news-please is a Python tool built on Scrapy for crawling and extracting structured news data, supporting Common Crawl archives and multiple storage backends.
OASIS is a Python CLI security auditor using LangGraph-orchestrated LLMs for two-phase scanning and deterministic validation of code vulnerabilities. It balances AI insights with guardrails to reduce false positives.
Omni-Diffusion models text, image, and speech tokens jointly via masked discrete diffusion, enabling any-to-any multimodal generation with a single unified model.
onnxmltools is a Python library for converting machine learning models from various frameworks into the ONNX format, enabling interoperability across runtimes and platforms.
OpenEvolve combines MAP-Elites evolutionary algorithms with LLMs to autonomously discover and optimize code, achieving 2-3x speedups and state-of-the-art results on real hardware.
OpenKB compiles documents into a persistent, interlinked wiki using LLMs and PageIndex’s vectorless retrieval, supporting multi-LLM backends and interactive chat with persisted sessions.
paper2code transforms arxiv papers into Python code with ambiguity auditing and inline citations, prioritizing traceability over completeness in ML implementations.
PEAR predicts expressive 3D human mesh parameters for body, hands, and face simultaneously at 100 FPS using a pixel-aligned architecture based on PyTorch and SMPL-X models.
Polypyus bypasses disassembler function detection using binary-only fuzzy matching to locate functions in raw ARM Thumb2 firmware, improving reverse engineering workflows.
pymobiledevice3 reimplements the entire iOS device communication stack in pure Python, replacing C-based tools. It supports iOS 17+ tunnel transport and offers a CLI and Python API for device management.
QuantDinger unifies AI-assisted research, Python strategy development, backtesting, and live trading in a self-hosted platform with scoped AI agent tokens and strict safety defaults.
Resume Matcher uses LiteLLM to unify six LLM providers for AI-powered resume tailoring, with a FastAPI backend and Next.js frontend. It supports local and cloud deployments with PDF export.
SafestClaw offers a Python CLI tool that simplifies AI model configuration and automates security scanning across projects. It supports cloud and local AI models with zero YAML config editing.
Scalene is a Python profiler using statistical sampling for 10-20% overhead, offering line-level CPU/GPU/memory insights and AI-driven optimization tips via LLMs. Cross-platform with CLI and GUI.
SciBlend is a Python add-on for Blender that imports scientific data formats and maps them to GPU shaders, enabling publication-quality visualizations within Blender’s rendering pipeline.
Scientific Agent Skills extends AI coding agents with 135 domain-specific scientific skills, unifying database queries and multi-step workflows across bioinformatics, chemistry, and clinical research.
SimScale provides a sim-real co-training pipeline for autonomous driving planners, combining synthetic simulation data with real-world data to improve robustness and generalization across multiple planner types.
Snyk Agent Scan is a Python CLI tool detecting 15+ security risks in AI agent MCP servers and skills, using an interactive consent model for safe scanning.
sre-agent is a Python AI tool that automates incident diagnosis by analyzing AWS CloudWatch logs, inspecting GitHub code, and reporting to Slack. It includes a unique evaluation suite for diagnosis quality.
