260317 X(트위터) 모음
RT by @hwchase17: We’re going live at #NVIDIAGTC in 30 minutes. ⏱️
Join us for
RT by @hwchase17: We’re going live at #NVIDIAGTC in 30 minutes. ⏱️
Join us for
We’re going live at #NVIDIAGTC in 30 minutes. ⏱️
Join us for GTC Live at 8 a.m. PT as we get ready for Jensen Huang's keynote 11 a.m.
Featuring industry leaders from: @bfl_ml, @Cadence, @CaterpillarInc, @cohere, @CoreWeave, @DellTech, @EdisonSci, @FireworksAI_HQ, @IBM, @LangChain, @MistralAI, @MorganStanley, OpenClaw, @EvidenceOpen, @PalantirTech, @perplexity_ai, PhysicsX, @PrimeIntellect, @SkildAI, @Waabi_ai
🔗 nvda.ws/4lx8m0w
출처: https://nitter.net/nvidia/status/2033551362210865371#m
RT by @hwchase17: LangChain just open-sourced a replica of Claude Code.
It’s an
RT by @hwchase17: LangChain just open-sourced a replica of Claude Code.
It’s an
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.
출처: https://nitter.net/hasantoxr/status/2033213054859792859#m
RT by @hwchase17: DeepAgents SDK is fantastic. I use it to build almost all my a
RT by @hwchase17: DeepAgents SDK is fantastic. I use it to build almost all my a
DeepAgents SDK is fantastic. I use it to build almost all my agentic software at this point.
It seems to find a great balance between ‘batteries included’ and ‘choose your own adventure’
The team also puts a lot of work into the docs, which obviously are consumable by your agent.
I have never met @Vtrivedy10 and have no affiliation with LangChain / DeepAgents, other than being a highly thankful user who appreciates all this awesome stuff we can now build with.
I need to put together some tutorials / guides here but it’s been hard because I have been having way too much fun building things
Viv (@Vtrivedy10)
the deepagents library is basically our starting point for doing harness engineering and shipping agents
the internal agents used at the company are built on it (background coding, GTM/SDR, research)
there’s primitives we find really useful across our evals and dogfooding like filesystems, multi-model, context management like compaction and large tool call offloading
the goal is to give builders a good starting harness and the tools to customize and extend it to any task they want
we have a lot of fun watching the open source community and customers ship with deepagents and also build evals that actually measure and improve their agents over time
reach out if you’re building agents, doing harness engineering, exploring the space - we wanna help!
출처: https://nitter.net/mstockton/status/2033626754229686679#m
RT by @hwchase17: You can now build your own version of Claude Code.
Deep Agent
RT by @hwchase17: You can now build your own version of Claude Code.
Deep Agent
You can now build your own version of Claude Code.
Deep Agents is a MIT-licensed framework that recreates the core workflow behind top coding agents.
It lets you inspect and modify the exact architecture that makes these agents work.
- Planning and todo tools for managing tasks.
- File system reading, editing, and shell commands.
- Sub-agents for delegating complex, multi-step tasks.
- 100% model-agnostic so you can plug in any LLM.
100% open source.
출처: https://nitter.net/simplifyinAI/status/2033581939756818648#m
RT by @hwchase17: A lot of work goes into making @LangChain_JS the easiest to re
RT by @hwchase17: A lot of work goes into making @LangChain_JS the easiest to re
A lot of work goes into making @LangChain_JS the easiest to render your agent to the frontend in ANY framework. Next up:
- document and improve streaming protocol: the next version will be a whole lot more efficient
- expose sandbox activities across subagents
- frontend tools
🚀
LangChain JS (@LangChain_JS)
We just shipped new docs showing how to wire @langchain/react's #useStream hook to any React UI library 🎉
Two ready-to-go integrations:
🧩 AI Elements: composable, @shadcn - ui-style components for chat
🤖 @assistantui: headless runtime with a full thread UI out of the box
📚 docs.langchain.com/oss/pytho…
출처: https://nitter.net/bromann/status/2033617426546589866#m
RT by @hwchase17: the deepagents library is basically our starting point for doi
RT by @hwchase17: the deepagents library is basically our starting point for doi
the deepagents library is basically our starting point for doing harness engineering and shipping agents
the internal agents used at the company are built on it (background coding, GTM/SDR, research)
there’s primitives we find really useful across our evals and dogfooding like filesystems, multi-model, context management like compaction and large tool call offloading
the goal is to give builders a good starting harness and the tools to customize and extend it to any task they want
we have a lot of fun watching the open source community and customers ship with deepagents and also build evals that actually measure and improve their agents over time
reach out if you’re building agents, doing harness engineering, exploring the space - we wanna help!
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.
출처: https://nitter.net/Vtrivedy10/status/2033608199564067098#m
RT by @hwchase17: We just shipped new docs showing how to wire @langchain/react'
RT by @hwchase17: We just shipped new docs showing how to wire @langchain/react'
We just shipped new docs showing how to wire @langchain/react's #useStream hook to any React UI library 🎉
Two ready-to-go integrations:
🧩 AI Elements: composable, @shadcn - ui-style components for chat
🤖 @assistantui: headless runtime with a full thread UI out of the box
📚 docs.langchain.com/oss/pytho…
출처: https://nitter.net/LangChain_JS/status/2033611656383893855#m
RT by @hwchase17: it’s our go to for harness engineering and building agents we
RT by @hwchase17: it’s our go to for harness engineering and building agents we
it’s our go to for harness engineering and building agents we actually use internally
hooks up to our evals + tracing in LangSmith so we use deepagents to build deepagents and also deepagents to autonomously improve itself
fun stuff
출처: https://nitter.net/Vtrivedy10/status/2033609759237046672#m
RT by @hwchase17: LangChain just open-sourced Deep Agents—an agent harness that’
RT by @hwchase17: LangChain just open-sourced Deep Agents—an agent harness that’
LangChain just open-sourced Deep Agents—an agent harness that’s opinionated and ready-to-run out of the box.
Instead of wiring up prompts, tools, and context management yourself, you get a working agent immediately and customize what you need. It’s an MIT-licensed system that’s perfect for anyone trying to understand how high-end coding agents are structured. @LangChain
What’s inside the harness:
- Planning: write_todos for task breakdown and progress tracking.
- Filesystem: Full context control via read_file, write_file, edit_file, ls, glob, and grep.
- Shell Access: execute for running commands (with sandboxing).
- Sub-agents: task tool for delegating work with isolated context windows.
- Smart Defaults: Optimized prompts that teach the model how to use these tools effectively.
- Context Management: Auto-summarization for long threads and large outputs saved directly to files.
Link in the comments
출처: https://nitter.net/itsafiz/status/2033591253955449289#m
RT by @hwchase17: We just shipped an update to openevals, our open-source librar
RT by @hwchase17: We just shipped an update to openevals, our open-source librar
We just shipped an update to openevals, our open-source library for evaluating LLM applications.
🖼️ Multimodal support: pass images, audio, and PDFs directly to any LLM-as-judge evaluator via the attachments parameter.
📋 20+ new prebuilt prompts: quality, safety, security, image, voice (beta), and more
Check it out: github.com/langchain-ai/open…
출처: http://github.com/langchain-ai/openevals
Easiest way to deploy agents
Easiest way to deploy agents
Easiest way to deploy agents
LangChain (@LangChain)
Deploy LangGraph agents using the LangGraph CLI
You can now deploy LangGraph agents to production straight from your terminal using the LangGraph CLI!
🛠️ langgraph new → scaffold from a template
🧪 langgraph dev → test locally in Studio
🚀 langgraph deploy → deploy your agent on LangSmith
📋 langgraph deploy logs/list/delete → manage everything after directly from your terminal
Blog: blog.langchain.com/introduci…
Watch the full walkthrough: piped.video/hcWHufkzicc
출처: https://nitter.net/hwchase17/status/2033601880618942672#m
RT by @hwchase17: Deploy LangGraph agents using the LangGraph CLI
You can now d
RT by @hwchase17: Deploy LangGraph agents using the LangGraph CLI
You can now d
Deploy LangGraph agents using the LangGraph CLI
You can now deploy LangGraph agents to production straight from your terminal using the LangGraph CLI!
🛠️ langgraph new → scaffold from a template
🧪 langgraph dev → test locally in Studio
🚀 langgraph deploy → deploy your agent on LangSmith
📋 langgraph deploy logs/list/delete → manage everything after directly from your terminal
Blog: blog.langchain.com/introduci…
Watch the full walkthrough: piped.video/hcWHufkzicc
출처: https://nitter.net/LangChain/status/2033596690171629582#m
RT by @hwchase17: today, we’re introducing @nozomioai + @LangChain integration.
RT by @hwchase17: today, we’re introducing @nozomioai + @LangChain integration.
today, we’re introducing @nozomioai + @LangChain integration.
20+ tools that give any langchain agent reliable context from docs, codebases, research papers, datasets, and other data sources.
python and typescript. available now.
출처: https://nitter.net/arlanr/status/2033689690990362901#m
RT by @hwchase17: LangChain Announces Enterprise Agentic AI Platform Built with
RT by @hwchase17: LangChain Announces Enterprise Agentic AI Platform Built with
LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA
We've partnered with NVIDIA to give enterprise teams a complete, integrated stack for building and running agents in production.
LangGraph and Deep Agents plug directly into NVIDIA's tooling. Build agents with the latest Nemotron 3 models deployed with NIM microservices, apply NeMo Guardrails for securing agentic applications, leverage NeMo Agent Toolkit to optimize your agents and monitor with LangSmith Observability.
The LangSmith agent engineering platform and NeMo Agent Toolkit together provide comprehensive evaluation across the full agent lifecycle.
We're also joining the NVIDIA Nemotron Coalition to help shape the open models that power these agents.
출처: https://nitter.net/LangChain/status/2033658575709462574#m
RT by @jerryjliu0: Agentic AI transforms document extraction from simple text tr
RT by @jerryjliu0: Agentic AI transforms document extraction from simple text tr
Agentic AI transforms document extraction from simple text transcription into intelligent reasoning, dramatically reducing manual review queues and maintenance overhead.
Traditional OCR hits a wall when documents deviate from templates - vendor format changes, skewed scans, or handwritten annotations break the pipeline. Agentic document extraction solves this by understanding context, not just converting pixels to text.
🧠 Plan-act-verify loops that identify document structure before extracting data, then validate results against context
📍 Visual grounding with bounding boxes links extracted text to precise page locations, solving spatial assignment errors
📋 Dynamic table processing infers header-row relationships instead of relying on brittle pixel coordinate templates
LlamaParse processes any document type without training phases or template maintenance. When your vendor changes invoice formats or you encounter new document types, the system adapts automatically instead of breaking.
Read the full breakdown of agentic AI and implementation best practices: llamaindex.ai/blog/agentic-d…
출처: https://nitter.net/llama_index/status/2033575287909417283#m
RT by @hwchase17: 早起读了 LangChain 工程师这篇讨论 Agent Harness 的文章，之前一些碎片性的概念被串起来了，也能更好理
RT by @hwchase17: 早起读了 LangChain 工程师这篇讨论 Agent Harness 的文章，之前一些碎片性的概念被串起来了，也能更好理
早起读了 LangChain 工程师这篇讨论 Agent Harness 的文章，之前一些碎片性的概念被串起来了，也能更好理解类似 Claude Code 这些工具为什么这样设计。推荐阅读。
Viv (@Vtrivedy10)
출처: https://nitter.net/chaosflutt28952/status/2033691577600905464#m
Great use case for langsmith-cli!
Great use case for langsmith-cli!
Great use case for langsmith-cli!
Ralph👨🏻💻 (@ralphesber)
Just published my first OpenClaw skill 🎉
langsmith-cli — query your LangSmith traces with natural language, right from your AI assistant.
ask "what do failing runs have in common?" and get an answer back. Also: cost breakdowns, latency percentiles, before/after diffs.
No extra API key. No data leaving your machine.
👉 clawhub.com/skills/langsmith…
출처: https://nitter.net/hwchase17/status/2033746066911465767#m
RT by @hwchase17: Just published my first OpenClaw skill 🎉
langsmith-cli — query
RT by @hwchase17: Just published my first OpenClaw skill 🎉
langsmith-cli — query
Just published my first OpenClaw skill 🎉
langsmith-cli — query your LangSmith traces with natural language, right from your AI assistant.
ask "what do failing runs have in common?" and get an answer back. Also: cost breakdowns, latency percentiles, before/after diffs.
No extra API key. No data leaving your machine.
👉 clawhub.com/skills/langsmith…
출처: https://nitter.net/ralphesber/status/2033653338298859659#m
RT by @hwchase17: Great kickoff at NVIDIA GTC - starting with a fun panel on age
RT by @hwchase17: Great kickoff at NVIDIA GTC - starting with a fun panel on age
Great kickoff at NVIDIA GTC - starting with a fun panel on agentic AI this morning with @steipete @SGRodriques @hwchase17 @saranormous @Alfred_Lin
출처: https://nitter.net/vincentweisser/status/2033730658309390695#m
관련 노트
- [[NVIDIA]]
- [[NVDA]]
- [[260314_x]] — 키워드 유사
- [[260318_x]] — 키워드 유사
- [[260319_x]] — 키워드 유사
- [[260313_x]] — 키워드 유사
- [[260319_tg]] — 키워드 유사
- [[260315_hn]] — 키워드 유사
- [[260316_x]] — 키워드 유사
- [[260310_tg]] — 키워드 유사