sonos/tract
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
GitHub repository with 2,942 stars and 260 forks.
Language: Rust
Topics: tensorflow, onnx, neural-networks, artificial-intelligence, rust-library, rust
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
GitHub repository with 2,942 stars and 260 forks.
Language: Rust
Topics: tensorflow, onnx, neural-networks, artificial-intelligence, rust-library, rust
Trending score 0.70, activity score 1.47, stars gained +2, forks gained +0.
2026-06-05: 2,942 stars and 260 forks.
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
GitHub repository with 2,942 stars and 260 forks.
Trending score: 0.70; stars gained: +2; forks gained: +0.
Language: Rust
Topics: tensorflow, onnx, neural-networks, artificial-intelligence, rust-library, rust
An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具,努力让Codex变得更好用更舒服
GitHub repository with 13,835 stars and 857 forks.
Trending score: 5.16; stars gained: +916; forks gained: +44.
Language: Rust
DeepSeek + MiMo coding agent in terminal
GitHub repository with 37,132 stars and 3,195 forks.
Trending score: 4.80; stars gained: +393; forks gained: +32.
Language: Rust
Topics: cli, deepseek, llm, rust, terminal, tui
Lightweight coding agent that runs in your terminal
GitHub repository with 88,860 stars and 13,058 forks.
Trending score: 4.58; stars gained: +326; forks gained: +48.
Language: Rust
Your Personal AI super intelligence. Private, Simple and extremely powerful.
GitHub repository with 30,848 stars and 2,977 forks.
Trending score: 4.37; stars gained: +332; forks gained: +50.
Language: Rust
Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path review and cold-path deletion evidence from real production traffic. Rust-native, sub-second, zero-config framework support.
GitHub repository with 3,085 stars and 94 forks.
Trending score: 4.05; stars gained: +346; forks gained: +16.
Language: Rust
Topics: cli, code-duplication, code-quality, codebase-intelligence, copy-paste-detection, dead-code
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
GitHub repository with 46,568 stars and 4,863 forks.
Trending score: 3.80; stars gained: +152; forks gained: +28.
Language: Rust
Topics: acp, ai, ai-agents, mcp
An Open Source Machine Learning Framework for Everyone
GitHub repository with 195,551 stars and 75,351 forks.
Trending score: 2.54; stars gained: +22; forks gained: -7.
Language: C++
Topics: deep-learning, deep-neural-networks, distributed, machine-learning, ml, neural-network
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
GitHub repository with 42,777 stars and 7,639 forks.
Trending score: 2.37; stars gained: +15; forks gained: +13.
Language: Python
Topics: data-science, deep-learning, deployment, distributed, hyperparameter-optimization, hyperparameter-search
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
GitHub repository with 20,732 stars and 3,961 forks.
Trending score: 1.89; stars gained: +7; forks gained: +3.
Language: C++
Topics: ai-framework, deep-learning, hardware-acceleration, machine-learning, neural-networks, onnx
NVR with realtime local object detection for IP cameras
GitHub repository with 33,538 stars and 3,255 forks.
Trending score: 1.62; stars gained: +50; forks gained: +7.
Language: TypeScript
Topics: rtsp, realtime, tensorflow, google-coral, mqtt, nvr
ncnn is a high-performance neural network inference framework optimized for the mobile platform
GitHub repository with 23,337 stars and 4,435 forks.
Trending score: 1.26; stars gained: +9; forks gained: +0.
Language: C++
Topics: inference, high-preformance, simd, arm-neon, deep-learning, artificial-intelligence
This is a text classification project based on the "Category News" feature of Toutiao. Initially, we used the random forest algorithm, then upgraded to FastText, and finally built a new text classification model using a BERT pre-trained model with an added fully connected layer.There may still contain several bugs—let's work together to fix them.
GitHub repository with 38 stars and 1 forks.
Trending score: 1.04; stars gained: +10; forks gained: +1.
Language: Python
Topics: ai, bert, distilbert, fasttext-python, python, random-forest-classifier