Hibiki: Высокоточный синхронный перевод речи в речь
Hibiki: High-Fidelity Simultaneous Speech-to-Speech Translation .
GitHub
GitHub - kyutai-labs/hibiki: Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike…
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H...
MathLib: кроссплатформенная математическая библиотека с поддержкой только заголовков SSE/AVX/NEON
MathLib: Cross-platform header-only SSE/AVX/NEON-accelerated math library .
GitHub
GitHub - NVIDIA-RTX/MathLib: Cross-platform SSE/AVX/NEON-accelerated math library, coming with a common library to be used in HLSL/C++…
Cross-platform SSE/AVX/NEON-accelerated math library, coming with a common library to be used in HLSL/C++ code - NVIDIA-RTX/MathLib
Wetube: легкий клиент YouTube для Android
Wetube: The lightweight YouTube experience client for Android .
GitHub
GitHub - Purehi/wetube_flutter: The lightweight YouTube experience client for android.
The lightweight YouTube experience client for android. - Purehi/wetube_flutter
JetKVM — высокопроизводительный KVM с открытым исходным кодом.
JetKVM is a high-performance, open-source KVM .
GitHub
GitHub - jetkvm/kvm: JetKVM - Control any computer remotely
JetKVM - Control any computer remotely. Contribute to jetkvm/kvm development by creating an account on GitHub.
Deepseek.cpp: вывод ЦП для семейства LLM DeepSeek на чистом C++
Deepseek.cpp: CPU inference for the DeepSeek family of LLMs in pure C++ .
GitHub
GitHub - andrewkchan/deepseek.cpp: CPU inference for the DeepSeek family of large language models in C++
CPU inference for the DeepSeek family of large language models in C++ - andrewkchan/deepseek.cpp
Показать HN: Inferable – создание надежных агентов ИИ с надежным выполнением
Show HN: Inferable – Build Reliable AI Agents with Durable Execution .
GitHub
GitHub - inferablehq/inferable: Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable…
Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution. - inferablehq/inferable
Показать HN: HMPL – настраиваемые шаблоны для JavaScript, ориентированные на сервер
Show HN: HMPL – Server-oriented customizable templating for JavaScript .
GitHub
GitHub - hmpl-language/hmpl: 🐜 Server-oriented customizable templating for JavaScript. Alternative to HTMX and Alpine.js.
🐜 Server-oriented customizable templating for JavaScript. Alternative to HTMX and Alpine.js. - hmpl-language/hmpl
Показать HN: Howm встречает org-dril: инструмент для создания заметок в сочетании с карточками в Emacs
Show HN: Howm meets org-dril: note taking tool combined with flashcards in Emacs .
GitHub
posts/2025-01-22-195006.org at master · artsi0m/posts
These posts will be rendered on the separate website, not tied to github, eventually - artsi0m/posts
IKVM: виртуальная машина Java и преобразователь байт-кода в IL для .NET
IKVM: A Java Virtual Machine and Bytecode-to-IL Converter for .NET .
GitHub
GitHub - ikvmnet/ikvm: A Java Virtual Machine and Bytecode-to-IL Converter for .NET
A Java Virtual Machine and Bytecode-to-IL Converter for .NET - ikvmnet/ikvm
Показать HN: LangGraph и CrewAI в одной фреймворке фреймворков
Show HN: LangGraph and CrewAI in One Framework of Frameworks .
GitHub
GitHub - apsquared/lg-agents: LangGraph agent samples
LangGraph agent samples. Contribute to apsquared/lg-agents development by creating an account on GitHub.
Показать HN: поддержка каталога айсбергов DuckDB для озер данных
Show HN: DuckDB iceberg catalog support for data lakes .
GitHub
duckdb-iceberg/README-ADDENDUM.md at iceberg-catalog · fivetran/duckdb-iceberg
Contribute to fivetran/duckdb-iceberg development by creating an account on GitHub.
Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know.
ArchGW: Open-source, AI-native (edge and LLM) proxy for prompt traffic .
GitHub
GitHub - katanemo/archgw: The smart edge and AI gateway for agents. Arch is a high-performance proxy server that handles the low…
The smart edge and AI gateway for agents. Arch is a high-performance proxy server that handles the low-level work in building agents: like applying guardrails, routing prompts to the right agent, a...
Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know.
Numbat: A typed language with support for physical dimensions and units .
GitHub
GitHub - sharkdp/numbat: A statically typed programming language for scientific computations with first class support for physical…
A statically typed programming language for scientific computations with first class support for physical dimensions and units - sharkdp/numbat