Explore
MCP servers and skills: search, filter by where they run, and compare.
bench-scoutDodai0419
Local
MCP servers and skills: search, filter by where they run, and compare.
Find the agent-memory benchmark that fits your system in one offline command.
SkillMITFew starsNo key
Claude Code skill: Claude Opus conducts and judges, GPT-6.1-Sol executes via the Codex CLI. Supervision every 30 min, council-backed decisions, HTML reports, Codex quota statusline.
SkillMIT★ 3Few starsNo key
Claude plans, Codex / OpenCode Go / DeepSeek execute: a quota-aware dispatcher that routes coding tasks to the cheapest capable agent, in isolated git worktrees with hard budgets.
SkillApache-2.0★ 2Few starsNo key
Taste + impeccable in one Claude Code / Codex skill, plus a gate that checks the page in a real browser. 29.2 to 2.2 design flaws a page by impeccable's own detector. MIT.
SkillMIT★ 2Few starsNo key
The most token-efficient and lossless way for multiple AI agents to edit the same file.
SkillMITFew starsNo key
Who stands behind it
