A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
- agent
- evaluation
- llmops
- simulator
104,105 visible repositories in the index
1,105–1,128 of 1,736 · Most stars
A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
Public release of Telepathy, an OSINT toolkit for investigating Telegram chats.
scikit-bio: a community-driven Python library for bioinformatics, providing versatile data structures, algorithms and educational resources.
Linux distribution optimized for audio playback
Brian is a free, open source simulator for spiking neural networks.
qt based music downloader written in python
NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
Full-text multi-table search application for Django. Easy to install and use, with good performance.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
A webui for different audio related Neural Networks
Persistent dict, backed by sqlite3 and pickle, multithread-safe.
[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
Tiny cute emulator plugin for IDA based on unicorn.
Python library for arbitrary-precision floating-point arithmetic
Official PyTorch implementation of BigVGAN (ICLR 2023)
Training a humanoid robot for locomotion using Reinforcement Learning
Fully Open Framework for Democratized Multimodal Training
A Python-based lightweight robot simulator designed for navigation, control, and learning
Download music from Deezer with a nice front end
Multi-objective Gymnasium environments for reinforcement learning
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.