TinyFish AI Releases Full Web Infrastructure Platform for AI Agents: Search, Fetch, Browser, and Agent Under One API Key

AI brokers wrestle 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 web site. 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 entire 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: Web Agent, Web Search, Web Browser, and Web Fetch.

What TinyFish is Shipping

Here is what every product does:

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

The Token Problem in Agent Pipelines

One of the constant efficiency issues in agent pipelines is context window air pollution. When an AI agent makes use of a regular net fetch instrument, it sometimes pulls the complete web page — together with hundreds 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 firm’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.

Beyond token rely, there may be an architectural distinction value understanding: MCP operations return output immediately 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 native Unix pipes and redirects — one thing that’s not attainable with sequential MCP round-trips.

On advanced multi-step duties, TinyFish stories 2× larger process completion charges utilizing CLI + Skills in comparison with MCP-based execution.

The CLI and Agent Skill System

TinyFish is transport two developer-facing parts 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 — immediately from the command line.

The Agent Skill is a markdown instruction file (SKILL.md) that teaches AI coding brokers — together with Claude Code, Cursor, Codex, OpenClaw, and OpenCode — tips on how to use the CLI. Install it with:

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

Once put in, the agent learns when and tips on how 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 talent, calls the suitable CLI instructions, and writes structured output to the filesystem — with out the developer writing integration code.

The firm additionally notes that MCP stays supported. The positioning is that MCP is suited for discovery, whereas CLI + Skills 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. This is a significant distinction from some opponents. For instance, Browserbase makes use of Exa to energy its Search endpoint, which means that layer isn’t proprietary. Firecrawl presents search, crawl, and an agent endpoint, however the agent endpoint has reliability points on many duties.

The infrastructure argument isn’t 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. Companies whose search or fetch layer runs on a third-party API wouldn’t have entry to this sign.

There can be a sensible price that groups integrating a number of suppliers encounter. Search finds a web page the fetch layer can’t render. Fetch returns content material the agent can’t parse. Browser periods 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 element boundaries the place these failures happen.

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

Key Metrics

Key Takeaways

• TinyFish strikes from a single net agent to a four-product platform — Web Agent, Web Search, Web Browser, and Web Fetch — all accessible below one API key and one credit score system, eliminating the necessity to handle a number of suppliers.
• The CLI + Agent Skill mixture lets AI coding brokers use the dwell net autonomously — set up as soon as and brokers like Claude Code, Cursor, and Codex routinely know when and tips on how to name every TinyFish endpoint, with no guide integration code.
• CLI-based operations produce 87% fewer tokens per process than MCP, and write output on to the filesystem as a substitute of dumping it into the agent’s context window — protecting context clear throughout multi-step workflows.
• Every layer of the stack — Search, Fetch, Browser, and Agent — is constructed in-house, giving end-to-end indicators when a process succeeds or fails, an information suggestions loop that can not be replicated by assembling third-party APIs.
• TinyFish maintains a single session identification throughout a whole workflow — identical IP, fingerprint, and cookies — whereas separate instruments seem to focus on websites as a number of unrelated purchasers, growing detection threat and failure charges.

Getting Started

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

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

The put up TinyFish AI Releases Full Web Infrastructure Platform for AI Agents: Search, Fetch, Browser, and Agent Under One API Key appeared first on MarkTechPost.