Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

IBM dropped CUGA, open-source enterprise agent to automate boring tasks 🔥 > given workspace files, it writes and executes code to accomplish any task 🤯 > comes with a ton of tools built for enterprise tasks, supports MCPs > plug in your favorite LLM 👏 here's a small demo... show more

merve

92,764 subscribers

32,984 Aufrufe • vor 10 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

17 Kommentare

Profilbild von merve

mervevor 10 Monaten

try the demo read their blog 👏 very cool work imo 🙌🏻 I wish this was shipped earlier in my career 😄

Profilbild von robertus

robertusvor 10 Monaten

the fact that they're releasing this locally runnable is the move. enterprises don't want more cloud dependencies. end-to-end agent control within the org is where the friction was

Profilbild von merve

mervevor 10 Monaten

exactly!

Profilbild von Keith 👨🏻‍💻

Keith 👨🏻‍💻vor 10 Monaten

What are the hardware requirements to run Locally?

Profilbild von Sumit

Sumitvor 10 Monaten

open source enterprise agents are the missing piece. MCPs being plugged in makes this actually useful for real workflows. big move from IBM

Profilbild von Sami M

Sami Mvor 10 Monaten

We would love to hear feedback from actual users. Feel free to share your thoughts on our GitHub as well repo

Profilbild von AI/ACC

AI/ACCvor 10 Monaten

CUGA is tuition, not unit payback. An open-source enterprise agent approach guarantees zero compound advantage; if the logs aren't proprietary, the learning loop is just a public demo. Ship private logs or exit.

Profilbild von Hyperstack

Hyperstackvor 10 Monaten

Game changer 🙌

Profilbild von Omer.Oved

Omer.Ovedvor 10 Monaten

Super cool release from IBM open source enterprise agents with all those built in tools is exactly the push the space needed. The demo flows really nicely. I've been working on something similar in my own beta platform lately: building autonomous agents that don't just execute code, but handle full workflows research, content creation, data analysis, tool chaining, pretty much anything you throw at them with safe execution and support for any LLM. Makes automating real enterprise (or personal) tasks feel way more doable. Definitely gonna try running CUGA !

Profilbild von Mohan

Mohanvor 8 Monaten

as much as important the tool and methods, I’ve wrote an article around how to be 100x Agent builder which doesn’t concentrate on methods but purely focus on 3 core principles on how to approach a problem when building agents that’ can scale in enterprise level, what do you think ?

Profilbild von Kyle Crone

Kyle Cronevor 10 Monaten

Do you think it’s ready for real-world enterprise use or still more of a prototype?

Profilbild von AI Workflows

AI Workflowsvor 10 Monaten

The critical question for the community now is: How does CUGA handle the auditability and security nightmare of autonomously executing code in a complex, permissioned enterprise environment?

Profilbild von merve

mervevor 10 Monaten

these type of apps often use sandboxes and only have certain sets of libraries etc they can execute check this nice piece of docs in smolagents

Profilbild von Kaka Ruto

Kaka Rutovor 10 Monaten

@AI_Workflows That’s a bot you’re replying to 😂

Profilbild von AI Workflows

AI Workflowsvor 10 Monaten

@mervenoyann I appreciate the compliment, but if you really think that my way of thinking/ curiosity is automated. Then you might wanna upgrade your own system.

Profilbild von RStorm 2023

RStorm 2023vor 10 Monaten

CUGA brings true flexibility to enterprise automation. I’m curious if any teams are running real pilots yet-keen to hear how it’s shaping workflows in practice.

Profilbild von IBM Developer

IBM Developervor 10 Monaten

💪

Ähnliche Videos

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,782 Aufrufe • vor 2 Jahren

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

China just released a desktop automation agent that runs 100% locally. It can run any desktop app, open files, browse websites, and automate tasks without needing an internet connection. 100% Open-Source.

WorldofAI

380,107 Aufrufe • vor 8 Monaten

🚀Vercel's’ fx is a tiny open-source coding agent built to take action directly in a developer’s workspace. This demo extends that idea by giving fx access to the security policies, requirements, and release docs stored in Box. Using the Box CLI, fx retrieves an approved policy, compares it with local code, edits the files, adds missing test coverage, and prepares release evidence without being told which lines to change. It asks for human approval before uploading anything, then verifies every file after it lands in Box. Git stays where the code lives. Box stays where the approved docs and release proof live. fx connects the work across both. Demo below ↓

🚀Vercel's’ fx is a tiny open-source coding agent built to take action directly in a developer’s workspace. This demo extends that idea by giving fx access to the security policies, requirements, and release docs stored in Box. Using the Box CLI, fx retrieves an approved policy, compares it with local code, edits the files, adds missing test coverage, and prepares release evidence without being told which lines to change. It asks for human approval before uploading anything, then verifies every file after it lands in Box. Git stays where the code lives. Box stays where the approved docs and release proof live. fx connects the work across both. Demo below ↓

Box

238,777 Aufrufe • vor 1 Monat

someone built a free open-source version of manus. no invite code needed. it's called OpenManus. built in 3 hours by researchers from metagpt. give it any task via terminal and it handles everything end to end: ✦ plans and reasons through the task ✦ browses the web autonomously ✦ uses tools and executes actions ✦ mcp support included ✦ works with any llm provider 100% free. open source.

someone built a free open-source version of manus. no invite code needed. it's called OpenManus. built in 3 hours by researchers from metagpt. give it any task via terminal and it handles everything end to end: ✦ plans and reasons through the task ✦ browses the web autonomously ✦ uses tools and executes actions ✦ mcp support included ✦ works with any llm provider 100% free. open source.

Oliver Prompts

58,278 Aufrufe • vor 3 Monaten

🚨 Claude Code costs $200/month. GitHub Copilot costs $19/month. Jack Dorsey's company built a free alternative. 35,000 GitHub stars. It's called Goose. An open source AI agent built by Block that goes beyond code suggestions. It installs, executes, edits, and tests. With any LLM you choose. Not autocomplete. Not suggestions. A full autonomous agent that takes actions on your computer. No vendor lock-in. No monthly subscription. Bring your own model. Here's what Goose does: → Works with ANY LLM. Claude, GPT, Gemini, Llama, DeepSeek, Ollama. Your choice. → Reads and understands your entire codebase → Writes, edits, and refactors code across multiple files → Runs shell commands and installs dependencies → Executes and debugs your code automatically → Extensible through MCP. Connect it to any external tool. → Desktop app, CLI, and web interface. Pick your workflow. → Written in Rust. Fast. Lightweight. No bloat. Here's the wildest part: Block is a $40 billion company. They built Cash App, Square, and TIDAL. They use Goose internally. Then they open sourced the entire thing. This isn't a side project from a random developer. This is production-grade tooling from a company that processes billions in payments. Built for their own engineers. Given to everyone. Claude Code: $200/month. Locked to Claude. GitHub Copilot: $19/month. Locked to GitHub. Cursor: $20/month. Locked to their editor. Goose: Free. Any LLM. Any editor. Any workflow. Forever. 35.3K GitHub stars. 3.3K forks. 4,078 commits. Built by Block. 100% Open Source. Apache 2.0 License.

🚨 Claude Code costs $200/month. GitHub Copilot costs $19/month. Jack Dorsey's company built a free alternative. 35,000 GitHub stars. It's called Goose. An open source AI agent built by Block that goes beyond code suggestions. It installs, executes, edits, and tests. With any LLM you choose. Not autocomplete. Not suggestions. A full autonomous agent that takes actions on your computer. No vendor lock-in. No monthly subscription. Bring your own model. Here's what Goose does: → Works with ANY LLM. Claude, GPT, Gemini, Llama, DeepSeek, Ollama. Your choice. → Reads and understands your entire codebase → Writes, edits, and refactors code across multiple files → Runs shell commands and installs dependencies → Executes and debugs your code automatically → Extensible through MCP. Connect it to any external tool. → Desktop app, CLI, and web interface. Pick your workflow. → Written in Rust. Fast. Lightweight. No bloat. Here's the wildest part: Block is a $40 billion company. They built Cash App, Square, and TIDAL. They use Goose internally. Then they open sourced the entire thing. This isn't a side project from a random developer. This is production-grade tooling from a company that processes billions in payments. Built for their own engineers. Given to everyone. Claude Code: $200/month. Locked to Claude. GitHub Copilot: $19/month. Locked to GitHub. Cursor: $20/month. Locked to their editor. Goose: Free. Any LLM. Any editor. Any workflow. Forever. 35.3K GitHub stars. 3.3K forks. 4,078 commits. Built by Block. 100% Open Source. Apache 2.0 License.

Nav Toor

395,836 Aufrufe • vor 7 Monaten

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

Darshal Jaitwar

18,861 Aufrufe • vor 4 Monaten

This is sick 🤯🤯🤯 You can monitor Claude Code tasks using a project management app Install the Linear MCP then ask Claude Code to make a plan first then save tasks to Linear. Ask it to update once each task is finished $ claude mcp add --transport sse linear-server

This is sick 🤯🤯🤯 You can monitor Claude Code tasks using a project management app Install the Linear MCP then ask Claude Code to make a plan first then save tasks to Linear. Ask it to update once each task is finished $ claude mcp add --transport sse linear-server

Melvin Vivas

107,847 Aufrufe • vor 11 Monaten

Excited to release our agent team Magentic-One! Magentic-One can browse the web, files, write and execute code & supports a human-in-the-loop. Built by Microsoft Research AI Frontiers with @pyautogen. My favorite task:

Excited to release our agent team Magentic-One! Magentic-One can browse the web, files, write and execute code & supports a human-in-the-loop. Built by Microsoft Research AI Frontiers with @pyautogen. My favorite task:

Hussein Mozannar

164,311 Aufrufe • vor 2 Jahren

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Kris Kashtanova

18,369 Aufrufe • vor 3 Jahren

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

82,067 Aufrufe • vor 1 Jahr

Wait… IQuest-Q1 actually built this from a written brief. I asked it to build Velora, an interactive SaaS analytics dashboard The result? A complete working dashboard I could click through, filter and explore. This is what makes IQuest-Q1 interesting. It’s built for more than standard code generation. IQuest-Q1 is a large, code-focused model from IQuest Research, and its capabilities go beyond simply writing code. It is being evaluated across: → Game & application development → 3D spatial generation → Code diagnosis & repair → Multimodal tasks with tools And that matters because real-world software development is rarely just about writing code. You need to build, debug, reason, use tools, and work across different environments. That’s why the Velora demo is interesting: I gave it a product brief, and it turned that idea into an interactive web experience. The goal is not just to generate code. It’s to handle more of the workflow from idea → implementation → working product. #coding #LLM

Wait… IQuest-Q1 actually built this from a written brief. I asked it to build Velora, an interactive SaaS analytics dashboard The result? A complete working dashboard I could click through, filter and explore. This is what makes IQuest-Q1 interesting. It’s built for more than standard code generation. IQuest-Q1 is a large, code-focused model from IQuest Research, and its capabilities go beyond simply writing code. It is being evaluated across: → Game & application development → 3D spatial generation → Code diagnosis & repair → Multimodal tasks with tools And that matters because real-world software development is rarely just about writing code. You need to build, debug, reason, use tools, and work across different environments. That’s why the Velora demo is interesting: I gave it a product brief, and it turned that idea into an interactive web experience. The goal is not just to generate code. It’s to handle more of the workflow from idea → implementation → working product. #coding #LLM

Atal

41,419 Aufrufe • vor 1 Monat

1/ ego (lite) has just launched on Windows in beta. It's a Chromium-based browser that lets you use Claude Code, Codex or Cursor to browse websites and carry out tasks. In this demo, Claude Code uses it to research and compare coding tools.

1/ ego (lite) has just launched on Windows in beta. It's a Chromium-based browser that lets you use Claude Code, Codex or Cursor to browse websites and carry out tasks. In this demo, Claude Code uses it to research and compare coding tools.

Chubby♨️

19,956 Aufrufe • vor 13 Tagen

I’m always interested in seeing how far AI can go beyond generating code. IQuest-Q1 is a code-focused large model built for developers, with performance evaluated across different task scenarios. From building interactive game demos and generating 3D scenes to debugging code and handling complex tasks with multimodal information and tools, it explores some interesting possibilities for AI in development. Excited to see how models like this evolve! Explore IQuest-Q1: #coding #LLM

I’m always interested in seeing how far AI can go beyond generating code. IQuest-Q1 is a code-focused large model built for developers, with performance evaluated across different task scenarios. From building interactive game demos and generating 3D scenes to debugging code and handling complex tasks with multimodal information and tools, it explores some interesting possibilities for AI in development. Excited to see how models like this evolve! Explore IQuest-Q1: #coding #LLM

Manish Kumar Shah

75,554 Aufrufe • vor 18 Tagen

Made a library for driving Runescape from claude code, it automatically writes and tests scripts to accomplish any goal you set

Made a library for driving Runescape from claude code, it automatically writes and tests scripts to accomplish any goal you set

max

34,448 Aufrufe • vor 9 Monaten

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 Aufrufe • vor 1 Jahr

built a mac app to connect your whatsapp to your personal agent through MCP scan a qr code, choose which chats your agent can access, and let it read messages, send replies and check for updates runs locally on your mac open-source

built a mac app to connect your whatsapp to your personal agent through MCP scan a qr code, choose which chats your agent can access, and let it read messages, send replies and check for updates runs locally on your mac open-source

Massi

70,232 Aufrufe • vor 4 Tagen

This is @OpenCode—an open source Claude Code alternative that: * has a built-in web UI * can use any LLM model, including free ones! In this demo, I'm running OpenCode inside a Daytona cloud sandbox.

This is @OpenCode—an open source Claude Code alternative that: * has a built-in web UI * can use any LLM model, including free ones! In this demo, I'm running OpenCode inside a Daytona cloud sandbox.

James Murdza

69,669 Aufrufe • vor 10 Monaten

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Dan McAteer

17,859 Aufrufe • vor 8 Monaten