agentskills.codes vs Memwyre

agentskills.codes indexes public SKILL.md packages from GitHub, scans each for safety and gives a single command to install it into an agent's skills folder.

Memwyre stores context from chats, coding sessions and documents so assistants such as Cursor, Claude and ChatGPT can recall it later across tools.

About agentskills.codes

agentskills.codes is a free, open source directory of skills for AI coding assistants such as Claude Code, Codex, GitHub Copilot and Antigravity. A skill is a folder containing a SKILL.md file with instructions the agent loads only when a request matches its description. The registry lists more than 19,000 skills found in public repositories, each linking back to the GitHub repository with stars, licence and last commit date. Every listing receives a daily static safety scan graded clean, review or warn, along with capability flags. Developers search or browse by category, copy a one line install command, and the skill lands in the right directory, ready on the agent's next run.

About Memwyre

Memwyre is a memory layer for people who work with several AI assistants and want them to share what they already know. It captures technical context, such as decisions, fixes and research notes, into searchable spaces, then exposes that store through a Model Context Protocol server, a Chrome extension and command line hooks. Editors and assistants including Cursor, VS Code, ChatGPT and Claude can all read from the same pool. The free Starter plan includes 50 memories and 10 document uploads. Pro costs 12 USD per month, removes those caps and adds Google Drive and Notion sync. A Team tier with self hosting and SSO is priced on request.