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。

Meet Optimus Prime Agent. Transform between GUI and terminal instantly. Same conversation, zero context lost. Track costs, split views, and save your favorite commands. Prime Agent, roll out.

super.engineering

6,114 subscribers

17,012 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

18 条评论

kevin 的头像

kevin2 个月前

this is so sick

Fitz 的头像

Fitz2 个月前

That’s hot

Daniel Zarifpour 的头像

Daniel Zarifpour2 个月前

cc: @PrimeIntellect

Seth Karten 的头像

Seth Karten2 个月前

Wow prime agent with a gui is nice. How does it handle subagents and swarm view?

KC 的头像

KC2 个月前

It's probably inadvertent, but quoting Optimus Prime to sell the agent one day after the voice of Optimus Prime dies. It's just uncomfortable for me.

Monty 的头像

Monty2 个月前

sweet

moku 的头像

moku2 个月前

Please add linux or windows support 🥺🥺

Ganidhu 的头像

Ganidhu2 个月前

super cool concept!

capad / aadarsh 的头像

capad / aadarsh2 个月前

Optimus Prime is such a sickk and perfect name for it wtf..

Brook Tang 的头像

Brook Tang2 个月前

another beautiful terminal after otty.

mqotip 的头像

mqotip2 个月前

Wait… same conversation, zero context lost when switching GUI vs terminal? How is that even possible 👀

Monty 的头像

Monty2 个月前

can't change the model in chat mode, uses default from CLI, and no fast toggle in chat mode.

Ymir 的头像

Ymir2 个月前

Does this support running the agents on a remote machine with port forwarding to yours over tailscale?

Guaryonline 的头像

Guaryonline2 个月前

where can i get this

Kaloyan Stoyanov 的头像

Kaloyan Stoyanov2 个月前

Hey, so i love how this looks and how you took Arc/Dia sidebars but the problem is that for soem reason on my mac its not 120fps but instead 60 so everything looks laggy and so i wanted to ask you if there's is some kind of a fix for that?

pozitiv4ik 的头像

pozitiv4ik2 个月前

bro, I really like your project, but add the ability to make a chat system instead of a worktree. sometimes you dont need to create one

elliott 的头像

elliott2 个月前

But can I has?

Danny 的头像

Danny2 个月前

but can it run doom?

相关视频

prime agent v0.9.5 we fixed a lot of bugs and, of course, we had prime agent feature its favorite updates it picked our perf work. then it created the video itself.

prime agent v0.9.5 we fixed a lot of bugs and, of course, we had prime agent feature its favorite updates it picked our perf work. then it created the video itself.

Seth Karten

12,986 次观看 • 1 个月前

Vercel Agent now works in @slackhq Code, with your app's full production context and zero setup. ▪︎ Connect secrets, env vars, commands, repos ▪︎ Steer the agent as a team ▪︎ Review diffs and ship directly in code channels

Vercel Agent now works in @slackhq Code, with your app's full production context and zero setup. ▪︎ Connect secrets, env vars, commands, repos ▪︎ Steer the agent as a team ▪︎ Review diffs and ship directly in code channels

Vercel Developers

15,726 次观看 • 2 个月前

Oneshot Bloomberg-style stock market board by Kimi Agent. Stocks, price action, and real-time context — all at your fingertip via terminal commands. All you need is a prompt; Kimi handles the rest.

Oneshot Bloomberg-style stock market board by Kimi Agent. Stocks, price action, and real-time context — all at your fingertip via terminal commands. All you need is a prompt; Kimi handles the rest.

Kimi Product

86,282 次观看 • 9 个月前

Meet Atomic Agent Desktop! ✦ Local AI-first agent for Mac, Windows & Linux ✦ 4x bigger context window on local models with TurboQuant ✦ Atomic Fusion orchestrates cloud and local models to reduce costs Download Free & Private Agent →

Meet Atomic Agent Desktop! ✦ Local AI-first agent for Mac, Windows & Linux ✦ 4x bigger context window on local models with TurboQuant ✦ Atomic Fusion orchestrates cloud and local models to reduce costs Download Free & Private Agent →

Atomic Agent

90,439 次观看 • 1 个月前

Kai-Fu Lee (founder of Sinovation Ventures) explains how the future is all about multi-agent systems. 1 agent today is like a pre-internet PC, useful but isolated. Connect agents, and they share context, split tasks, and coordinate instantly.

Kai-Fu Lee (founder of Sinovation Ventures) explains how the future is all about multi-agent systems. 1 agent today is like a pre-internet PC, useful but isolated. Connect agents, and they share context, split tasks, and coordinate instantly.

Rohan Paul

61,663 次观看 • 9 个月前

Peter Cullen, the legendary voice of Optimus Prime, has passed away at 85. 💔 For generations, his voice was Optimus Prime. “Autobots, roll out!” Rest in peace, legend. 🕊️

Peter Cullen, the legendary voice of Optimus Prime, has passed away at 85. 💔 For generations, his voice was Optimus Prime. “Autobots, roll out!” Rest in peace, legend. 🕊️

Every Movie Plug

71,444 次观看 • 2 个月前

My favorite agent terminal app

My favorite agent terminal app

Tommy J. Vedvik

217,194 次观看 • 4 个月前

The next task will almost certainly suit a different agent. Keep the context when you change tools → With Bring Your Own Agent, you can switch between Codex, Claude Code, Cursor, and other tools while keeping the same underlying context: • Switch model tools seamlessly • Reuse recorded briefs and Playbooks • Maintain strict permission boundaries Models will keep changing. Today it’s Claude, tomorrow it’s Cursor. What stays is the context you built. Save the rules, keep the history, and bring whichever agent fits the job.

The next task will almost certainly suit a different agent. Keep the context when you change tools → With Bring Your Own Agent, you can switch between Codex, Claude Code, Cursor, and other tools while keeping the same underlying context: • Switch model tools seamlessly • Reuse recorded briefs and Playbooks • Maintain strict permission boundaries Models will keep changing. Today it’s Claude, tomorrow it’s Cursor. What stays is the context you built. Save the rules, keep the history, and bring whichever agent fits the job.

Ethan Pierce

13,719 次观看 • 21 天前

Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.

Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.

Prime Intellect

3,229,669 次观看 • 3 个月前

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

rody

18,089 次观看 • 1 个月前

your personal AI agent is coming to every pair of Meta Glasses. same agent. same context. now just a name away.

your personal AI agent is coming to every pair of Meta Glasses. same agent. same context. now just a name away.

Muse

31,782 次观看 • 1 个月前

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 次观看 • 4 个月前

I used the new Cursor agent + CopyCoder to build a Calendly frontend clone in 20mins Cursor agent now: - runs terminal commands - picks it's own context - executes more jobs with one prompt Crazy where this is going

I used the new Cursor agent + CopyCoder to build a Calendly frontend clone in 20mins Cursor agent now: - runs terminal commands - picks it's own context - executes more jobs with one prompt Crazy where this is going

Moritz Kremb

164,416 次观看 • 1 年前

I really loved how dynamic the battle between the Optimus Prime and Starscream clones was.

I really loved how dynamic the battle between the Optimus Prime and Starscream clones was.

Prime

117,319 次观看 • 1 个月前

CSS-only Optimus Prime toggle 🤙 CSS transform was intended for transformers, right?

CSS-only Optimus Prime toggle 🤙 CSS transform was intended for transformers, right?

jhey ʕ•ᴥ•ʔ

238,621 次观看 • 3 年前

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.

InsForge

53,090 次观看 • 5 个月前

1️⃣New Agent Mode: With agent mode in VS Code, Copilot goes beyond your initial request, completing all necessary subtasks and even inferring unspecified tasks. Agent mode allows Copilot to iterate on its own code, propose and guide terminal commands, and analyze and resolve run-time errors. Available today for VS Code Insiders 💫 (2/4)

1️⃣New Agent Mode: With agent mode in VS Code, Copilot goes beyond your initial request, completing all necessary subtasks and even inferring unspecified tasks. Agent mode allows Copilot to iterate on its own code, propose and guide terminal commands, and analyze and resolve run-time errors. Available today for VS Code Insiders 💫 (2/4)

Thomas Dohmke

95,639 次观看 • 1 年前