1broseidon/ketch

Fast, stateless CLI for web search and scrape. Built for AI agents.

What it solves

Researching information across the web, code repositories, and documentation often requires managing multiple disparate APIs, SDKs, and authentication methods. Ketch solves this by providing a unified, stateless command-line interface that abstracts these services into a single, predictable tool.

How it works

Ketch acts as a single-binary research engine. You configure your preferred backends (such as Brave, SearXNG, or GitHub) once, and the tool handles the underlying requests. It supports web search, code searching, and documentation retrieval. For AI agents, it provides structured JSON output and standardized exit codes, allowing for seamless integration into automated workflows without needing to write custom glue code for every provider.

Who it’s for

It is designed for developers and AI agents that need a fast, reliable way to fetch and scrape data from the web or codebases. It is particularly useful for those building agentic workflows who want a consistent interface for research tasks.

Highlights

  • Unified Interface: Collapses web search, code search, and documentation lookups into one binary.
  • Agent-Ready: Features structured --json output, documented exit codes, and a single configuration discovery call.
  • Zero-Config Defaults: Includes a keyless "auto" mode that falls back through multiple providers automatically.
  • Smart Extraction: Automatically converts HTML and PDFs into clean markdown, with built-in support for JS-rendered pages via headless browser fallback.
  • Integrated Bookmarking: Includes a tagging system to track and revisit research sources across sessions.

Related

  • Project
    hatchet-dev/hatchet

    Hatchet is an open‑source orchestration engine that lets you run reliable background tasks, AI‑agent pipelines and durable workflows. It stores all state in PostgreSQL, provides retries, scheduling, DAGs, rate‑limiting, priority queues and a real‑time UI, and offers SDKs for Python, TypeScript, Go and Ruby. You can use it as a managed cloud service or self‑host it via Docker.

  • Project
    dondai44423/donsetch

    A high-performance Rust-based web research tool for AI agents that provides stealthy fetching, keyless search, and crawling without requiring API keys.

  • Project
    yusukebe/ax

    A command-line tool designed for AI agents to fetch, discover, and extract structured data from the web, replacing the need for fragile parsing scripts and raw HTML dumps.

  • Project
    lakeday-org/perch

    Perch is an AI‑powered semantic linting CLI that scans code, asks decision‑model APIs to reason about potential defects, and returns ranked, confidence‑scored issues. It supports custom natural‑language rules, works with multiple model providers, and integrates with CI and assistant tools.

  • Project
    firecrawl/cli

    Firecrawl CLI is a terminal tool that connects to the Firecrawl AI‑powered web‑scraping and search service. It lets you scrape pages (markdown, HTML, JSON, screenshots, etc.), run web searches with highlights, query specialised developer or government indexes, and install “skills” that teach popular AI coding assistants (Claude Code, Cursor, OpenClaw, etc.) how to use Firecrawl automatically. Authentication is interactive or via API key, and you can point the CLI at a self‑hosted Firecrawl instance. Install with `npm i -g firecrawl-cli` and start with `firecrawl <url>` or `firecrawl search "query"`.