language

directional-prompting

72

Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions. Works in Claude Code and Codex CLI.

go

Go

90

The Go programming language

plain-writing-skill

HTML

77

A plain-language writing skill for AI agents, with a revision view that shows what changed.

claude-code

Python

80

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

codebase-memory-mcp

C

95

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

brain2qwerty

Python

85

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

scrumboy

Go

77

Self-hosted kanban & project management with shareable boards, voice commands, sticky-notes, multi-language and MCP support

harness

Swift

77

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

self-learning-skills

82

A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.

skills

77

A set of agent skills that help improve different parts of a product, from animations and typography to layout and colors.

claude-tutors

77

Claude tutoring skills that explain clearly and guide practice when needed.

rust

Rust

85

Empowering everyone to build reliable and efficient software.

local-llm

Shell

77

Everything I know about running LLMs locally

langflow

Python

95

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Airpipe

Go

78

Send files to/from the cli easily! no scp

best-humanizer-handbook

58

Best AI Humanizer Handbook A practical guide to making AI-assisted writing clearer, more credible, and more human

transformers

Python

90

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

ECC

JavaScript

95

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

ollama

Go

90

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

langchain

Python

95

The agent engineering platform.

MLX-LoRA-Studio

Swift

77

A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.

gemma-chat

TypeScript

80

Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama

MTPLX

Python

82

3x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

cursed_browser

Swift

58

True AI-Native Browser — a VLM reads the HTML and hallucinates the page.

electron

C++

95

:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS

project-based-learning

Python

95

Curated list of project-based tutorials

beautify-github-readme

Python

82

Design clear, theme-specific GitHub README homepages with SVG titles, real proof, and maintainable Markdown

Taskosaur

TypeScript

80

Open Source Project Management with Conversational AI Task Execution. Built for teams who want conversational workflow management alongside traditional PM features. Self-hostable with modular architecture.

appless

TypeScript

82

What if your phone had no apps

Flowise

TypeScript

90

Build AI Agents, Visually

zep

Python

90

Zep | Examples, Integrations, & More

feeds.fun

Python

72

News reader with tags, scoring, and LLM