Craft Anything
storytold/craft-anything
An open-source Rust desktop app, CLI and MCP server that studies a website, app or game and has a coding agent such as Claude Code build your own version, then checks it against the original.
ToolAI.io · Canale GitHub
Scopri i nuovi progetti AI open source aggiunti su GitHub, con informazioni sul repository, note di configurazione, licenze e risorse correlate.
Dati del repository pubblico
storytold/craft-anything
An open-source Rust desktop app, CLI and MCP server that studies a website, app or game and has a coding agent such as Claude Code build your own version, then checks it against the original.
google/elephant-goldfish-model
An open-source plugin that has one agent draft a software spec with full project context, then sends it to fresh reviewer agents that have not seen the conversation.
microsoft/agent-framework
An open-source framework for building, orchestrating, and evaluating AI agents across Python and .NET.
mcp-use/mcp-use
A full-stack TypeScript framework for building MCP servers, clients, and interactive MCP apps.
huggingface/smolagents
A lightweight Python library for building agents that use tools and execute code to solve tasks.
openlit/openlit
OpenTelemetry-native observability and evaluation tools for LLM applications and AI infrastructure.
CrewAIInc/crewAI
A Python framework for coordinating role-based AI agents and structured task workflows.
khoj-ai/khoj
A self-hostable personal AI assistant for searching your knowledge and automating research tasks.
typesafe-ai/skills
Official agent skills for designing applications around TypeSafe typed decisions. Development guidance complements the runtime SDKs and API.
anthropics/claude-quickstarts
Anthropic’s reference application collection covers knowledge-backed support, data analysis, browser use and desktop interaction as starting points for development.
anthropics/claude-cookbooks
Anthropic’s collection of Claude development examples covers classification, summarization, retrieval augmentation, tool use, image understanding, and evaluation. It is suitable for learning from specific tasks and adapting the code.
microsoft/playwright
Use a single API to drive Chromium, Firefox, and WebKit for web testing, form interactions, screenshots, and failure replay; it can also serve as the execution foundation for AI browser tasks.
Pagina 1 / 13 · 151 progetti