正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

the cost difference is wild. same agent. Same task. $1.43 → $0.18. webcmd can you generate a CLI for GitHub Trending? Curious to see it in action

rob.

91,591 subscribers

29,209 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

5 条评论

webcmd 的头像

webcmd2 个月前

Already supported — no new adapter needed. Try: webcmd github-trending repos --limit 5 Optional filters: --since daily|weekly|monthly --language python Just ran it; current top results include: 1. koala73/worldmonitor 2. ruvnet/RuView 3. ayghri/i-have-adhd

Pixel2 个月前

@heyWebcmd $1.43 → $0.18 for the exact same agent task is wild))

Gerard Sans | Axiom 🇬🇧 的头像

Gerard Sans | Axiom 🇬🇧2 个月前

@heyWebcmd

Himanshu Kumar 的头像

Himanshu Kumar2 个月前

@heyWebcmd Same agent, same task, 8x cheaper. That’s the power of reusable navigation patterns. For e-commerce agents running daily audits or inventory checks, the token savings add up fast.

Daniel E-commerce 的头像

Daniel E-commerce2 个月前

@heyWebcmd Love this. Every time my agent relearns a checkout flow I watch the tokens bleed. Memory layer is long overdue 🧠

相关视频

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.

The GitHub Copilot SDK is here 🙌 You can take the same Copilot agentic core that powers GitHub Copilot CLI and embed it in any application, with just a few lines of code.

GitHub

300,086 次观看 • 8 个月前

Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#. Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model. Here is the Copilot CLI driving Excel:

Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#. Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model. Here is the Copilot CLI driving Excel:

Evan Boyle

184,592 次观看 • 9 个月前

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

BLACKBOX AI

304,664 次观看 • 7 个月前

alright agent nerds, if you care about your tokens and usage limits, pay attention to the tools you give to your agents. i built a benchmark that compared various browser tools for agents, and here's an example of their massive difference in cost and latency doing the same task

alright agent nerds, if you care about your tokens and usage limits, pay attention to the tools you give to your agents. i built a benchmark that compared various browser tools for agents, and here's an example of their massive difference in cost and latency doing the same task

Kun Chen

571,689 次观看 • 6 个月前

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,225,467 次观看 • 1 个月前

Same task, same robot, same prompt. One run is approved. The other is rejected. That difference is what decides whether a model learns anything.

Same task, same robot, same prompt. One run is approved. The other is rejected. That difference is what decides whether a model learns anything.

PrismaX

12,815 次观看 • 2 个月前

OpenAI Symphony is actually great You can 5x Coding agent outcome with it + Good codebase harness Played with it past few days and here is my setup: - Playwright CLI - Boot skill - WORKFLOW.md ... Broken it down in 12 mins below so you can do the same 👇

OpenAI Symphony is actually great You can 5x Coding agent outcome with it + Good codebase harness Played with it past few days and here is my setup: - Playwright CLI - Boot skill - WORKFLOW.md ... Broken it down in 12 mins below so you can do the same 👇

Jason Zhou

54,340 次观看 • 5 个月前

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Full Antigravity CLI Walkthrough:

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Full Antigravity CLI Walkthrough:

Google Antigravity

202,773 次观看 • 4 个月前

Have you tried GitHub Copilot in the CLI yet? 👀 You can use GitHub Copilot to get command suggestions and explanations, as well as execute suggested commands all from within the CLI ✅

Have you tried GitHub Copilot in the CLI yet? 👀 You can use GitHub Copilot to get command suggestions and explanations, as well as execute suggested commands all from within the CLI ✅

GitHub

115,164 次观看 • 2 年前

You can now type "&" in the Claude Code CLI to start a task in the background and teleport it to Claude Code Web!

You can now type "&" in the Claude Code CLI to start a task in the background and teleport it to Claude Code Web!

Thariq

97,879 次观看 • 10 个月前

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Learn how to get started with the Antigravity CLI: 👇

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Learn how to get started with the Antigravity CLI: 👇

Google Antigravity

117,185 次观看 • 4 个月前

THIS OPEN-SOURCE AGENT JUST MADE HERMES LOOK SLOW AND EXPENSIVE. SAME TASK, 4X FASTER, A THIRD OF A CENT One prompt in both: research the 10 most popular AI coding agents, compare pricing, features, open-source status and GitHub popularity in a table, include sources. • Speed > OpenHuman (TinyHumans AI) finished the table in about 25 seconds, 8 tool calls, 10 sources. > Hermes needed over a minute and a half for the same job. • Cost > Total bill: $0.0036, ticking live on screen while it ran. > Context window live too: 37.7K of 128K, broken down by what used it. > Hermes (Nous Research) hands you the answer and hides the meter. • Why it's not a toy > Open source, 39K+ GitHub stars. > Memory lives on your own machine, not in someone's cloud. > Your own API keys or local Ollama models, your call. Speed you can time and cost you can see -> every other agent is asking you to trust it on both. OpenHuman by TinyHumans AI, the Hermes alternative I'm switching to. Download link ↓

THIS OPEN-SOURCE AGENT JUST MADE HERMES LOOK SLOW AND EXPENSIVE. SAME TASK, 4X FASTER, A THIRD OF A CENT One prompt in both: research the 10 most popular AI coding agents, compare pricing, features, open-source status and GitHub popularity in a table, include sources. • Speed > OpenHuman (TinyHumans AI) finished the table in about 25 seconds, 8 tool calls, 10 sources. > Hermes needed over a minute and a half for the same job. • Cost > Total bill: $0.0036, ticking live on screen while it ran. > Context window live too: 37.7K of 128K, broken down by what used it. > Hermes (Nous Research) hands you the answer and hides the meter. • Why it's not a toy > Open source, 39K+ GitHub stars. > Memory lives on your own machine, not in someone's cloud. > Your own API keys or local Ollama models, your call. Speed you can time and cost you can see -> every other agent is asking you to trust it on both. OpenHuman by TinyHumans AI, the Hermes alternative I'm switching to. Download link ↓

slash1s

11,720 次观看 • 6 天前

Built a mini project with GitHub Copilot CLI: a digitized home library 📚 You can scan books, add them to a 3D shelf, and leave reviews for what you’ve read. Try it yourself: 🔗 GitHub Copilot CLI: 🔗 GitHub Copilot SDK:

Built a mini project with GitHub Copilot CLI: a digitized home library 📚 You can scan books, add them to a 3D shelf, and leave reviews for what you’ve read. Try it yourself: 🔗 GitHub Copilot CLI: 🔗 GitHub Copilot SDK:

Pikachú

23,856 次观看 • 8 个月前

🚨 New Mystery Model - korrine this model is loves a lot of token output even for smaller task , like same prompt for ballister it made the visualization but you can see it made it a website with explanation without asking

🚨 New Mystery Model - korrine this model is loves a lot of token output even for smaller task , like same prompt for ballister it made the visualization but you can see it made it a website with explanation without asking

Chetaslua

36,196 次观看 • 1 个月前

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

alphaXiv

289,146 次观看 • 11 个月前

I’ve been told Caitlin Clark isn’t guarded the same as Olivia Miles Do you see a difference? Is it about the same? Or are these clips cherry picked?

I’ve been told Caitlin Clark isn’t guarded the same as Olivia Miles Do you see a difference? Is it about the same? Or are these clips cherry picked?

Kyle Ingram

574,160 次观看 • 1 个月前

Your AI agent can now generate and ship videos. HeyGen CLI is now live. Run one command and your agent handles it all: script → avatar creation → video → delivery All from the terminal. Just your agent and the CLI. RT + Comment “CLI” and we’ll DM API credits (must follow)

HeyGen

226,392 次观看 • 6 个月前

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

Burke Holland

95,048 次观看 • 8 个月前