Stars
🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platfor…
Modern, fast and obfuscated VPN protocol
High-performance proxy router for LLM APIs with automatic load balancing, rate limiting, and fail2ban protection
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
AGENTS.md — a simple, open format for guiding coding agents
A fork of Faster-COCO-Eval modified specifically for the AI-TOD dataset
Hybrid Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
Hybrid Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
Библиотека клиентов для взаимодействия с LLM
T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice
Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.
A JupyterLab extension to create custom launcher entries.
run Jupyter browser client commands from a CLI, REST API, or other browser windows
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Inference and training library for high-quality TTS models.
Understanding the algorithm behind findContours from OpenCV based on the paper "Topological structural analysis of digitized binary images by border following."
Phoneme multilingual(Russian-English) voice cloning based on
An Open Source text-to-speech system built by inverting Whisper.