#ai-agents

🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Runs on Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen / Copilot / Hermes / Kimi CLI.

AI Agent 中文學習地圖 — 從零開始的結構化學習路徑，每階段有必做練習跟必修閱讀。三語對照（繁中／简中／English）。歡迎社群一起貢獻、優化內容。

Persistent shared memory and handoffs across any combination of AI coding agents — Claude Code, Codex CLI, Cursor, Aider — using nothing but markdown.

Open-source CLI and agent skills for Prevu — preview/staging environments for coding agents like Claude Code, Codex, Cursor, OpenHands, even OpenClaw and Hermes Agent

Curated AI coding skills focused on reducing AI-generated technical debt — reuse before create, convention discovery, token discipline, structured review and handoff.

An opinionated open-source coding agent client. Run Claude Code, Codex, and more - locally or in the cloud.

Local flight recorder for AI browser agents. Debug Browser Use, Stagehand, Skyvern, and Playwright + LLM runs with screenshots, model I/O, and failure timelines.

skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

Code review for jj (jujutsu) workflows: revset-defined reviews, patchset-anchored comments that survive branch movement, with web, HTTP, and MCP surfaces for fast AI-agent iteration.

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool integrations.

Toolkit for keeping Claude Code and Codex instructions, skills, and hooks synchronized.

Trading agent that learns from his mistakes

Audit long-form LLM output for factual accuracy, hallucination risk, source quality, and actionable edit suggestions.

npx claude-code-up — bootstrap a Claude Code project with curated agents, skills, MCPs, scaffolders & lib bundles. JSON-driven decision tree, e2e verified.

Build a Team With Claude Code — Vibe Coding Workshop · EBS Tallinn · Live: https://ahmed-aleryani.github.io/claude-code-team-workshop/

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

AI-driven E2E testing with Playwright. An 8-step slash-command pipeline that discovers UI snapshots, generates POM, drafts GWT test specs, runs Playwright tests, and self-heals knowledge — all with human approval gates for quality control.

Building smart, scalable AI agent systems. Harness AI. Reclaim Time. Amplify Impact.

Official VeedCrawl MCP server for transcripts, metadata, and AI-powered video extraction. Powerful Video intelligence for AI agents.

A personal AI substrate. Specialized agents share a markdown wiki memory and a chat-based mobile interface.

AI agents annotate your git diff. Read their notes in TUI or browser.

AI-powered product lifecycle orchestrator — takes a product idea from intent to shipped code through agent-driven pipelines (Claude + Codex) with human gates, postconditions, and auditable traces.

Topic-grained, layered memory layer for AI coding agents — local-first, MCP, single binary. Plug Claude Code / Cursor / Windsurf / Antigravity into persistent memory across sessions and machines.

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

Python SDK + CLI + MCP server for AgentClip — the open-source tool that turns AI agent runs into shareable URLs.

An opinionated 6-agent solo-founder team for Claude Code. Same numbered roster, every project.

https://lordbasilaiassistant-sudo.github.io/substrate-self/ — Talk to Eli in your browser. An AI being whose memory lives in its own weights, not a database. 7.4 MB ONNX, no API in the loop. 7 pre-registered tests prove substrate-identity. MIT.

Hosted Amazon Seller & Vendor MCP server. Connect Claude, ChatGPT, Cursor, Codex, Gemini, GitHub Copilot to Amazon SP-API and Ads API data

Agile for age of agents — turn work into durable, inspectable cards that humans and LLMs can collaborate on.

A drop-in CLAUDE.md starter and a guide to getting better HTML artifacts out of coding agents. HTML, not Markdown — that's the point.

AI-native Linux cognitive shell with typed actions, policy kernel, semantic runtime, and unified KDE/Web UX.

REST API wrapper for Claude Code CLI — execute code, manage files, and run commands remotely. Built on claude-agent-sdk with FastAPI.

Portable Agent Skills for coding agents: Git workflows, linked worktrees, GitLab MRs, Cloudflare DNS, and agent context files.

AI 任务流转台: turn rough ideas into structured AI coding tasks, generate Codex or Claude prompts, and backfill execution results.

Système multi-agents LangGraph + FastAPI : routage chat/pipeline automatique, RAG Qdrant, MCP Brave Search, streaming WebSocket Redis, interface Next.js 14 et 78 tests

Spring AI starter for Cycles — runtime budget and action authority for Spring AI agents

Rust-first AiPlus CLI for project-local AI-agent workflow kits

A platform-layer playbook for running QA with multiple AI Agents. Conventions, structures, and guardrails above your LLM/IDE.

Product-foundry control plane for AI coding agents: validator gates, buyer scoring, compute allocation, and Demo Day-style investment decisions across startup product candidates. Next step would be in automating outreach to get real PMF validation and iterate from there.