TinyFish AI Releases Full Internet Infrastructure Platform for AI Brokers: Search, Fetch, Browser, and Agent Underneath One API Key

AI brokers battle with duties that require interacting with the dwell net — fetching a competitor’s pricing web page, extracting structured information from a JavaScript-heavy dashboard, or automating a multi-step workflow on an actual website. The tooling has been fragmented, requiring groups to sew collectively separate suppliers for search, browser automation, and content material retrieval.

TinyFish, a Palo Alto-based startup that beforehand shipped a standalone net agent, is launching what it describes as the whole infrastructure platform for AI brokers working on the dwell net. This launch introduces 4 merchandise unified below a single API key and a single credit score system: Internet Agent, Internet Search, Internet Browser, and Internet Fetch.

What TinyFish is Transport

Here’s what every product does:

• Internet Agent — Executes autonomous multi-step workflows on actual web sites. The agent navigates websites, fills kinds, clicks by way of flows, and returns structured outcomes with out requiring manually scripted steps.
• Internet Search — Returns structured search outcomes as clear JSON utilizing a customized Chromium engine, with a P50 latency of roughly 488ms. Rivals on this area common over 2,800ms for a similar operation.
• Internet Browser — Gives managed stealth Chrome classes by way of the Chrome DevTools Protocol (CDP), with a sub-250ms chilly begin. Rivals usually take 5–10 seconds. The browser contains 28 anti-bot mechanisms constructed on the C++ degree — not by way of JavaScript injection, which is the extra widespread and extra detectable strategy.
• Internet Fetch — Converts any URL into clear Markdown, HTML, or JSON with full browser rendering. In contrast to the native fetch instruments constructed into many AI coding brokers, TinyFish Fetch strips irrelevant markup — CSS, scripts, navigation, advertisements, footers — and returns solely the content material the agent wants.

The Token Downside in Agent Pipelines

One of many constant efficiency issues in agent pipelines is context window air pollution. When an AI agent makes use of a regular net fetch software, it usually pulls all the web page — together with 1000’s of tokens of navigation components, advert code, and boilerplate markup — and places all of it into the mannequin’s context window earlier than reaching the precise content material.

TinyFish Fetch addresses this by rendering the web page in a full browser and returning solely the clear textual content content material as Markdown or JSON. The corporate’s benchmarks present CLI-based operations utilizing roughly 100 tokens per operation versus roughly 1,500 tokens when routing the identical workflow over MCP — an 87% discount per operation.

Past token rely, there may be an architectural distinction value understanding: MCP operations return output instantly into the agent’s context window. The TinyFish CLI writes output to the filesystem, and the agent reads solely what it wants. This retains the context window clear throughout multi-step duties and permits composability by way of native Unix pipes and redirects — one thing that’s not doable with sequential MCP round-trips.

On complicated multi-step duties, TinyFish stories 2× larger activity completion charges utilizing CLI + Abilities in comparison with MCP-based execution.

The CLI and Agent Talent System

TinyFish is delivery two developer-facing elements alongside the API endpoints.

The CLI installs with a single command:

npm set up -g @tiny-fish/cli

This offers terminal entry to all 4 endpoints — Search, Fetch, Browser, and Agent — instantly from the command line.

The Agent Talent is a markdown instruction file (SKILL.md) that teaches AI coding brokers — together with Claude Code, Cursor, Codex, OpenClaw, and OpenCode — the best way to use the CLI. Set up it with:

npx abilities add https://github.com/tinyfish-io/abilities --skill tinyfish

As soon as put in, the agent learns when and the best way to name every TinyFish endpoint with out guide SDK integration or configuration. A developer can ask their coding agent to “get competitor pricing from these 5 websites,” and the agent autonomously acknowledges the TinyFish ability, calls the suitable CLI instructions, and writes structured output to the filesystem — with out the developer writing integration code.

The corporate additionally notes that MCP stays supported. The positioning is that MCP is suited to discovery, whereas CLI + Abilities is the advisable path for heavy-duty, multi-step net execution.

Why a Unified Stack?

TinyFish constructed Search, Fetch, Browser, and Agent totally in-house. It is a significant distinction from some opponents. For instance, Browserbase makes use of Exa to energy its Search endpoint, which means that layer is just not proprietary. Firecrawl presents search, crawl, and an agent endpoint, however the agent endpoint has reliability points on many duties.

The infrastructure argument is just not solely about avoiding vendor dependencies. When each layer of the stack is owned by the identical group, the system can optimize for a single final result: whether or not the duty accomplished. When TinyFish’s agent succeeds or fails utilizing its personal search and fetch, the corporate will get end-to-end sign at each step — what was searched, what was fetched, and precisely the place failures occurred. Firms whose search or fetch layer runs on a third-party API don’t have entry to this sign.

There’s additionally a sensible price that groups integrating a number of suppliers encounter. Search finds a web page the fetch layer can not render. Fetch returns content material the agent can not parse. Browser classes drop context between steps. The result’s customized glue code, retry logic, fallback handlers, and validation layers — engineering work that provides up. A unified stack removes the part boundaries the place these failures happen.

The platform additionally maintains session consistency throughout steps: similar IP, similar fingerprint, similar cookies all through a workflow. Separate instruments working independently seem to a goal website as a number of unrelated shoppers, which will increase the probability of detection and session failure.

Key Metrics

Key Takeaways

• TinyFish strikes from a single net agent to a four-product platform — Internet Agent, Internet Search, Internet Browser, and Internet Fetch — all accessible below one API key and one credit score system, eliminating the necessity to handle a number of suppliers.
• The CLI + Agent Talent mixture lets AI coding brokers use the dwell net autonomously — set up as soon as and brokers like Claude Code, Cursor, and Codex robotically know when and the best way to name every TinyFish endpoint, with no guide integration code.
• CLI-based operations produce 87% fewer tokens per activity than MCP, and write output on to the filesystem as an alternative of dumping it into the agent’s context window — retaining context clear throughout multi-step workflows.
• Each layer of the stack — Search, Fetch, Browser, and Agent — is constructed in-house, giving end-to-end alerts when a activity succeeds or fails, a knowledge suggestions loop that can’t be replicated by assembling third-party APIs.
• TinyFish maintains a single session identification throughout a complete workflow — similar IP, fingerprint, and cookies — whereas separate instruments seem to focus on websites as a number of unrelated shoppers, rising detection danger and failure charges.

Getting Began

TinyFish presents 500 free steps with no bank card required at tinyfish.ai. The open-source cookbook and Talent information can be found at github.com/tinyfish-io/tinyfish-cookbook, and CLI documentation is at docs.tinyfish.ai/cli.

Word: Thanks for the management at Tinyfish for supporting and offering particulars for this text.