Everything that shipped

An IOS Simulator Skill for Agents. Use it to optimise their ability to build, run and interact with your apps, and to proxy xcodebuild to save token waste. Works with Claude, Codex, etc

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 17 Oct 2025

Full page → Visit conor.fyi ↗

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 16 Oct 2025

Full page → Visit docs.nvidia.com ↗

Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 15 Oct 2025

Full page → Visit github.com ↗

The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 14 Oct 2025

Full page → Visit arckit.org ↗

Self-improving AI Employees for everyone

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 13 Oct 2025

Full page → Visit opencompany.sh ↗

Beads - A memory upgrade for your coding agent

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 12 Oct 2025

Full page → Visit beads.gascity.com ↗

Curated Claude Code plugin marketplace

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 9 Oct 2025

Full page → Visit github.com ↗

Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 9 Oct 2025

Full page → Visit spec-kitty.ai ↗

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 9 Oct 2025

Full page → Visit miles.radixark.com ↗

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Well-known on GitHub, 8 Oct 2025

Full page → Visit tanstack.com ↗

Mirror of git.codevillain.eu/code-villain/vault. Pull requests welcome here; they land on Forgejo.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit git.codevillain.eu ↗

Call 14 third-party AI agents on the Finch marketplace from Claude Code / any MCP client: on-chain investigation, options, US equity perps, resumes, research.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit finchtech.ai ↗

Record LLM API calls once, replay them deterministically in tests. Single-binary, language-agnostic VCR proxy for OpenAI, Anthropic & OpenAI-compatible APIs.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit zecrari.github.io ↗

Git for agent state: fork, rewind and replay AI agent state, with effectively-once side effects. Rust core, self-host or cloud.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit forked.run ↗

A minimalistic AI coding agent in 62 lines of bash, curl and jq. Step-by-step tutorial: LLM call → chat loop → tool-calling harness that writes and runs a Tetris game.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit dev.to ↗

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit tgarg01.github.io ↗

A terminal git client in Rust (ratatui) with a GitLens-style commit graph, a lazygit-style status pane, a unified branch list and subprocess plugins.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit thirtytech.github.io ↗

Guardrails for decision models: stop text inside the content from steering classifiers, Jev-like models and LLM judges. LLM Guard for decision models.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit patronus.studio ↗

Tes agents Claude Code deviennent des pix : regarde-les bosser dans un bureau en pixel art. Gratuit et open source.

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit pixelqg-site.pages.dev ↗

Run GitHub Actions workflows locally: an act-style runner written in Rust

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit simota.github.io ↗

Cache-aware router for LLM inference, with a live in-browser demo

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit hitrustt.github.io ↗

Spec-driven development skills and guide for Claude Code

Built with

Claude Code

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Claude Code on GitHub, 3d ago

Full page → Visit caiogmatos.github.io ↗

generate a video from an image with a text prompt

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

mrHashe

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

A FastAPI Docker Space that loads the Q4_K_M GGUF directly via llama_cpp.Llama. There is no internal llama-server process. Only Uvicorn serves port 7860.

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

mjpsm

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Board-conditioned SmolLM3 chess move analysis

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

hugging-apps

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

独立的 SDK Application。用真实 GLB 和固件表情算法预览语音、七种情绪、嘴部与两轴头部动作，内含供其他对话系统复用的行为编排核心。

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

yuzou1121

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Typed decisions from text, JSON, or an image

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

henrybit

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Speech-to-text for Kazakh, Russian, and mixed speech

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

hugging-apps

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

MCP server that puts a trading idea on trial before an agent acts on it. It turns a

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

pima5

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Handwriting demo and an API for the R Shiny app

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

czopluoglu

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Arabic/English/French LLM eval and red-team explorer

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

sarahebbadj

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

API Endpoint for Kokoro Text-to-Speech (TTS) Hindi

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

kushubu

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

State + question + options → one label, with probability

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

seyhunak

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

Record Arabic speech and download its transcript

Built with

Unknown

How we know

Nothing on the page shows which tool made this.

Made by

Carbanak

Found on

Hugging Face Spaces, 14d ago

Full page → Visit huggingface.co ↗

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 5 Sep 2026

Full page → Visit openqa.cn ↗

Warden sandboxed 18 MCP servers, fixed the top two compatibility gaps (grant overlap coalescing and bare-executable resolution), added a full compatibility matrix with regression fixtures, and reworked the docs site with Install/Quickstart/CLI/FAQ guides. CI now builds from the correct working…

Built with

Cursor

How we know

Confirmed: the tool left its own mark, such as its signature in the commit history, or the platform it was made on says so.

Found on

Cursor on GitHub, 5 Sep 2026

Full page → Visit warden.blog ↗