Early AccessEvery agent is free to connect — no card, no checkout.
We use essential cookies to keep you signed in. With your consent we also use non-essential cookies for analytics. Read our privacy policy
Filter by Industry (who it's for) and Discipline (what it does). Pick either, or both.
Every agent is scanned and human-reviewed, and your API keys are only sent to the hosts it declares.How it works
FindAgent is a cross-LLM marketplace of focused AI agents. You find an agent, connect it to the AI app you already use — Claude, ChatGPT, Gemini, Cursor, the FindAgent CLI, or any MCP client — and use it where you already work.
Browse across two axes: the Industry an agent serves (who it is for) and the Discipline it embodies (what it does). Pick either or both, then refine by item type, tags, and integrations, or search for what you need.
Open an agent and follow its steps: install it locally with the FindAgent CLI, or, for a hosted agent, add its MCP server URL as a connector to wire it into Claude, ChatGPT, Gemini, Cursor, or any MCP client.
Every agent is scanned and human-reviewed before it is published, and your API keys are only sent to the hosts an agent declares. Declarative agents ship no executable code.
Every industry and discipline
Runs the intake interview one question at a time and freezes the brief.
A transparent 0-100 health score for any public GitHub, GitLab or Bitbucket repo, with the formula behind every finding.
Hooks, proof and CTAs built from real customer quotes as mix-and-match pieces, so one shoot becomes many ad variants.
Turns a fuzzy bug report into a scoped investigation and a planner brief.
Shot beats, continuity kits and generation prompts for every scene. Real proof gets filmed, never faked.
X-ray any page: SEO, accessibility, security, speed, UX, AI-search readiness and the hidden issues nobody checks
Plans an install ad that only claims what the product actually did.
Turns your agent's listing copy into a family-style logo and visual-first screenshots, as PNG. Every word and number comes from you.
Turns approved ad creative into an IntroGen motion-graphics brief. Every claim checked, one production per approval.
Turns your script pack into a costed production plan with work tracks and shoot briefs. Nothing gets spent without your approval.
Keeps a team's written knowledge findable instead of merely large.
Reviews a mobile change with severities that still mean something.
Finds what your change left untested, and the device cases nobody runs.
Turns your landing page into a locked video ad brief, one question at a time. No invented prices, claims or audiences.
Finds the security defects that pass a code review and a green build.
The file-level plan you approve before anyone opens an editor.
Turns your research into a ranked list of ad angles, each scored out of 100 with the math shown and weak claims removed.
The design spec before the screen gets built: states, copy, accessibility.
QA-checks your finished clips and sets up tests that change one thing at a time. No score without a measurement.
Turns a vague mobile feature request into a spec with a real scope boundary.
Ranks competitor ads by how long they stayed live and mines reviews for customer language. Gaps are reported, never guessed.