* [Clawd on Desk v0.16.0](https://github.com/rullerzhou-afk/clawd-on-desk) – Desktop pet reacting to AI coding agent sessions in real time with animations for thinking, typing, juggling, permission prompts, and sleep.

* [Conduit v1.17.0](https://github.com/tsouth89/toolport) – Local MCP gateway that centralizes and shares authenticated server tool catalogs across AI clients while reducing per-request token overhead via lazy tool discovery.

* [Memorix v1.8.0](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [Skills Hub v0.9.0](https://github.com/qufei1993/skills-hub) – Cross-platform Tauri and React app for installing, organizing, updating, and syncing Agent Skills across multiple AI coding tools’ skills directories.

* [Conduit v1.16.0](https://github.com/tsouth89/toolport) – Local MCP gateway that centralizes and shares authenticated server tool catalogs across AI clients while reducing per-request token overhead via lazy tool discovery.

* [Memorix v1.8.4](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [DBCode v1.36.16](https://github.com/dbcodeio/public) – Modern database client for VS Code, Cursor, and Windsurf with Copilot and MCP integration, SQL IntelliSense, ER diagrams, notebooks, and secure report sharing.

* [Nomadcxx/opencode-cursor v2.5.8](https://github.com/Nomadcxx/opencode-cursor) – Cursor ACP provider plugin that routes Cursor Pro models through an HTTP proxy into OpenCode with OAuth authentication and optional Cursor bridge hooks.

* [mex v0.7.3](https://github.com/mex-memory/mex) – Persistent, navigable project memory for AI coding agents, using a structured markdown scaffold with CLI-driven routing and drift detection.

* [skillreaper v0.7.0](https://github.com/thousandflowers/skillreaper) – Prunes unused AI-agent skills, MCP servers, subagents, hooks, and always-loaded prose from transcript evidence to reduce context bloat.

* [Memorix v1.8.3](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [Memorix v1.8.2](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [DBCode v1.36.15](https://github.com/dbcodeio/public) – Modern database client for VS Code, Cursor, and Windsurf with Copilot and MCP integration, SQL IntelliSense, ER diagrams, notebooks, and secure report sharing.

* [DBCode v1.36.14](https://github.com/dbcodeio/public) – Modern database client for VS Code, Cursor, and Windsurf with Copilot and MCP integration, SQL IntelliSense, ER diagrams, notebooks, and secure report sharing.

* [Memorix v1.8.1](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [DBCode v1.36.13](https://github.com/dbcodeio/public) – Modern database client for VS Code, Cursor, and Windsurf with Copilot and MCP integration, SQL IntelliSense, ER diagrams, notebooks, and secure report sharing.

* [SigMap v8.28.1](https://github.com/manojmallick/sigmap) – Finds relevant files in a codebase and supplies compact function and class signatures to AI models to reduce tokens and improve answers.

* [Memorix v1.7.3](https://github.com/AVIDS2/memorix) – Persistent, shared memory layer for AI coding agents enabling cross-agent context, compression, and reranked retrieval.

* [mex v0.7.2](https://github.com/mex-memory/mex) – Persistent, navigable project memory for AI coding agents, using a structured markdown scaffold with CLI-driven routing and drift detection.

* [Safari MCP v2.16.3](https://github.com/achiya-automation/safari-mcp) – Safari-based MCP server for AI agents that drives the logged-in Safari on macOS with 97 native automation tools and low CPU overhead.

* [skillreaper v0.6.3](https://github.com/thousandflowers/skillreaper) – Prunes unused AI-agent skills, MCP servers, subagents, hooks, and always-loaded prose from transcript evidence to reduce context bloat.