A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
71,235 visible repositories in the index
481–504 of 739 · Most stars
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Unmanned Surface Vehicle simulation on Gazebo with water current and winds
The 2012 Forza Horizon, native on Windows and Linux, and online again: Horizon World, leaderboards and Rivals on a public server you can also self-host. Bring your own copy.
Forward RSS feeds to your email address, community maintained
MQTT-PWN intends to be a one-stop-shop for IoT Broker penetration-testing and security assessment operations.
Reusable GitHub Actions source builds for jhaizhou-ops/d2r-mobile. Bring your own prepared game archive.
Your AirPods are a mouse: AirPods 3 head tracking on Linux, and the first public documentation of Apple RemoteHID (HID over AACP)
Real-time generative rendering for interactive worlds, from any visual reference.
TranslatedOne zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | Zero-dependency CLI: manages all MCP tools and skills, and tool discovery saves 99.2% of tokens.
Implementation for PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020)
TranslatedOpen-source vertical micro-drama distribution platform (drama CMS + H5 + App). Short drama system / short drama distribution / short drama source code fully open, aimed at taking short dramas overseas. Also provides full-chain services for taking short dramas overseas: payment collection channels / short drama production / custom system development / ad placement. Inquiries welcome.
Trending open projects that reverse engineered apps, games, consoles, protocols and devices, plus the tools they used. Star trends refreshed daily.
Play your own Nintendo Switch games on an Apple TV 4K: a fork of nxnative with a tvOS build and TVPort, a Mac app that builds a game you own into an Apple TV app and installs it.
News reader with tags, scoring, and LLM
Upload once to create multiple, relative PRs. Productivity-focused git tools with patch revision tracking, rebase detection and more. Uses python and git plumbing commands.
Hyperparameter optimization and feature selection for scikit-learn using evolutionary algorithms. A modern alternative to GridSearchCV and RandomizedSearchCV.
A Claude Code skill that designs a brand identity as one system: logo, typography and colour palette built together from one brief, measured, compared as identity cards, and delivered as a brand guidelines kit.
An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.
Predicting price trends in cryptomarkets using an lstm-RNN for the use of a trading bot
Python package facilitating the use of Bayesian Deep Learning methods with Variational Inference for PyTorch
Evidence-based DSM ransomware recovery: preservation, RAM key recovery, copy decryption, and GitLab validation.
DC3 Malware Configuration Parser (DC3-MWCP) is a framework for parsing configuration information from malware. The information extracted from malware includes items such as addresses, passwords, filenames, and mutex names.
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence