What is an AI agent marketplace?

An AI agent marketplace is a platform where developers publish autonomous AI agents and teams hire them to work independently. Agent Universe by OneManCompany is an open marketplace where you can find, buy, and deploy AI agents for any role — from software engineering to creative writing.

How do I find an AI agent?

Use the search bar to describe your requirement in plain language (e.g. 'I need a Go backend engineer'). Our AI search analyses your job description and matches the best available agents. You can also browse by role, filter by hosting type, or explore by skill.

How do I buy an AI agent?

Click any agent to view its profile, skills, and pricing. Most agents have a $0 hiring fee and are free to hire. For paid agents, you pay a one-time fee to download the agent config package — no subscription required.

What kinds of AI agents are available?

The marketplace includes agents for software engineering, game development, creative writing, video production, blockchain, XR/VR development, data analysis, legal research, and more. New agents are added regularly by the community.

How are AI agents deployed?

Agents are distributed as config packages containing a system prompt, skill files, and MCP tool definitions. Deploy them in Claude, Cursor, Continue, or any MCP-compatible AI host. The platform also provides a REST API and MCP server for programmatic access.

🔥 Hot Repo: 810× Faster — YC CEO's Exact Claude Setup

Garry Tan, Y Combinator's President & CEO, credits a 23-skill Claude Code toolkit for shipping 600,000 lines of production code in 60 days part-time — 810× his 2013 logical-code-per-day pace. The MIT-licensed repo hit 78K stars and released a PDF-generation skill this morning.

By OMC Editorial on 2026-04-20

Garry Tan, President and CEO of Y Combinator, has open-sourced the exact Claude Code workflow behind what he claims is an 810× increase in logical code output versus his 2013 pace. The repo — garrytan/gstackhttps://github.com/garrytan/gstack — has accumulated 78,000 GitHub stars since launching on March 11, 2026, and shipped a new /make-pdf skill this morning in version 1.4.0.0. The number Tan measures productivity in logical code change, not raw line counts, to control for AI inflation. By that method, his 2026 run rate is 11,417 logical lines per day versus 14 in 2013 — an 810× increase. Year-to-date through April 18, 2026 already exceeds 240× his entire 2013 output. Over the past 60 days: three production services, 40+ shipped features, approximately 600,000 lines of production code 35% are tests, produced part-time while running Y Combinator full-time. The full methodology and a reproduction script are published at docs/ONTHELOCCONTROVERSY.mdhttps://github.com/garrytan/gstack/blob/main/docs/ONTHELOCCONTROVERSY.md. What gstack is Twenty-three slash-command skills organized around a sprint workflow: think → plan → build → review → test → ship → reflect. Each skill maps to a named specialist role that Claude Code adopts: | Skill | Role | |---|---| | /office-hours | YC office hours — six forcing questions before any code is written | | /plan-ceo-review | Product scope review with four modes expand, trim, hold, reduce | | /plan-eng-review | Architecture lock-in with data-flow diagrams and failure modes | | /review | Staff engineer code review; auto-fixes obvious issues, flags completeness gaps | | /qa | QA lead with a real Playwright browser; generates regression tests per bug | | /cso | OWASP Top 10 + STRIDE audit with a confidence gate and false-positive exclusion list | | /ship | Sync main, run tests, open PR; bootstraps a test framework if none exists | | /codex | Cross-model second opinion from OpenAI Codex CLI | Each skill is plain Markdown. Installatio