— · Apache-2.0
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
v0.10.2 · no license
Open-source adversary emulation for AI agents and MCP servers.
v2.0.0 · MIT
Analytics tool for MCP (Model Context Protocol) servers and AI agents - tracks tool usage patterns and provides insights
— · Apache-2.0
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
— · MIT
A repository for skills that are essential to my daily work
v0.12.1 · MIT
MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client, with background sessions and structured code review
— · MIT
a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate
— · MIT
yoink is an AI agent that removes complex dependencies by reimplementing only what you need.
— · Apache-2.0
MCP server for JADX-AI Plugin
— · MIT
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
— · MIT
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
v2.4.3 · MIT
Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.
— · Apache-2.0
Local code intelligence MCP server and CLI for AI coding agents
v5.3.7 · Apache-2.0
Automated ADR (Architecture Decision Records) for AI Coding Agents - MCP server with SQL-backed decision repository
v0.1.2 · no license
Build with Claude Code without your brain going numb — a plugin that quizzes you on the code it just wrote and gates the session until you pass.
— · MIT
Simple, modular, and observable Go framework for backend applications.
— · MIT
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
v3.2.3 · Apache-2.0
MCP server that launches Claude Code/Codex sub-agents and routes tasks to Claude Messages or OpenAI-compatible API providers.
v0.1.0 · MIT
Figma to design.md — Convert Figma design tokens into structured design.md for AI-assisted coding (Cursor, Claude Code, Copilot)
v1.33.0 · MIT
Claude Code plugin for structured, AI-driven software development. Orchestrates complex workflows -- from issue assessment to staged implementation to review and merge -- giving developers the speed of full automation with the control of human-in-the-loop checkpoints.
v0.4.1 · MIT
Claude Code execution playbook with 3 pilot modes: cost-first (Haiku), quality-first (Sonnet), ceiling-elevation (Opus). Quantitative escalation gates.
— · MIT
Скилл для ИИ-агентов: находит и убирает следы машинной генерации из русского текста. 38 паттернов, 39 regex-маркеров с реестром доказательств, слепые парные прогоны, файловый слой снятия C2PA/EXIF/XMP. Пакет на PyPI и онлайн-демо | Russian AI-writing humanizer skill, PyPI: humanizer-ru, live demo
v0.1.8 · MIT
Local-first CLI for importing, searching, and exposing AI conversation history to local agents.
v0.12.6 · MIT
Give AI coding agents live React and TanStack DevTools from the terminal. Inspect, optimize, test, and verify a running app.