A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
132,241 visible repositories in the index
313–336 of 345 · Most stars
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
C++ package retrieval
A dependency-free cross-platform swiss army knife for PDB files.
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.
Hyperparameter optimization and feature selection for scikit-learn using evolutionary algorithms. A modern alternative to GridSearchCV and RandomizedSearchCV.
Claude paints with code: a Claude Code skill for procedural illustration in 83 styles, from ink wash (水墨), watercolour and ukiyo-e to stained glass, Roman mosaic, Art Deco, shadow puppets, pastel UI, sketchbook doodles, spot illustrations, grainy picture books, dreamy hills, sunlit greenery. No image model: numpy + Pillow on a CPU, draw-on GIFs.
Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
Aggregates security advisories from 10 international CERTs daily and provides an AI skill that cross-references alerts against your project's tech stack.
BiliFlow · B 站视频下载、直播录制与本地归档工具,支持批量下载、断点续传、字幕和弹幕。Open-source Bilibili downloader & live recorder with desktop GUI and CLI.
ComfyUI Timeline Studio for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing.
Real-time Ethereum whale tracker with WebSocket transaction streaming, ETH/ERC-20 decoding, and instant Telegram alerts above a configurable USD threshold. Wallet labels, counterparty analysis, smart-money PnL, exchange flows, SQLite storage, CSV/XLSX/JSON export, auto-reconnect, and cross-platform Python support.
Agent skills for Codex and Claude Code that preserve project context, decisions and next steps across AI sessions in plain Markdown.
VisSearch-Bench is a benchmark of 204 human-written tasks that test how well multimodal agents find, organize, and use visual evidence across multiple steps of web search.
Cross-platform, open-source shellbag parser
A cross-platform modding language for GameMaker games. // Moved to Codeberg! https://codeberg.org/katsaii/catspeak-lang
A self-extending AI agent that runs anywhere Termux runs. Writes its own capabilities, remembers across sessions.
Terminal CLI to search and download ROMs, ISOs and Switch games. Interactive Textual UI, cross-platform catalog, resumable downloads.
🔥🔥🔥[NeurIPS 2026] Official Implementation of DGP: Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
Correct GeoJSON geometries that cross the 180th meridian
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
Stoik-Stitch-Creator: Windows Cross-Stitch Pattern Design Tool with Image Conversion and Canvas Cont
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
MERK is an open source, cross-platform, multiple-document interface GUI IRC client for Windows, Linux, and macOS written in Python, PyQt5, and Twisted.
TranslatedOpen-source unified usage dashboard for Claude — track tokens, quota, costs across Claude Code, claude.ai & API in one panel. Suitable for Pro/Max subscribers and developers. https://dyp23yngrtumg.ok.kimi.link