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.

Yesterday in AI: 20 June 2026 — Claude Skills Hit 139K Stars While Agents Get 95% Cheaper

Matt Pocock's Claude Code skills framework crosses 139K GitHub stars; a Netflix engineer's open-source token compressor headroom cuts LLM costs by up to 95%; and a new MCP server brings 158-language code intelligence at 99.2% token savings.

By OMC Editorial on 2026-06-21

TL;DR — Matt Pocock's Claude Code skills framework crossed 139K GitHub stars with a v1.0.1 update that enforces engineering discipline without removing developer control; Netflix engineer Tejas Chopra's open-source headroom is cutting LLM agent token costs by up to 95% in production and hit 1 on GitHub trending; and codebase-memory-mcp is a new single-binary MCP server that indexes 158 programming languages into a persistent knowledge graph, claiming a 99.2% token reduction versus file-by-file exploration. --- 1️⃣ Matt Pocock's Claude Code Skills Framework Crosses 139K Stars - What: TypeScript educator Matt Pocock released v1.0.1 of mattpocock/skills, a collection of 21 composable Claude Code skills addressing the top failure modes in AI-assisted engineering: agent misalignment, excessive verbosity, and architectural decay. - Why it matters: Unlike BMAD or Spec-Kit which own the entire process, these skills are a lightweight contract layer — developers stay in control while eliminating the most common Claude Code complaint: technically correct output that misses the actual goal. - Key number: 139K stars and 12K forks; v1.0.1 cuts skill-load token costs 63% through progressive disclosure. The framework ships as 21 plain markdown files. /grill-with-docs front-loads alignment by making Claude ask detailed questions before writing code, then saves shared vocabulary to CONTEXT.md. /tdd enforces a test-first loop on every change. /caveman strips agent verbosity to near-zero when the path is already clear. Version 1.0.1, released June 17, added a formal user-invoked vs. model-invoked taxonomy — a subtle but important distinction that prevents Claude from running skills unsolicited — along with design workflows and shared session state. Pocock has a 60,000-subscriber developer newsletter, which explains why 1,395 stars landed in a single day on June 20. The repo overtook several established AI frameworks by star count within its first month. 📎 mattpocock/skillshttps