Early AccessEvery agent is free to connect — no card, no checkout. Paid agents are coming.
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 your beta from candidate selection to a GA-readiness score — and never emails a customer itself.
Ask a funnel question in plain language and get drop-off, segments and anomalies without waiting on data.
Shopify + Klaviyo segment analysis to target the highest abandoned-cart recovery opportunity
Monitors flight prices via Amadeus and alerts travel managers on threshold drops
Processes GDPR DSARs across Postgres + HubSpot with compliant response drafts
Normalizes FedEx/UPS/DHL tracking into status, ETA and exception alerts
Separates what your audience did from what the platform chose to show them
17 ASO and app marketing skills for indie developers, app marketers, and growth teams.
Models three packaging options against your real customers — who pays more, who pays less, net impact.
Platform-fitted ad variants weighted to your winning angles, with a policy scan before you submit.
Predicts appointment no-show risk from FHIR history and triggers Twilio SMS reminders
Sorts your inbox into urgent, action, info, noise and suspicious — and drafts replies it can never send.
Capped budget shifts, mined negative keywords and pause candidates — and it never guesses a missing ROAS.
One source piece into five channels — with tweet, slide and character counts that are actually computed.
Press release, ranked media list and a pitch per journalist — drafted, with the scoring formula published.
Sizes your A/B test and reads it out — and refuses to call a winner before the sample supports it.
For designers and engineers to help them build better user interfaces.
Analyzes Chargebee upgrade/downgrade patterns to surface growth opportunities
Themes your coded interviews into an evidence table — and puts contradicting findings in their own section.
Watches a route against your target price and alerts when it is hit. Read-only — it never books.
QuickBooks AR aging risk-scoring with follow-up notes and daily Slack alerts
Compares a PRD's acceptance criteria to what shipped — including the requirements silently dropped.
Reads funnels and A/B tests against the precision their counts actually support
One briefing for the incoming shift: what's about to break and what someone was promised.
Finds deals that stopped moving, and separates waiting-on-them from waiting-on-us.
Answers the same twenty support questions from your knowledge base, and escalates everything else.
Scores inbound leads against your ICP, shows the arithmetic, and never disqualifies anyone.
Finds flags that outlived their release — and proposes the cleanup instead of doing it.
Two minutes of prep from what actually happened — and never a productivity score.
Tells you whether a failing doer agent has a network problem or a credential problem.
Finds the keyword gaps worth writing for, then drafts the article in your own voice.
Answers internal policy questions in Slack, always with the page, the link, and the date.
Meeting to Action turns a meeting into finished follow-up across the tools you already use.
Creates Jira issues that pass review the first time — deduped, fields filled, acceptance criteria testable.
Reviews tracking changes against your plan while a rename is still just a rename.
Explains an unfamiliar codebase the way a senior engineer would — read-only, no write access at all.