geowifi is a Python OSINT tool querying seven WiFi geolocation databases to map BSSID or SSID to coordinates, outputting JSON or HTML maps with vendor lookup.
GIMP MCP bridges GIMP 3.2 with AI assistants via MCP, offering 56 tool commands and live PNG snapshots for AI-driven iterative image editing workflows.
GIS-MCP is a Python MCP server that exposes geospatial operations as structured tools for LLMs, bridging natural language and GIS workflows without coding.
Graph-R1 trains large language models with reinforcement learning to reason over knowledge graphs, cycling through think-query-retrieve-rethink steps for complex knowledge tasks.
GS-Playground combines 3D Gaussian Splatting rendering with a velocity-impulse physics engine to enable large-scale visual reinforcement learning at up to 10^4 FPS. Preview release with core simulation API and demos.
H4X-Tools is a Python 3.10+ CLI toolkit offering 16 modular OSINT utilities, including a dual-source leak search combining stealer logs and a 3.2B+ credential dataset for actionable breach insights.
Hackingtool-plugin wraps 183 pentesting and OSINT tools behind a Claude Code plugin. It smartly dispatches commands to native Bash, WSL, or Docker containers, outputting clean JSON.
Harvey LAB offers an open-source benchmark for evaluating LLM agents on realistic legal tasks using an all-pass rubric and LLM-as-judge scoring. It includes datasets, adapters, and dashboards.
Hivemind is a PyTorch library enabling decentralized deep learning over the internet using a peer-to-peer Distributed Hash Table (DHT). It supports fault-tolerant training and decentralized parameter averaging without global sync.
AlohaMini is an open-source project combining hardware and Python software to build and teleoperate a mini robotic arm. It covers 3D printing, assembly, and control.
gtm-agents bundles 67 GTM plugins, 92 AI agents, 52 business skills, and 20 workflow orchestrators for Claude Code, saving 15+ hours/week on sales and marketing busywork.
Mini-SGLang is a modular Python reimplementation of the SGLang LLM inference engine with production features like Radix Cache, chunked prefill, overlap scheduling, and tensor parallelism.
NavDP uses a diffusion policy architecture with privileged information to achieve mapless robot navigation across simulated and real environments without real-world training data.
Papermerge is a Python-based open-source document management system for scanned files with OCR and full-text search, using a meta-repo pattern to scale its codebase.
PicoAgents is a Python multi-agent framework built from scratch, offering transparent agent orchestration, LLM provider abstraction, streaming UI, and production-ready benchmarks.
Explore a Python trading bot for Polymarket’s 15-minute BTC markets. It uses a 7-phase modular pipeline, fuses three signals, and features a self-learning weight adjustment engine.
Poppy Humanoid is an open-source 3D-printed humanoid robot controlled via Python and Jupyter Notebooks, designed for research and education in embodied cognition and sensorimotor learning.
red-run orchestrates Claude Code AI agent teams across the full pentest kill chain using persistent teammates and semantic routing. Explore its architecture, strengths, and quickstart.
Explore WeatherBet, a Python trading bot exploiting Polymarket weather markets using multi-source forecasts and self-calibrated fractional Kelly position sizing for risk management.
IntellAgent is a Python framework that stress-tests conversational AI agents by generating structured adversarial dialogues via policy graph decomposition, helping uncover blind spots before production.
