BoxPwnr benchmarks LLM-based autonomous agents on cybersecurity challenges using iterative command execution in a Kali Docker container, supporting 20+ LLM models and 13+ platforms.
claude-memory-compiler automates capturing and compiling Claude Code conversations into a knowledge base, improving AI agent memory management with minimal setup.
claude-shorts uses AI scoring, GPU transcription, and adaptive video reframing to extract viral-ready vertical clips from long videos, optimizing cuts with audio-aware snapping and platform-specific encoding.
CORAL uses git worktree branches combined with symlinked shared state to orchestrate multiple AI coding agents collaborating in real-time. This Python infrastructure supports iterative code improvement through evaluation loops.
Cupid is a feed-forward 3D reconstruction model that jointly estimates camera pose and reconstructs 3D objects from single 2D images, outputting textured 3D meshes and radiance fields in seconds.
CustomTkinterBuilder is a Python RAD GUI builder for CustomTkinter, supporting drag-and-drop design, code export, and themes. Honest about performance limits and project dormancy.
DATAGEN orchestrates eight specialized AI agents using LangGraph to automate data analysis workflows with progressive disclosure and multi-LLM provider support.
DocStrange converts PDFs, DOCX, PPTX, XLSX, images, and URLs into LLM-ready Markdown, JSON, HTML, and CSV. It offers free cloud and private local GPU modes for flexible, privacy-compliant document parsing.
fastapi-guard offers a composable security middleware for FastAPI with per-route decorators, IP filtering, rate limiting, and an optional cloud dashboard for monitoring.
FlowKit automates AI video creation using Google Flow API with a unique reference image system ensuring visual consistency across scenes. It pairs a FastAPI backend with a Chrome extension bridge.
ForensiX combines ML-driven URL classification with browser artifact extraction for forensic analysis of Chrome and Brave data. Docker-based deployment included.
gpt_image_2_skill packages 162 curated image generation prompts as an AI agent skill and CLI, wrapping OpenAI’s image APIs with validation and budget control for natural-language invocation.
HGM implements a Gödel Machine approximation that iteratively rewrites its own code using subtree promise estimates, balancing exploration and exploitation in self-improving AI agents.
OpenClaw Medical Skills offers 869 modular AI agent skills to transform Claude agents into specialized medical research assistants. Explore its architecture, strengths, and installation.
ByteDance’s In-Place TTT enables adaptive transformer inference by updating MLP down-projection weights in-place at test time, supporting long-context reasoning without extra modules.
llm-madness offers a Python-built GPT-style transformer training pipeline with tokenizer training, memory-mapped datasets, and a unique web UI for per-layer attention inspection and loss visualization.
ToddlerBot offers a full Python stack for training, classifying, and deploying multi-skill humanoid locomotion policies using stereo depth data and reinforcement learning.
LangAlpha uses AI agents that write and execute Python to analyze financial data, reducing token waste and enabling persistent, steerable multi-agent research workspaces.
Leo Health Core is a zero-dependency Python CLI for parsing large Apple Health XML and Whoop CSV exports into a unified SQLite DB, using SAX streaming parsing and local file watching for seamless ingestion.
lich-skills offers seven domain-specific AI coding assistant skills with a focus on spec-driven development and scientific debugging to improve reliability.
