

hwchase17 pushed to langchain-ai/deepagents: code update

code update

hwchase17 pushed to langchain-ai/deepagents: code update

code update

hwchase17 starred tavily-ai/tavily-python: The Tavily Python SDK allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python programs. Easily integrate smart search, content extraction, and research capabilities into your applications, harnessing Tavily's powerful features.

The Tavily Python SDK allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python programs. Easily integrate smart search, content extraction, and research capabilities into your applications, harnessing Tavily's powerful features.. Stars: 1187

Harrison Chase's X Feed Proposed for Hourly Polling in User Monitoring

A user note designates Harrison Chase's X feed as the subject of an hourly polling mechanism. The phrase "Why not?" endorses or questions the absence of such polling. This suggests real-time monitoring of Chase's posts for intelligence or updates.

Harrison Chase's X Feed Becomes Hourly Community Poll for LangChain Engagement

Harrison Chase is running an hourly poll on his X feed focused on his own posts, inviting users to participate. This serves as a community engagement tactic. It directs traffic to LangChain's careers page for recruitment.

ListenLabs' Agent Architecture Features Self-Reviewing Subagents and Sandboxed Executions

ListenLabs employs self-reviewing feedback subagents, sandboxed environments, and purpose-built abstractions in their AI agent architecture. Their system supports large-scale response analysis. Discussion highlights key decisions enabling scalable agent performance.

Harrison Chase Acknowledges Jacob's Contribution to Hourly X Feed Poll

Harrison Chase publicly thanks Jacob in response to an hourly poll tracking his X feed activity. The content indicates ongoing monitoring of Chase's posts on an hourly basis. This reflects community engagement around his updates.

Harrison Chase's X Feed Scheduled for Hourly Polling in Intelligence Feed

A user note designates Harrison Chase's X feed (@hwchase17) for hourly polling to capture timely updates. The instruction requests tagging upon release of the compiled feed output. This setup enables automated, frequent monitoring of Chase's posts for editorial intelligence.

DeepAgents: Comprehensive Framework for Building Agents with Full Customization Hooks

DeepAgents is positioned as an all-in-one solution for agent development, providing batteries-included convenience alongside extensive hooks for customization. It enables developers to adjust components precisely to their needs without starting from scratch. The framework is highlighted in Harrison Chase's feed as a key advancement in deep agent technology.

LangChain Offers Skills Configuration Analogous to Anthropic's Claude-API Skill

Harrison Chase confirms the existence of a LangChain skills repository mirroring Anthropic's skills structure, specifically at langchain-ai/langchain-skills/config/skills. This addresses a query for DeepAgents skills similar to the claude-api skill. The repository enables building apps with LangChain/DeepAgents more effectively via pre-configured skills.

LangChain Skills Configurations Now Hosted in Dedicated GitHub Repository

Harrison Chase confirmed the availability of LangChain skills configurations in a dedicated GitHub repository. The repo at langchain-ai/langchain-skills contains a config/skills directory for these resources. This enables developers to access and contribute to standardized skill definitions for LangChain applications.

Harrison Chase Anticipates High Engagement on His X Feed During LangChain Event

Harrison Chase predicts significant activity on his X feed coinciding with Tadeo Donegan's San Francisco visit for the LangChain Interrupt event (May 9-16). The comment "everyones gonna be here!" in an hourly poll context suggests expectation of community influx. This aligns with Donegan's open invitation for AI, agents, and production discussions.

yup

(honestly asking) any documentation on those formats or how to use them outside of codex? would love to an open standard for memory - let me know if any interest in collaborating!

need open standards

i think memory is most immediately valuable when you are doing the same thing repeatedly. i use chatgpt for random stuff, it doesnt matter that much if it remembers things about me

agree this would be great

if there is an open standard for memory (like agents.md or skills) then that would be great and would alleviate a lot of my concerns unless you store memories in skills rn (which is reasonable actually, but not what they are doing), i dont think any standard exists?

langsmith