Julia Schottenstein

1.2K posts

Julia Schottenstein banner
Julia Schottenstein

Julia Schottenstein

@j_schottenstein

Building @LangChain | ex-product @getdbt | angel investor 👼 | @Stanford CS engineer | NYC native + SF transplant | runner (sometimes) | https://t.co/QuVTU4Gmjm

Katılım Ekim 2016
809 Takip Edilen3.3K Takipçiler
Julia Schottenstein retweetledi
sitin
sitin@sitinme·
LangChain 官方开源了 Deep Agents，一句话定位：「batteries-included agent harness」——不用自己拼 prompt、拼工具、拼上下文管理，装完就是一个能用的 Agent。 开箱自带 5 大能力： • 📋 规划——write_todos 自动拆解任务、追踪进度 • 📁 文件系统——read/write/edit/ls/glob/grep 全套 • 💻 Shell——沙箱内执行命令 • 🤖 子 Agent——task 工具做任务委派，上下文隔离 • 🧠 上下文管理——对话太长自动摘要，大输出自动存文件 两行代码启动： from deepagents import create_deep_agent agent = create_deep_agent() 还有独立 CLI，支持 Web 搜索、远程沙箱、持久记忆、人工审批。 灵感来源？README 直接写了：「primarily inspired by Claude Code」。本质上是 LangChain 版的 Claude Code 开源复刻，还基于 LangGraph 做了流式输出、状态持久化、检查点。 MIT 协议，模型不绑定，OpenAI/Anthropic/开源模型随便换。 🔗 github.com/langchain-ai/d…
sitin tweet mediasitin tweet media
中文
7
49
223
17K
Julia Schottenstein retweetledi
◢
◢@joemccann·
If you want to understand why open source agent harnesses are going to win, read this post. Sure, @AnthropicAI is going for the walled garden @Apple approach to force users to use “their” harness, but in order to win, they’ll need to entrench enterprises with Claude Code whilst making CC more “secure”, make switching costs too expensive, from career risk to engineering leadership to literal dollars.
Can Bölük@_can1357

x.com/i/article/2021…

English
18
20
312
76.7K
Julia Schottenstein retweetledi
Suryansh Tiwari
Suryansh Tiwari@Suryanshti777·
Holy shit...Someone just open-sourced a batteries-included AI agent that does what took me weeks to build — in literally 3 lines of code. Meet Deep Agents 🦕 Most “AI agent” libs throw you into DIY hell: wiring tools, prompts, memory, context… everything. This doesn’t. Out of the box you get: → Planning + task breakdown → File read/write/edit → Sandboxed shell access → Sub-agents with isolated context → Auto summarization And the quickstart is kinda ridiculous: pip install deepagents agent = create_deep_agent() agent.invoke({"messages": [...]}) That’s it. Your agent can now: plan → execute → read files → run commands → manage its own context. The CLI is where it gets serious: → Web search → Remote sandboxes → Persistent memory → Human-in-the-loop approvals This feels way closer to a real “AI coworker” than a demo. Under the hood: → Built on LangGraph → Streaming + persistence + checkpoints → Provider-agnostic (use any tool-calling model) And the best part? They straight up say: “This was inspired by Claude Code.” No fluff. Just: “we studied it and built our version.” MIT licensed. This is one of those repos that quietly shifts the baseline. Link in comments👇
Suryansh Tiwari tweet media
English
15
19
110
10.7K
Julia Schottenstein retweetledi
LangChain
LangChain@LangChain·
LangSmith for Startups Spotlight: @ListenLabs Listen is an autonomous research agent that conducts thousands of customer interviews simultaneously. Teams bring a business question, and Listen runs the entire research process: designing studies, recruiting participants, moderating conversations with intelligent follow-ups, and delivering structured insights overnight. Listen is trusted by Google, Microsoft, Perplexity, Robinhood, Replit and hundreds of other enterprises to power their customer research. Listen uses LangSmith as core infrastructure for production tracing and observability. Their team relies on it to monitor the LLM calls that power their interviewing, analysis, and report generation agents. Join the team if you want to build the future of customer understanding! 👉 listenlabs.ai/careers
English
8
12
57
8K
Julia Schottenstein retweetledi
Derek Gilbert
Derek Gilbert@derek_gilbert·
I cannot explain how good agent fleets are going to be. This seems like an industry changing product. nothing Ive used has even come close. It feels like both large CRMs really tried to do this initially but it failed. Langchain nailed it. Ive only played with it for a few hours but I cant stop. Feels like if you want a personal hobby agent you go with openClaw, if you want an agent to help you at work its claude, but if you want a fleet of agents for your entire workforce? well there is only one place ive seen that vision accomplished and its now langchain. congrats guys. @LangChain @hwchase17
English
5
6
29
7.7K
Julia Schottenstein retweetledi
Kevin Simback 🍷
Kevin Simback 🍷@KSimback·
LangChain is one of the pioneers of AI agents and agentic orchestration Now they’ve released Deep Agents - an open source alternative to Claude Code that’s model agnostic 🤯
Hasan Toor@hasantoxr

LangChain just open-sourced a replica of Claude Code. It’s an MIT-licensed framework that recreates the core workflow behind coding agents like Claude Code but in an open system developers can inspect and modify. It is called Deep Agents. I spent a bit of time looking through the repo and it’s actually a pretty helpful reference if you’re trying to understand how these coding agents are structured. Here's what's inside: → Planning tools for breaking down tasks → File system access for reading, writing, and editing code → Shell command execution with sandboxing → Sub-agents for handling complex work in parallel → Auto-summarization when context gets too long Another useful aspect is that it’s model-agnostic, so you can plug in different LLMs and experiment with building your own coding agents on top of the same structure. If you’re exploring agent frameworks or just curious how tools like Claude Code work under the hood, this is a pretty good repo to bookmark. Link in the comments.

English
7
14
97
21.3K
Julia Schottenstein retweetledi
LangChain
LangChain@LangChain·
🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: smith.langchain.com/agents?skipOnb… Learn more: blog.langchain.com/new-in-agent-b…
English
104
265
3.1K
24.9M
Julia Schottenstein
Julia Schottenstein@j_schottenstein·
ngl Fleet is very very good. makes me feel like i have superpowers
LangChain@LangChain

Introducing LangSmith Fleet. Agents for every team. → Build agents with natural language → Share and control who can edit, run, or clone each agent → Manage authentication with agent identity → Approve actions with human-in-the-loop → Track and audit actions with tracing in LangSmith Observability Try Fleet: smith.langchain.com/agents?skipOnb…

English
0
2
9
2.5K
Julia Schottenstein retweetledi
LangChain
LangChain@LangChain·
Introducing LangSmith Fleet: an enterprise workspace for creating, using, and managing your fleet of agents. Fleet agents have their own memory, access to a collection of tools and skills, and can be exposed through the communication channels your team uses every day. Fleet includes: → Agent identity and credential management with “Claws” and “Assistants” → Sharing and permissions to control who can run, clone, and edit (just like Google Docs) → Custom Slack bots so each agent has its own identity in Slack Try Fleet: smith.langchain.com/agents?skipOnb… Read the announcement: blog.langchain.com/introducing-la…
English
16
43
206
139.5K
Charlie Marsh
Charlie Marsh@charliermarsh·
We've entered into an agreement to join OpenAI as part of the Codex team. I'm incredibly proud of the work we've done so far, incredibly grateful to everyone that's supported us, and incredibly excited to keep building tools that make programming feel different.
English
285
146
3.1K
465.5K
Julia Schottenstein retweetledi
LangChain
LangChain@LangChain·
Polly is our AI assistant built directly into LangSmith to help you debug, analyze, and improve your agents — now generally available. Now, Polly lives on every page of LangSmith, remembers your full session as you navigate, and can take action to update prompts, compare experiments, write evaluators, and more. Read the blog: blog.langchain.com/polly-langsmit… See the docs: docs.langchain.com/langsmith/polly Try Polly in LangSmith: smith.langchain.com
English
10
16
70
12.1K
Julia Schottenstein retweetledi
LangChain
LangChain@LangChain·
We're at GTC all week! Come say hello to the LangChain team at the NVIDIA booth 👋 Today at 12:30 PM at GTC, Harrison will join the panel “Open Models: Where We Are and Where We’re Headed,” alongside Jensen and the CEOs of Cursor, Thinking Machines Lab, Perplexity, and others. Add it to your schedule ➡️ nvidia.com/gtc/session-ca…
LangChain tweet media
English
0
5
35
3.9K

Keşfet

@AnthropicAI @Apple @ListenLabs @LangChain @hwchase17 @charliermarsh @rajko_rad @jakebroekhuizen