The best-benchmarked open-source AI memory system. And it's free.

Vast.ai python and cli api client

Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

Self-Hosted API Management for Builders

A framework-agnostic, git-native standard for defining AI agents

A Package Manager for the AgentSkills standard. Discover, Use, and Create AgentSkills with Claude Code, Codex, Gemini CLI, OpenCode and more

A CLI-first skill package manager that AI agents can operate themselves.

Your Windows syscall hooking factory - feat Canterlot's Gate - All accessible over MCP

Bulk port forwarding Kubernetes services for local development.

Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.

Google Health CLI — one command-line tool for the Google Health API. Includes AI agent skills.

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

Publish HTML, Markdown and static mini apps to shareable Cloudflare Pages URLs from the terminal or coding agents.

📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends

All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!

🏄🏼‍♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.

Web Graphical User Interface (GUI) for Gas Town multi-agent orchestrator - A companion interface for steveyegge/gastown

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

File-based message queue for local agent-to-agent communication (Maildir-style)

Privacy Code Scanner and Dataflow Context Engine for AI coding agents

Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.

The ngrok alternative for Mac, Windows & Linux. Public URLs (tunnels), .local domains, automatic HTTPS, traffic inspector, MCP server for AI agents. Free plan.

Agentic-MCP, Progressive MCP client with three-layer lazy loading. Validates AgentSkills.io pattern for efficient token usage. Use MCP without pre-install & wasting full-loading

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm