Pinned Loading
-
some-claude-skills
some-claude-skills PublicA Claude Code plugin marketplace: atomic skills (scaffold-skill-marketplace, day-in-review, brainstorm, create-skill) and an opt-in multi-agent feature workflow.
HTML 1
-
agents-recap
agents-recap PublicLocal, offline recap and RAG memory of your AI coding sessions. Reads Claude Code, Cursor and VS Code Copilot Chat session state read-only, tells you where you left off, and lets you ask about it l…
Python
-
-
crewai-play
crewai-play PublicA sandbox for building and experimenting with crewAI multi-agent crews. Each crew lives in its own top-level directory with its own pyproject.toml and virtual environment, so they can use different…
-
m5-max-llm-bench
m5-max-llm-bench PublicLLM inference on a Mac Studio M5 Max (40-core GPU, 48 GB): achieved memory bandwidth (≈550 GB/s, ~90% of 614 GB/s theoretical), decode vs bandwidth bound, mac-llm-bench results. Independent researc…
Python
-
terminal-harbor
terminal-harbor PublicA GUI manager for many terminal sessions — built for juggling several shells and AI-agent sessions (e.g. Claude Code) at once. One large focus area with split panes, a sidebar of live thumbnails of…
TypeScript
If the problem persists, check the GitHub status page or contact support.




