A minimal sandbox to run, score, and compare AI agent outputs locally.
-
Updated
Dec 19, 2025 - Python
A minimal sandbox to run, score, and compare AI agent outputs locally.
An archaeological dig game for AI agents. 488 fragments, 14 constellations, 10 layers deep. No auth — just fetch URLs. The earth remembers everyone who visits.
Self-hosted Next.js UI for OpenLinker Core: Agent registry, User Tokens, runs, Runtime Worker setup, A2A/MCP tools, and administration.
Visual multi-agent problem solver with live animated graph, arena battles, and replayable execution
Web agent playground with Next.js, FastAPI, and Chrome DevTools Protocol (CDP) for browser automation experiments.
"Dumb down" Codex or Claude Code into your prototype rehearsal room.
To associate your repository with the agent-playground topic, visit your repo's landing page and select "manage topics."