🐙 GitHub

1818 tools

OpenCompass is a comprehensive open-source platform for evaluating large language models. It benchmarks models from OpenAI, Anthropic, Google, Qwen, GLM, DeepSeek and…

★ 4.02,500 savesDetails >

Slime is an open-source LLM training framework from Tsinghua’s THUDM lab, purpose-built for reinforcement-learning scaling — the post-training stage that turns a…

★ 4.02,500 savesDetails >

Vision Agents is Stream's open-source Python framework for building real-time voice and video AI agents, published on GitHub with around 8,200 stars.…

★ 4.02,500 savesDetails >

OpenCommit is a command-line tool that writes your git commit messages with an LLM — in about a second, in the format…

★ 4.02,500 savesDetails >

TileLang is an open-source domain-specific language for writing high-performance GPU and accelerator kernels in Python — the kind of attention, GEMM and…

★ 4.02,500 savesDetails >

imaginAIry is an open-source Python library and command-line tool for generating images and videos with AI, published on GitHub with around 8,200…

★ 4.02,500 savesDetails >

TinyTroupe is a Microsoft open-source library for simulating people with large language models. You define artificial personas — with names, personalities, occupations…

★ 4.02,500 savesDetails >

FreeAskInternet is a free, private and locally running search-and-answer engine: you ask a question, it searches multiple web engines, feeds the combined…

★ 4.02,500 savesDetails >

BertViz is an open-source tool for visualizing attention in transformer language models, published on GitHub with around 8,200 stars. It turns the…

★ 4.02,500 savesDetails >

ODS — the Osmantic Deployment System — turns an ordinary PC, Mac or Linux box into a private AI server. One installer…

★ 4.02,500 savesDetails >

VAR (Visual Autoregressive Modeling) is the research codebase that redefined how autoregressive models generate images — predicting whole resolution scales instead of…

★ 4.02,500 savesDetails >

DataFlow is an open-source data preparation framework from OpenDCAI that uses LLM-based operators to build high-quality training data, published on GitHub with…

★ 4.02,500 savesDetails >