Softaworks Agent Toolkit offers 40+ modular AI skills and plugins for coding agents like Claude Code, enabling composable AI workflows via a plugin marketplace. Here’s how it works.
Sherlock is a Python CLI tool that checks username availability across 400+ social networks using a modular JSON-driven detection system. Practical, extensible, and flexible.
This repo automates Matplotlib cheat sheet generation by programmatically creating figures with Python and compiling polished PDFs using xelatex, offering a reproducible documentation workflow.
cfpsec is a Python CLI tool that fetches Call For Papers data from cfptime.org with security-focused hardening like ANSI escape sanitization and CSV formula injection protection.
changedetection.io is a Python-based web monitoring tool that detects page content changes with AI filtering, supports HTTP and Playwright fetchers, and sends notifications via Discord, Slack, Telegram, and webhooks.
daymade/claude-code-skills offers a robust plugin marketplace with 51 pre-built Claude Code skills and a hardened skill-creator fork featuring security scanning and expanded validation.
TheWhisper breaks Whisper’s 30s fixed chunk limit by supporting flexible chunk sizes for streaming speech-to-text. It provides optimized CoreML and CUDA engines for Apple Silicon and NVIDIA GPUs.
google/agents-cli enhances coding assistants with skills for building, evaluating, and deploying AI agents on Google Cloud’s ADK. It offers a modular CLI workflow covering agent scaffolding to observability.
comfyui-custom-node-skills equips Claude Code with 9 skills to master ComfyUI custom node development, covering full lifecycle with trigger-based loading and verified source alignment.
Kiln implements a 7-step multi-agent AI pipeline entirely through markdown files and Claude Code’s native primitives, avoiding any runtime or package dependencies.
obsidian-second-brain rewrites Obsidian vault pages autonomously using Claude Code agents, detecting contradictions and running scheduled maintenance for a self-healing AI knowledge base.
Genie Sim 3.0 is an open-source platform combining 3D Gaussian Splatting and LLM-driven scene generation for embodied AI simulation, offering large-scale synthetic data and low sim-to-real discrepancy.
A curated directory catalogs over 80 terminal-native AI coding agents and harnesses, highlighting open-source projects, platform agents, and emerging architectural patterns in the CLI AI agent space.
MedRAX uses GPT-4o to dynamically route medical queries across multiple AI models for chest X-ray interpretation. It offers modular, tool-agnostic orchestration with a Gradio interface.
Octopoda-OS is a Python library providing persistent memory, loop detection, and audit trails for AI agents. It supports SQLite/PostgreSQL, zero-config runtime, and cloud sync.
secrets-patterns-db offers over 1600 regex patterns for detecting secrets in code, doubling coverage compared to TruffleHog and vastly outpacing Gitleaks. It enhances AppSec scanning with tested, categorized regexes.
SkillClaw is a Python framework enabling flexible AI agent orchestration across OpenAI-compatible and AWS Bedrock APIs, focusing on modularity and provider-agnostic design.
4DGen extends Stable Video Diffusion to generate geometry-consistent multi-view RGB-D videos from single RGB-D inputs using pointmap latents. Trained on multi-view robotic datasets, it enables robot pose extraction from generated videos.
Action100M provides a hierarchical Tree-of-Captions annotation for 100M video segments, enabling multi-scale video understanding with LLM-generated captions. Explore its structure, tech strengths, and how to access the data.
agentic-stack provides a harness-agnostic shared memory layer for AI coding agents, enabling seamless context persistence and migration across tools like Claude Code and Cursor.
