A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
111,821 visible repositories in the index
1,249–1,272 of 1,472 · Most stars
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
A "run" function for asyncio-based apps that does all the boilerplate.
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
A py.test plugin to validate Jupyter notebooks
Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it through and returns the transcript. Self-hosted, open source, no phone numbers or Twilio.
A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.
Community Discovery Library
DDoS attacks over Tor
🎆 A visualization of the CapsNet layers to better understand how it works
Find, verify and organize your game library. Native Windows and Docker, DAT checks, ROM Hub plugins, and optional RomM/Cartridge integration.
An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.
Photoreal Blender scenes from a one-paragraph brief, built by AI agents: image→3D props on fal, scripted layout, lighting, camera and grade.
An extension for Inkscape that makes it easier to draw optical diagrams.
Neural networks toolbox focused on medical image analysis
PaperRead|An Open-Source AI Research Workspace for Reading, Annotating, Analyzing, and Organizing Academic Papers.
Free global SEO/GEO skill for Claude Code, Codex & 10 agent hosts — 18 market portals, 56 stdlib scripts, 672 golden tests, self-update intel loop, monitoring daemon, CI gates. Multilingual GEO, pSEO, CWV, penalty recovery.
Model extraction attacks on Machine-Learning-as-a-Service platforms.
Search and filter videos based on objects that appear in them using convolutional neural networks
TranslatedMulti-market intelligent quantitative workbench (A-shares/Hong Kong stocks/US stocks) — secondary development based on shy3130/tickflow-stock-panel, adding multi-market support for Hong Kong and US stocks. Self-hosted stock screening + monitoring + backtesting. MIT.
AgML is a centralized framework for agricultural machine learning. AgML provides access to public agricultural datasets for common agricultural deep learning tasks, with standard benchmarks and pretrained models, as well the ability to generate synthetic data and annotations.
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
The Cold Disk Quick Response (CDQR) tool is a fast and easy to use forensic artifact parsing tool that works on disk images, mounted drives and extracted artifacts from Windows, Linux, MacOS, and Android devices
End-To-End Memory Network using Tensorflow
Pytest in IPython notebooks.