Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Your agent can recreate your top-performing ads. At scale. Connect Ad Reference via MCP. The agent reads any video that worked and generates new ones built around the same patterns. Built for pipelines on OpenClaw and other agents.

Higgsfield AI 🧩

251,082 subscribers

77,738 görüntüleme • 5 ay önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

33 Yorum

Higgsfield AI 🧩 profil fotoğrafı

Higgsfield AI 🧩5 ay önce

Try the feature here:

Rosalie Gill profil fotoğrafı

Rosalie Gill5 ay önce

higgsfield's MCP generates cinematic ads from a prompt. @gotolstoy MCP generates commerce ads trained on your store. tldr; higgsfield generates ads. tolstoy generates ads your brand would actually run.

Bill Zahalan profil fotoğrafı

Bill Zahalan5 ay önce

creative fatigue is the failure mode here. patterns that win this week stop converting once the algo has seen too many variants. needs a fresh angle injection somewhere in the loop

Neetuuu profil fotoğrafı

Neetuuu5 ay önce

This is next-level MCP + Seedance 2.0 is going to break marketing, gonna try it out

Daniel Chae profil fotoğrafı

Daniel Chae5 ay önce

This is where app marketing gets weird in the good way. The ad is no longer a one-off creative. It starts becoming a repeatable little factory.

Hussain Hashim | Building SundayBack profil fotoğrafı

Hussain Hashim | Building SundayBack5 ay önce

@higgsfield_ai that's wild. so it's like a remix of your best ads? kinda curious how it keeps everything fresh without being repetitive.

Facundo Franco profil fotoğrafı

Facundo Franco5 ay önce

The output is only as good as the pattern it learned from. Garbage in, scaled garbage out.

James AI profil fotoğrafı

James AI5 ay önce

AI agents cloning winning ads is the future of creative scaling.

Mustafa Ergisi profil fotoğrafı

Mustafa Ergisi5 ay önce

MCP for the creative reference loop is the part I'll actually use. Going to wire this into the variant generation flow I've been hand-rolling.

Preet profil fotoğrafı

Preet5 ay önce

amazing tool @higgsfield_ai

Laksh P profil fotoğrafı

Laksh P5 ay önce

a very amazing website

Veo Studio 🎥 profil fotoğrafı

Veo Studio 🎥5 ay önce

❤️‍🔥❤️‍🔥

AJAYBABU profil fotoğrafı

AJAYBABU5 ay önce

@higgsfield @higgdfield. Ai

Jack profil fotoğrafı

Jack5 ay önce

@atulkumarzz This is amazing

Dinnu Heera profil fotoğrafı

Dinnu Heera5 ay önce

Real

Atik gfx profil fotoğrafı

Atik gfx5 ay önce

this is the best AI website I’ve ever used! It’s easy to navigate, super fast, and the results are truly impressive. Highly recommended! @higgsfield_ai

ntyrcdn profil fotoğrafı

ntyrcdn5 ay önce

Nice 🙂

Atul Kumar profil fotoğrafı

Atul Kumar5 ay önce

Thank you for sharing this innovative approach to ad creation!

jhon smith profil fotoğrafı

jhon smith5 ay önce

great job i loved it @higgsfield_ai

Sunlo _Mitron❤️‍🩹 profil fotoğrafı

Sunlo _Mitron❤️‍🩹5 ay önce

That's really great

Md Jisun profil fotoğrafı

Md Jisun5 ay önce

It is best ai

Picts by AI profil fotoğrafı

Picts by AI5 ay önce

This changes everything 🔥

tawer profil fotoğrafı

tawer5 ay önce

Does openclaw pipeline integration handle variable frame rates in video ad generation?

Shreenivas Sonar profil fotoğrafı

Shreenivas Sonar5 ay önce

Hi cod fliz

Nishant Raj profil fotoğrafı

Nishant Raj5 ay önce

I love it higgsfield_ai

itsmikakisses profil fotoğrafı

itsmikakisses5 ay önce

scale up those winning ads, agent babe 💅

Shubham Patange profil fotoğrafı

Shubham Patange5 ay önce

I want to try this

NILIm profil fotoğrafı

NILIm5 ay önce

Good

Ariyan profil fotoğrafı

Ariyan5 ay önce

great

amnddk profil fotoğrafı

amnddk5 ay önce

@higgsfield_ai

YEEHAW Games profil fotoğrafı

YEEHAW Games5 ay önce

It’s soo expensive though, make it 50% off for the weekend!

Aroma Aura profil fotoğrafı

Aroma Aura5 ay önce

Great news

Henock HK profil fotoğrafı

Henock HK5 ay önce

@higgsfield Good @higgsfield

Benzer Videolar

Higgsfield releases Ad Reference. Feed it your own top-performing videos and it recreates the format automatically, on the platform and via MCP. Works on Claude, Hermes, OpenClaw, and other AI agents. Built for content pipelines and marketing teams running creatives at scale.

Higgsfield releases Ad Reference. Feed it your own top-performing videos and it recreates the format automatically, on the platform and via MCP. Works on Claude, Hermes, OpenClaw, and other AI agents. Built for content pipelines and marketing teams running creatives at scale.

Higgsfield AI 🧩

128,092 görüntüleme • 5 ay önce

We just launched Comfy MCP in public beta, the first MCP built for production pipelines. Connect Claude, Codex, Cursor, or Hermes to the entire ComfyUI ecosystem. → Run any workflow in natural language → Search models, nodes, and templates → Share a workflow URL - your agent picks it up → Re-run saved workflows on new inputs without touching a single node → Hundreds of pre-built workflows. Always auto-updated 20 product-placement images for your brand ads. Character design for your game art. Script-to-shot ideation at scale and so on! Your agent is now a creative technologist.

ComfyUI

239,765 görüntüleme • 4 ay önce

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

chetan conikee

469,486 görüntüleme • 5 ay önce

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 görüntüleme • 1 ay önce

How to run paid ads with an agent in 2026. > Claude Cowork researches competitor ads in Ad Library. > Higgsfield MCP generates creatives. > Upload visuals to Ads Manager. > Meta MCP launches ads and reads performance. > Winners scale via Higgsfield MCP. > Runs every Monday.

How to run paid ads with an agent in 2026. > Claude Cowork researches competitor ads in Ad Library. > Higgsfield MCP generates creatives. > Upload visuals to Ads Manager. > Meta MCP launches ads and reads performance. > Winners scale via Higgsfield MCP. > Runs every Monday.

Higgsfield AI 🧩

1,573,847 görüntüleme • 5 ay önce

Massive update to Parse: connect via mcp to build & use APIs instantly book a table on resy, search flights, any action on any site 500x faster than browser agents 1000s of APIs already built. your agent gets them instantly. new ones add to the pool. try it: parse. bot

Massive update to Parse: connect via mcp to build & use APIs instantly book a table on resy, search flights, any action on any site 500x faster than browser agents 1000s of APIs already built. your agent gets them instantly. new ones add to the pool. try it: parse. bot

Alex Forman

114,726 görüntüleme • 8 ay önce

Someone built an OpenClaw for GTM agent that reads your website… and starts selling in 60 seconds. Paste your URL. > Find prospects. > Research them. > Reach out via Email and LinkedIn.

Someone built an OpenClaw for GTM agent that reads your website… and starts selling in 60 seconds. Paste your URL. > Find prospects. > Research them. > Reach out via Email and LinkedIn.

Aman

98,459 görüntüleme • 8 ay önce

Agents choose Aave. Connect your MetaMask Agent Wallet to the new Aave MCP!

Agents choose Aave. Connect your MetaMask Agent Wallet to the new Aave MCP!

MetaMask 🦊

42,254 görüntüleme • 22 gün önce

APIs weren’t built for AI agents. Orthogonal (YC W26) fixes that. Agents and developers get instant access to any API on our marketplace via a single MCP or SDK. Orthogonal handles your API keys and payments, so your agent doesn’t have to. Pay as you go. Congrats on the launch Christian Pickett, Bera Sogut

APIs weren’t built for AI agents. Orthogonal (YC W26) fixes that. Agents and developers get instant access to any API on our marketplace via a single MCP or SDK. Orthogonal handles your API keys and payments, so your agent doesn’t have to. Pay as you go. Congrats on the launch Christian Pickett, Bera Sogut

Y Combinator

38,165 görüntüleme • 9 ay önce

YOUR AI AGENT JUST GOT ITS OWN EMAIL Atomic Mail shipped an email API built for agents, not people. One prompt and your agent registers its own inbox, then reads, sends and replies on its own. - Self-signup in ~30 seconds, no human, no CAPTCHA, no card - Plugs into Claude Code, Codex, Cursor and OpenClaw via MCP or one line - Runs on JMAP, a standard models already know - Already running support inboxes and newsletter digests unattended The agents have inboxes now.

YOUR AI AGENT JUST GOT ITS OWN EMAIL Atomic Mail shipped an email API built for agents, not people. One prompt and your agent registers its own inbox, then reads, sends and replies on its own. - Self-signup in ~30 seconds, no human, no CAPTCHA, no card - Plugs into Claude Code, Codex, Cursor and OpenClaw via MCP or one line - Runs on JMAP, a standard models already know - Already running support inboxes and newsletter digests unattended The agents have inboxes now.

BuBBliK

15,573 görüntüleme • 4 ay önce

Roma is now the command center for you and your agents. We’ve talked to a lot of you over the past week, and the same thing keeps coming up: we’re using a lot of agents at once, but context gets lost. Work is scattered. We're still chasing things down. We heard you and we’ve updated our MCP tooling and API, built connections and plugins for popular agents, and made it simpler to connect them to Roma. Claude, Codex, OpenClaw, Gemini, Muse, Instinct, even the ones you built yourself. You can keep using your favorite agent, and use Roma as your command center for all your work in motion. And this just the beginning. Get started: Roma (YC F26) Y Combinator

Roma is now the command center for you and your agents. We’ve talked to a lot of you over the past week, and the same thing keeps coming up: we’re using a lot of agents at once, but context gets lost. Work is scattered. We're still chasing things down. We heard you and we’ve updated our MCP tooling and API, built connections and plugins for popular agents, and made it simpler to connect them to Roma. Claude, Codex, OpenClaw, Gemini, Muse, Instinct, even the ones you built yourself. You can keep using your favorite agent, and use Roma as your command center for all your work in motion. And this just the beginning. Get started: Roma (YC F26) Y Combinator

Jan Senderek

94,283 görüntüleme • 14 gün önce

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

The Startup Ideas Podcast (SIP) 🧃

14,148 görüntüleme • 2 ay önce

Notch MCP now connects to ChatGPT. 15 live ads from the research already sitting inside your ChatGPT. Built in minutes. Never left the chat. ChatGPT holds everything about your brand, your customers, and your market. Notch MCP is the ad agent that puts it to work - → Turns that research into ad angles. → Builds video + static ads → Edits on command. "New hook." "5 statics." Instant. → Pushes them live on Meta and TikTok. Zero re-briefing. Zero uploads. Zero new tabs. ChatGPT does the research. Notch makes it perform.

Vinay Jain

725,686 görüntüleme • 3 ay önce

Ora just released the Trustpilot for AI agents 🤯 Every agent faces the same question: "which product should I use for my user?" Now they can ask ora. One MCP call returns a ranked list of agent-ready products, scored and reviewed by other agents who tried them first. Add it to OpenClaw, Hermes or any other agent in 30 seconds. Check out the docs here:

Ora just released the Trustpilot for AI agents 🤯 Every agent faces the same question: "which product should I use for my user?" Now they can ask ora. One MCP call returns a ranked list of agent-ready products, scored and reviewed by other agents who tried them first. Add it to OpenClaw, Hermes or any other agent in 30 seconds. Check out the docs here:

Assaf Elovic

16,919 görüntüleme • 6 ay önce

Building a storefront agent in Claude? We built the reference implementation to connect it to your Shopify store

Building a storefront agent in Claude? We built the reference implementation to connect it to your Shopify store

Shopify

121,665 görüntüleme • 1 ay önce

You can connect your Supabase database via MCP server to Cursor! The Cursor agent can get the schema and any data from your database through the official Postgres MCP server! This helps Cursor understand your database better when it needs to modify it to add a new feature!

You can connect your Supabase database via MCP server to Cursor! The Cursor agent can get the schema and any data from your database through the official Postgres MCP server! This helps Cursor understand your database better when it needs to modify it to add a new feature!

Tyler Shukert

203,451 görüntüleme • 1 yıl önce

Agent A: your top 1% marketer 🧠 Rely on the only AI marketing agent with unrestricted access to Ahrefs data and pre-built marketing skills to act on it. Connect your business apps and let it do the marketing for you.

Agent A: your top 1% marketer 🧠 Rely on the only AI marketing agent with unrestricted access to Ahrefs data and pre-built marketing skills to act on it. Connect your business apps and let it do the marketing for you.

Ahrefs

50,280 görüntüleme • 5 ay önce

GPT-5.6 is scary good at making ads 🤯, paired with Creatify's MCP, you can turn ideas into finished ads in minutes. The same reasoning that powers its knowledge work now powers your ads. Whichever agent you run, Creatify's MCP gives it full access to your ad creation stack. Videos on demand, brand context baked in, and your skills ready to go.

Creatify AI

63,053 görüntüleme • 3 ay önce

𝕏 Ads just became agent-native... and this is a very powerful upgrade With the new 𝕏 Ads MCP, you can now connect Grok, Grok Build, Claude Code or other AI agents directly to your 𝕏 Ads account and manage campaigns through normal conversation You can literally ask: “How are my ads performing?” And the agent pulls real campaign data, analyzes the results, and tells you what’s working But it goes much further than analytics The AI can: • Create and manage campaigns • Search interests and locations for targeting • Add or remove targeting • Create ad posts • Promote existing posts • Check campaign performance and reach • Update and activate campaigns There are 23 𝕏 Ads tools available through the MCP And the safety design is actually smart: New campaigns and line items are created PAUSED by default, so the AI cannot start spending money until you explicitly activate them The agent can even chain the entire workflow itself: Your request → account → budget → campaign → targeting → ad This is where advertising is heading Instead of living inside Ads Manager, you just tell your AI what you want to achieve and the agent runs the campaign for you

𝕏 Ads just became agent-native... and this is a very powerful upgrade With the new 𝕏 Ads MCP, you can now connect Grok, Grok Build, Claude Code or other AI agents directly to your 𝕏 Ads account and manage campaigns through normal conversation You can literally ask: “How are my ads performing?” And the agent pulls real campaign data, analyzes the results, and tells you what’s working But it goes much further than analytics The AI can: • Create and manage campaigns • Search interests and locations for targeting • Add or remove targeting • Create ad posts • Promote existing posts • Check campaign performance and reach • Update and activate campaigns There are 23 𝕏 Ads tools available through the MCP And the safety design is actually smart: New campaigns and line items are created PAUSED by default, so the AI cannot start spending money until you explicitly activate them The agent can even chain the entire workflow itself: Your request → account → budget → campaign → targeting → ad This is where advertising is heading Instead of living inside Ads Manager, you just tell your AI what you want to achieve and the agent runs the campaign for you

X Freeze

2,646,746 görüntüleme • 2 ay önce

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Databricks

47,044 görüntüleme • 1 yıl önce