speakeasy-api/gram
Securely scale AI usage across your organization. Control plane for building, securing and monitoring your agents, mcp and skills.
Securely scale AI usage across your organization. Control plane for building, securing and monitoring your agents, mcp and skills.
npx skills add speakeasy-api/gramSecurely scale AI usage across your organization. Control plane for building, securing and monitoring your agents, mcp and skills.
Safe, auditable SSH access to remote Linux servers and Raspberry Pis for AI agents — works with Claude Code, OpenCode, and any agent that supports skills or custom instructions.
BitFun is a desktop-grade Agent runtimeand a ready-to-use suite of desktop Agent applications.with built-in Code Agent 、 Cowork Agent、Computer Use. It has memory, personality, and the ability to evolve over time
Claude Code skill: one-shot join the current machine to https://eng.impo.ai — bundled single-file agent, device-login, optional launchd/systemd. Onboarding companion for cjzeroxaa/tmux-mobile.
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
ex-cog — externalized cognition. Four Claude Code plugins. vasana-system — cross-session pattern memory (forms, not just facts). research-toolkit — self-checking investigation & verification. makers-toolkit — build-discipline & prompt-design. security-toolkit — dangerous-action guardrails.
EU AI Act high-risk classification — Art. 6 depth assessment skill for Claude, grounded in Commission draft Art. 6(5) guidelines (general principles, Annex I, Annex III). AGPL-3.0. Canonical source: oliverschmidtprietz/claude-skills.