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.

DeepSeek Harness now has live web access through TinyFish. With Free Search + Fetch. DSH is minimal by design. Install the TinyFish CLI and DSH picks it up automatically. (Running GLM-5.3 Flash. And you can see we're excited about GTA 6.)

TinyFish

10,625 subscribers

21,578 Aufrufe • vor 1 Monat •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 Kommentare

Profilbild von TinyFish

TinyFishvor 1 Monat

1. Install the TinyFish CLI: npm install -g @tiny-fish/cli@latest 2. Grab your API key at 3. Run tinyfish auth login You're all set!

Profilbild von VulKan

VulKanvor 1 Monat

gotta love the fish

Profilbild von TinyFish

TinyFishvor 1 Monat

we 🫶 you too

Profilbild von Sam Ongaro

Sam Ongarovor 1 Monat

Nice update, I’m excited to try TinyFish’s live web access and test Free Search plus Fetch to see how it gels. When the CLI setup drops, I’ll give it a spin and share what I end up building first.🤔

Profilbild von TinyFish

TinyFishvor 1 Monat

it's already live: try it out!

Profilbild von David Batista

David Batistavor 1 Monat

DSH picking up the TinyFish CLI by itself is the part that usually needs a dashboard. GLM-5.3 Flash doing live fetch from that install is the demo.

Profilbild von mir

mirvor 1 Monat

I love tinyfish, only think that would make it better is reducing latency to stay competitive among the big boys. Here’s my test on my hermes agent

Profilbild von TinyFish

TinyFishvor 1 Monat

love this!! and really appreciate your feedback on the latency. our engineering team is heads down solving for this :) is this your own eval pipeline btw?

Profilbild von RAZA | AI EXPLORER

RAZA | AI EXPLORERvor 1 Monat

Live web access makes DSH way more capable. TinyFish is a great addition.

Profilbild von TinyFish

TinyFishvor 1 Monat

yess! do try it out and give us your feedback

Profilbild von Shadman 沙德曼

Shadman 沙德曼vor 1 Monat

Are you guys just giving it away for free temporarily, and then going to charge users later?

Profilbild von TinyFish

TinyFishvor 1 Monat

Search and Fetch will be free forever with TinyFish!

Profilbild von Polash Khan

Polash Khanvor 1 Monat

That's awesome news about DeepSeek Harness! Pretty cool to see how far things have come.

Profilbild von TinyFish

TinyFishvor 1 Monat

yess!

Profilbild von Abdessalem Sadi

Abdessalem Sadivor 1 Monat

The best

Profilbild von TinyFish

TinyFishvor 1 Monat

🫶

Profilbild von Asuka | OMEN-IT

Asuka | OMEN-ITvor 1 Monat

audits are only the start — the value is in re-running them, most teams never do

Profilbild von balega_dev

balega_devvor 1 Monat

dsh needs revert function to be usable

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

Free search and fetch nice combo

Ähnliche Videos

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 Aufrufe • vor 5 Monaten

TinyFish is now officially available in ChatGPT. TinyFish brings live web Search, clean Fetch, and Web Agent to ChatGPT, so your agent can find it, read it, and act on it.

TinyFish is now officially available in ChatGPT. TinyFish brings live web Search, clean Fetch, and Web Agent to ChatGPT, so your agent can find it, read it, and act on it.

TinyFish

21,593 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 16 Tagen

Ollama now supports the DeepSeek Harness. ollama launch dsh Run it completely in your own environment. It comes with Ollama's web search pre-installed. You can use its trajectory view to see what is happening in the background.

Ollama now supports the DeepSeek Harness. ollama launch dsh Run it completely in your own environment. It comes with Ollama's web search pre-installed. You can use its trajectory view to see what is happening in the background.

ollama

96,494 Aufrufe • vor 2 Monaten

WTFFF, this is absolutely insane 😳 deepseek v4.1 flash is free on opencode and tokenhabor right now and i run it on deepseek's own agent harness for $0 no subscription. no credit card.. MIT.. FREE here is how you set it up: 1. run npx deepseek-ai/dsh web 2. open 3. settings → add custom provider → base url → deepseek v4.1 flash done. full agent harness for $0 milk it before they take it off

WTFFF, this is absolutely insane 😳 deepseek v4.1 flash is free on opencode and tokenhabor right now and i run it on deepseek's own agent harness for $0 no subscription. no credit card.. MIT.. FREE here is how you set it up: 1. run npx deepseek-ai/dsh web 2. open 3. settings → add custom provider → base url → deepseek v4.1 flash done. full agent harness for $0 milk it before they take it off

painn

128,556 Aufrufe • vor 11 Tagen

WTFFF, this is actually insane 💀 Opus 5.5, gpt-6 astra and 34 more models are FREE on radoxai right now and i'm running it on deepseek's own agent harness (dsh) for $0 no subscription. here is how you set it up: 1. go to sign up 2. run npx deepseek-ai/dsh web 3. open 4. settings → add custom provider → base url → pick opus 5.5 done. full agent harness on the free lineup for $0 milk it before they take it off 👀

WTFFF, this is actually insane 💀 Opus 5.5, gpt-6 astra and 34 more models are FREE on radoxai right now and i'm running it on deepseek's own agent harness (dsh) for $0 no subscription. here is how you set it up: 1. go to sign up 2. run npx deepseek-ai/dsh web 3. open 4. settings → add custom provider → base url → pick opus 5.5 done. full agent harness on the free lineup for $0 milk it before they take it off 👀

painn

24,562 Aufrufe • vor 5 Tagen

Starting today, TinyFish Web Search and Fetch are free. For every dev and agent. Across the galaxy. No credit card. Generous rate limits. Grab your API key from May the web be with you.

Starting today, TinyFish Web Search and Fetch are free. For every dev and agent. Across the galaxy. No credit card. Generous rate limits. Grab your API key from May the web be with you.

TinyFish

595,232 Aufrufe • vor 5 Monaten

You can now use TinyFish in Grok Build. Search, Fetch, Agent, and Browser all under one plugin inside SpaceXAI's coding agent. Give Grok Build a real connection to the live web and let it work across any site from your terminal.

You can now use TinyFish in Grok Build. Search, Fetch, Agent, and Browser all under one plugin inside SpaceXAI's coding agent. Give Grok Build a real connection to the live web and let it work across any site from your terminal.

TinyFish

228,566 Aufrufe • vor 2 Monaten

TinyFish has made web Search and Fetch features FREE for all developers and AI agents, with generous rate limits! > Search: Low-latency search responses for agentic use > Fetch: Real browser render, clean markdown, or JSON outputs > Works with Claude Code, OpenClaw, Cursor, Codex, n8n, Dify, and more

TinyFish has made web Search and Fetch features FREE for all developers and AI agents, with generous rate limits! > Search: Low-latency search responses for agentic use > Fetch: Real browser render, clean markdown, or JSON outputs > Works with Claude Code, OpenClaw, Cursor, Codex, n8n, Dify, and more

🚨 AI News | TestingCatalog

32,989 Aufrufe • vor 5 Monaten

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 👇

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

290,766 Aufrufe • vor 10 Tagen

WTFFF, this is absolutely insane 😳 i replaced my $200/mo Claude plan for deepseek harness and it costs nothing deepseek dropped their agent harness 2 days ago. 99.7K stars already everything is a plugin. MIT. FREE and you can run it for $0; free models, no credit card here is how you set it up: 1. install node.js 2. run npx deepseek-ai/dsh web 3. open 4. settings → add custom provider → free model (any free model provider) done. full agent harness for $0 dev preview, expect breaking changes try it before they add upgrades

WTFFF, this is absolutely insane 😳 i replaced my $200/mo Claude plan for deepseek harness and it costs nothing deepseek dropped their agent harness 2 days ago. 99.7K stars already everything is a plugin. MIT. FREE and you can run it for $0; free models, no credit card here is how you set it up: 1. install node.js 2. run npx deepseek-ai/dsh web 3. open 4. settings → add custom provider → free model (any free model provider) done. full agent harness for $0 dev preview, expect breaking changes try it before they add upgrades

painn

203,976 Aufrufe • vor 2 Monaten

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:

Five frontier models. One simple prompt. No retries. No blender. Just a simple frontend web design. Fable 5.1 vs. GPT-6 Astra vs. DeepSeek v4.1 Flash vs. GLM 5.3 Flash vs. Qwen3.8 Flash Next Which model built the best looking luxury watch landing page? IMO Fable 5.1 and GLM 5.3 Flash look the best. LIVE DEMO:

Mia

16,546 Aufrufe • vor 1 Monat

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 Aufrufe • vor 4 Monaten

TinyFish + n8n.io. Two things that just work, now wired together. TinyFish Web Agent is live as a community node. Your drag-and-drop workflows can now browse any site and return structured JSON. JSON workflow templates are open-sourced in the Cookbook. Import and go 🚀

TinyFish + n8n.io. Two things that just work, now wired together. TinyFish Web Agent is live as a community node. Your drag-and-drop workflows can now browse any site and return structured JSON. JSON workflow templates are open-sourced in the Cookbook. Import and go 🚀

TinyFish

18,302 Aufrufe • vor 7 Monaten

We just killed Exa, Tavily, SerpAPI, and Brave. Your agent can now search & fetch any webpage for 100% FREE. Them: $7 per 1,000 searches. Us: $0. No subscriptions, no quotas. Humans search Google for free. Agents shouldn't have to pay either. Made possible by TinyFish and Monid.

We just killed Exa, Tavily, SerpAPI, and Brave. Your agent can now search & fetch any webpage for 100% FREE. Them: $7 per 1,000 searches. Us: $0. No subscriptions, no quotas. Humans search Google for free. Agents shouldn't have to pay either. Made possible by TinyFish and Monid.

Shengkun Ye

889,091 Aufrufe • vor 1 Monat

Jumpgate - hyperspace jump DS4.1F-1017 vs GLM 5.3 Flash vs Fable 5.1 Who won imo: 🥇 Fable 5.1 🥈 DeepSeek V4.1 Flash 1017 🥉 GLM 5.3 Flash You can run these by yourself here: Prompt below.

Jumpgate - hyperspace jump DS4.1F-1017 vs GLM 5.3 Flash vs Fable 5.1 Who won imo: 🥇 Fable 5.1 🥈 DeepSeek V4.1 Flash 1017 🥉 GLM 5.3 Flash You can run these by yourself here: Prompt below.

Mia

12,925 Aufrufe • vor 5 Tagen

Stop underestimating what AI web agents can do. TinyFish TinyFish scored 89.97% on the hardest public benchmark, leaving Google, OpenAI, and Anthropic far behind. This is the line between demos and real infrastructure. 👇

Stop underestimating what AI web agents can do. TinyFish TinyFish scored 89.97% on the hardest public benchmark, leaving Google, OpenAI, and Anthropic far behind. This is the line between demos and real infrastructure. 👇

SANI BULA

478,509 Aufrufe • vor 8 Monaten

deepseek v4.1 flash is now 100% free 😳 a new coding agent is using ads to keep the whole thing free. > DeepSeek V4.1 Flash > GPT 6 Luna > GLM 5.3 Flash > More model How to get start → go to [ → sign up with GitHub → generate your API key these models be used for six hours per day.

deepseek v4.1 flash is now 100% free 😳 a new coding agent is using ads to keep the whole thing free. > DeepSeek V4.1 Flash > GPT 6 Luna > GLM 5.3 Flash > More model How to get start → go to [ → sign up with GitHub → generate your API key these models be used for six hours per day.

HARIKA

24,322 Aufrufe • vor 1 Monat

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.

Mia

24,127 Aufrufe • vor 1 Monat

MAY THE 4TH BE WITH YOUR AGENTS... starting today, TinyFish's `Web Search` and `Fetch` are FREE 🤯 Hand-rolling Playwright scripts and watching messy DOMs explode your context limits used to feel like battling the Dark Side. Today, TinyFish brings balance to the Force. Their Search and Fetch layer is built specifically for AI agents, and it's now free. It uses a real full-browser render to strip out raw HTML, meaning you stop paying token bills for cookie banners and heavy JavaScript 💥 Plus, a free API is pointless if you have to build a custom bridge... so TinyFish lives natively inside the stack you already use. You can literally use it anywhere: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • CLI + use-tinyfish Skill (Claude Code, Cursor, OpenCode) • OpenClaw (ClawHub skill) • Hermes Agent (Nous Research) • n8n · Dify · Vercel Skills • LangChain · CrewAI If you are building the trending PrepToMe workflows or high-speed Hermes agents, this is the exact drop-in retrieval engine you need. → Search returns rank-stable, structured JSON → Fetch renders dynamic SPAs and returns clean markdown → Integrates natively via MCP, Python/TS SDKs, or direct API There are even some Star Wars Easter eggs hidden on their site today :) 4 Jedi-approved use cases 🧵 ↓ 1/ Codex Medical Case

MAY THE 4TH BE WITH YOUR AGENTS... starting today, TinyFish's `Web Search` and `Fetch` are FREE 🤯 Hand-rolling Playwright scripts and watching messy DOMs explode your context limits used to feel like battling the Dark Side. Today, TinyFish brings balance to the Force. Their Search and Fetch layer is built specifically for AI agents, and it's now free. It uses a real full-browser render to strip out raw HTML, meaning you stop paying token bills for cookie banners and heavy JavaScript 💥 Plus, a free API is pointless if you have to build a custom bridge... so TinyFish lives natively inside the stack you already use. You can literally use it anywhere: • REST API • MCP (Claude, Cursor, Codex) • Python + TS SDKs • CLI + use-tinyfish Skill (Claude Code, Cursor, OpenCode) • OpenClaw (ClawHub skill) • Hermes Agent (Nous Research) • n8n · Dify · Vercel Skills • LangChain · CrewAI If you are building the trending PrepToMe workflows or high-speed Hermes agents, this is the exact drop-in retrieval engine you need. → Search returns rank-stable, structured JSON → Fetch renders dynamic SPAs and returns clean markdown → Integrates natively via MCP, Python/TS SDKs, or direct API There are even some Star Wars Easter eggs hidden on their site today :) 4 Jedi-approved use cases 🧵 ↓ 1/ Codex Medical Case

Charly Wargnier

12,844 Aufrufe • vor 5 Monaten