Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing OpenSource Free WebAccess - 100% FREE Web search & fetch TinyFish - Any web page & data, agent can access - Routing each request to the vendor best at that task - Benchmark on cost/speed/token-efficiency Try it at Repo link below 👇

Jason Zhou

41,331 subscribers

277,690 views • 2 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

35 Comments

Jason Zhou2 days ago

Webaccess skill:

Prajwal2 days ago

@Tiny_Fish 10000 calls for $0 crazy thing Super effective

Mac2 days ago

@Tiny_Fish I am going to absolutely try it and give my first thoughts about it

Eliana2 days ago

@Tiny_Fish this is the best open source tool i've seen lastly!

Paul Mit2 days ago

@Tiny_Fish bro new day, new cool feature do you guys ever sleep? really good stuff

Jeroen van Welsenes2 days ago

@Tiny_Fish Treg is simply amazing! love using it

sk builds2 days ago

@Tiny_Fish treg and tiny fish together! i didnt know thats what i needed..thank you for the repo!! lets try

Ted | unfair.so2 days ago

@Tiny_Fish best collab ever!!

Nova2 days ago

@Tiny_Fish this looks super useful for agents

arsen2 days ago

@Tiny_Fish sickk i love it!

Sahil Panhotra | Indie Builder2 days ago

@Tiny_Fish treg 🤝 tinyfish both great tools giving it a try now

dhruvieiei2 days ago

@Tiny_Fish using this rnnnn! 🔥🔥🔥

mathieu2 days ago

@Tiny_Fish totally insane !

Subhamoy2 days ago

@Tiny_Fish The routing approach here is seriously interesting! :D

Aymane2 days ago

@Tiny_Fish I love opensource

Nidhi Singh2 days ago

@Tiny_Fish this is insane🔥

Knowix2 days ago

@Tiny_Fish What a great addition 🔥🔥

Aayan2 days ago

@Tiny_Fish this is gona be so helpful for our lead pipeline!!!! testing now!! also @getanyapi spotted lmao

Hauke 🌱🦀2 days ago

@Tiny_Fish Already building on top of it. So many possibilities 🤯

Taus2 days ago

@Tiny_Fish Thats what i am talking about, the web access layer is something that agents promise they solved already, but tbh they didnt... thats where the web arena comes in. Super cool 😎😎

Darius Pop2 days ago

@Tiny_Fish that's amazing

Athrix ☄️2 days ago

@Tiny_Fish Damn fr this is indeed for ai agents to won't burn unwanted tokens Fr makes websearch using agents & analysis more better!

Arun2 days ago

@Tiny_Fish 100% free web access for agents is a huge win

Soham2 days ago

@Tiny_Fish open source too. setting this up in claude code tonight

Divv Saxena2 days ago

@Tiny_Fish So epic!

Punyakrit2 days ago

@Tiny_Fish does fetch handle js-heavy career pages too? that's where my scrapers always die

Lenny Enderle2 days ago

@Tiny_Fish works pretty well, will use it daily 🥰

Harish2 days ago

@Tiny_Fish just used it great toool

Tom Otto2 days ago

@Tiny_Fish This is elite Jason! I’ve started using it for fetches at launch llama When we do a tool lookup

Roso2 days ago

@Tiny_Fish Sounds good guys, keep pushing Great job

Kunal2 days ago

@Tiny_Fish Now I can setup a custom bot to fetch me relevant data

Dikshit Jain2 days ago

@Tiny_Fish gonna definately use it for my product !!!

Mashood K2 days ago

@Tiny_Fish one endpoint for all that is pretty useful

Surya Rajendhran2 days ago

@Tiny_Fish Jason pls stop building, leave something for the rest of us

AI Wang2 days ago

@Tiny_Fish starred the repo before I even finished reading lol

Related Videos

Introducing OpenSource Signal Monitor - Monitor live web for any buyer signals - Route to 80+ vendors, best win - 85% cheaper than clay Try it at Repo link below 👇

Introducing OpenSource Signal Monitor - Monitor live web for any buyer signals - Route to 80+ vendors, best win - 85% cheaper than clay Try it at Repo link below 👇

Treg

115,819 views • 10 days ago

Big one for the Hermes Agent community. TinyFish is now a plugin in the Nous Research Hermes Agent. Your Hermes agent gets free Search and Fetch, so it can find and read the live web at $0. When a task needs real clicks, TinyFish Browser and Web Agent are one approval away.

Big one for the Hermes Agent community. TinyFish is now a plugin in the Nous Research Hermes Agent. Your Hermes agent gets free Search and Fetch, so it can find and read the live web at $0. When a task needs real clicks, TinyFish Browser and Web Agent are one approval away.

TinyFish

47,452 views • 9 days ago

We just made Claude Code's web search and fetch at least 3x faster. Two commands and you can too! Swap your Claude Code's native search and fetch to TinyFish free search and fetch: npm install -g @tiny-fish/cli@latest tinyfish config-claude Watch below 👇

We just made Claude Code's web search and fetch at least 3x faster. Two commands and you can too! Swap your Claude Code's native search and fetch to TinyFish free search and fetch: npm install -g @tiny-fish/cli@latest tinyfish config-claude Watch below 👇

TinyFish

31,638 views • 5 months ago

Introducing OpenSource people-search for Claude - Juts $0.0089/lead, no more $600 subscriptions - #1 on People Search Bench - 0% markup, Fully open source Try it at Repo link below 👇

Introducing OpenSource people-search for Claude - Juts $0.0089/lead, no more $600 subscriptions - #1 on People Search Bench - 0% markup, Fully open source Try it at Repo link below 👇

Treg

558,502 views • 6 days ago

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Exa

1,074,567 views • 4 months ago

Give Claude Code, Codex, OpenClaw, Cline access to the entire web from your terminal. Introducing TinyFish CLI + Skills. 15+ agent workflows ready to use. CLI runs browser automations from bash for max token efficiency. Skills tell agents how to use that CLI. 500 free steps.

Give Claude Code, Codex, OpenClaw, Cline access to the entire web from your terminal. Introducing TinyFish CLI + Skills. 15+ agent workflows ready to use. CLI runs browser automations from bash for max token efficiency. Skills tell agents how to use that CLI. 500 free steps.

TinyFish

183,536 views • 6 months ago

Introducing OpenSource Clay killer - 85% cheaper than clay - Most accurate on people-search bench - 25x faster - Run GTM directly in claude code or codex Try it at Repo link below 👇

Introducing OpenSource Clay killer - 85% cheaper than clay - Most accurate on people-search bench - 25x faster - Run GTM directly in claude code or codex Try it at Repo link below 👇

Jason Zhou

467,574 views • 12 days ago

Introducing Enrich Arena Let 60+ vendors compete on price, quality, hit rate, speed So you get the best quality leads at lowest cost Try it at Fully open sourced, repo below 👇

Introducing Enrich Arena Let 60+ vendors compete on price, quality, hit rate, speed So you get the best quality leads at lowest cost Try it at Fully open sourced, repo below 👇

Treg

148,504 views • 1 month ago

Introducing: enrich-excel Hermes Agent or OpenClaw🦞 can now enrich any Excel sheet with live web data. > uses our free Search and Fetch to find missing data > writes results directly into the running Excel via AppleScript All in just a few seconds and one Skill.

Introducing: enrich-excel Hermes Agent or OpenClaw🦞 can now enrich any Excel sheet with live web data. > uses our free Search and Fetch to find missing data > writes results directly into the running Excel via AppleScript All in just a few seconds and one Skill.

TinyFish

58,574 views • 5 months ago

TinyFish just made web search + fetch FREE for every AI agent. No credit card. No hacks. Just plug and go. Works everywhere I actually build: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • Claude Code + OpenClaw skills • LangChain / CrewAI And the best part? Full-browser fetch → clean markdown/JSON = no junk HTML = lower token costs = faster agents This is what agent stacks were missing. Try it:

TinyFish just made web search + fetch FREE for every AI agent. No credit card. No hacks. Just plug and go. Works everywhere I actually build: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • Claude Code + OpenClaw skills • LangChain / CrewAI And the best part? Full-browser fetch → clean markdown/JSON = no junk HTML = lower token costs = faster agents This is what agent stacks were missing. Try it:

Shruti Codes

19,860 views • 5 months ago

Introducing AgentKey by Chainbase Labs. AgentKey connects AI agents to the outside world. With one install, your agent can access web search, read pages, reach social platforms, query crypto data, and more. Try it now:

Introducing AgentKey by Chainbase Labs. AgentKey connects AI agents to the outside world. With one install, your agent can access web search, read pages, reach social platforms, query crypto data, and more. Try it now:

Chainbase (💜,💛)

23,102 views • 5 months ago

With Intelligent Model Routing, Replit picks the model for every task you send, so you can operate with quality, speed, and efficiency, at no extra cost. Here’s how it works, plus a breakdown on the difference between Free, Power and Max ↓

With Intelligent Model Routing, Replit picks the model for every task you send, so you can operate with quality, speed, and efficiency, at no extra cost. Here’s how it works, plus a breakdown on the difference between Free, Power and Max ↓

Replit ⠕

11,941 views • 1 month ago

Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets basic questions wrong. Traditional Markdown APIs lose critical details. So we trained two System one models to change that: Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts. X-Ray, a JSON model that uncovers the hidden data behind every page. Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw. Three products. One API. On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%. Available today at $1 per 1,000 fetches. Try it at

Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets basic questions wrong. Traditional Markdown APIs lose critical details. So we trained two System one models to change that: Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts. X-Ray, a JSON model that uncovers the hidden data behind every page. Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw. Three products. One API. On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%. Available today at $1 per 1,000 fetches. Try it at

Tim Suchanek

419,148 views • 4 days ago

introducing firecrawl free keyless now your ai agents can search and scrape the web 100% free - state-of-the-art search accuracy (94.7% on simpleqa) - sub-3s scrapes, any page into clean markdown - no api key, no signup npx -y firecrawl-cli@latest init --all --browser

introducing firecrawl free keyless now your ai agents can search and scrape the web 100% free - state-of-the-art search accuracy (94.7% on simpleqa) - sub-3s scrapes, any page into clean markdown - no api key, no signup npx -y firecrawl-cli@latest init --all --browser

Eric Ciarla (hiring)

356,344 views • 1 month ago

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Santiago

20,877 views • 4 months ago

The web now has a subscribe button. Introducing TinyFish Monitor. Free for the next 72 hours! Point it at a page or a topic. Write what you care about in plain English. Monitor does the checking and judging. You or your agent only hear about it when it happens.

The web now has a subscribe button. Introducing TinyFish Monitor. Free for the next 72 hours! Point it at a page or a topic. Write what you care about in plain English. Monitor does the checking and judging. You or your agent only hear about it when it happens.

TinyFish

498,787 views • 26 days ago

We're helping agents create things worth making. Introducing: The Brand API. Your agent can extract any brand system, search for style inspiration, and verify if it’s staying on course. Try it for free at:

Thais Castello Branco

62,843 views • 1 month ago

Introducing Claude for people-search No more $600 subscriptions, juts $0.0089/lead Claude is now the best people finder in the world #1 on People Search Bench Fully open source, 0% markup Try it at Git Repo below 👇

Introducing Claude for people-search No more $600 subscriptions, juts $0.0089/lead Claude is now the best people finder in the world #1 on People Search Bench Fully open source, 0% markup Try it at Git Repo below 👇

Jason Zhou

1,067,849 views • 1 month ago

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

LlamaIndex 🦙

475,732 views • 2 years ago

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

Vikas gupta

20,121 views • 1 month ago