AI-coding skills for the CometChat UI Kit — auto-detects your framework (React, Next.js, React Router, Astro, Expo, React Native, Angular, native Android, Flutter, native iOS) and installs the right skills. Works with Claude Code, Cursor, Kiro, Copilot, R
Deterministic OpenCode message compression with per-session saved-character stats and a TUI indicator.
Local-first tests for AGENTS.md and coding-agent instructions.
Full-lifecycle AI-assisted development kit with Test Architect and Whiteport Design Studio embedded. Inspired by BMAD Method and WDS.
Human-driven, AI-accelerated pair programming framework. Orchestrates AI agents with guardrails, parallelization, and shared memory.
Local-first MCP server for agent skills. Validate, lint, diff, and convert skills across Cursor, Claude, Kiro, Windsurf, VS Code, and Amazon Q. Optional cloud sync with ModelBound.
IP2Proxy proxy detection component
A dev-time CLI that reflects your live API for AI coding agents — verify what the server actually does, not what the code assumes.
Personal context layer for AI agents. Your memory, portable across every agent you use.
WebSocket cat
This package is intended for Prisma's internal use.
Model Context Protocol server for Autoza Ireland — query the Irish used-car market (autoza.ie) from any MCP-compatible AI client.
Develocity® combines troubleshooting features with toolchain observability, empowering npm users to accelerate troubleshooting and measure and improve key performance metrics.
Agent memory plugin for OpenCode - persistent memory with semantic search using LanceDB
AI-powered development tool
Local PR-review loop for human ↔ LLM. Run inside any git repo.
Proxy that bridges GitHub Copilot API to Cursor IDE — translates Anthropic format, bridges Responses API for GPT 5.x, and more
MCP server for the Web Resurrect API — resurrect expired domains via AI assistants
MCP server for Run402 — AI-native Postgres databases with REST API, auth, storage, and row-level security. Pay with x402 USDC micropayments.
AI Agents discover, invoke, and settle paid LLMs, APIs, and Skills — starting with Skill Boss. No manual key setup. No prepayment. Pay-per-call via x402 or Agent Card.
Unified multi-protocol server runtime. One core, multiple transports.
Selected dispatchables of Substrate pallets, to be re-exported by txwrappers.
Prebuilt libvips and dependencies for use with sharp on Linux (glibc) x64
OpenCode plugin + provider that routes LLM prompts to agy (Google Antigravity CLI)