Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONA collection of 120 plain-text DESIGN.md brand design specifications reverse engineered from live production sites, letting AI coding agents generate on-brand UI. Each brand includes real colors, typography, components and guardrails plus a self-contained preview.html.
Ponytail is an AI coding-agent skill/plugin that nudges agents toward minimal, necessary code using a seven-rung decision ladder, plus review/audit commands. It supports Claude Code, Codex, Copilot CLI, Gemini, OpenCode, and many other coding tools via plugin installs or ruleset files.
Open-source library of 388 production-ready AI coding agent skills, plugins, and personas. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and 9 more tools across engineering, marketing, product, compliance, C-level advisory, and research domains.
Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, reducing token usage while preserving key information. Runs locally as a Python/TypeScript library, proxy, MCP server, or agent wrapper for Claude Code, Codex, Copilot, Cursor, and more.
A multi-harness agentic plugin marketplace offering 94 plugins, 202 agents, 183 skills and 105 commands, generated from one Markdown source for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI and GitHub Copilot.
An AI-first engineering toolkit that provides specialized knowledge, workflows, and standards to turn AI coding agents into senior mobile engineers.
MLflow is an open-source AI engineering platform designed for managing the lifecycle of agents, LLMs, and traditional ML models, focusing on observability, evaluation, and deployment.
A community-curated collection of custom agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot, with a searchable website, Learning Hub, and installable plugin marketplace.
A curated library of machine-readable task prompts and Agent Skills for coding agents, focusing on common agent failures like broken setup scripts, vague issues, and tests requiring unavailable services. Includes fixtures with planted defects for validation.
A transparency archive collecting extracted system prompts and guidelines from major AI models and agents, including OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, and others, for public inspection.
FlexiGPT is a local-first, Bring Your Own Key (BYOK) AI workspace designed for power users and teams to create repeatable LLM workflows with private local history.
This open-source collection features AI Agent books, tutorials, and code repositories from GitHub, covering LLM Agent resources, courses, and frameworks. It supports daily automatic Star count updates, sorting by popularity, and provides recommended reading paths for developers and learners.
AgnosticUI Local (v2) is a CLI-based, framework-agnostic UI component library that copies component source, styles and tests directly into your project for React, Vue, Svelte or Lit, with 55 accessible components, CSS custom-property theming and AI prompt playbooks.
A free 21-lesson Microsoft course for beginners to build generative AI applications, covering LLMs, prompt engineering, RAG, agents, fine-tuning, and more, with Python/TypeScript examples.
Caveman is a skill and proxy that compresses the prose of AI coding agents, cutting output tokens by up to 65% and input tokens by about a third. It works with 30+ agents via a simple CLI, offers benchmark data, and includes privacy‑friendly telemetry controls.
Deep Suite is a harness layer for AI coding agents (Claude Code, Codex, Grok) that enforces structured, verifiable development: plan-before-code, independent review, cross-session durability, and knowledge capture via ten composable plugins.
Open-source prompt library for AI chat models, with web directory, CSV/MD data exports, self-hosting, interactive book, kids game, CLI, Claude Code plugin, and MCP server.
A comprehensive open-source guide covering prompt engineering techniques, RAG, AI agents, and LLM optimization. Includes tutorials, research papers, tools, and notebooks for working effectively with large language models.
HermesMade provides six CLI tools addressing common AI user pain points: censorship risk analysis, model quality monitoring, API cost optimization, local LLM deployment, code inspection, and task cost estimation.
Humanizer is a Markdown-based agent skill that rewrites AI-sounding text to read like human writing without changing its meaning. It detects 25 patterns of AI writing, marks them by strength, and produces a rewrite plus critique, while never inventing facts.
