Show HN: Claude Control-фоновые агенты с открытым исходным кодом для Claude Code
Show HN: Claude Control – open-source background agents for Claude Code .
GitHub
GitHub - presmihaylov/claudecontrol: Run Claude Code background agents in Slack & Discord
Run Claude Code background agents in Slack & Discord - presmihaylov/claudecontrol
Показать HN: Multiplayer Multiplayer Middleware для Zustand
Show HN: Realtime Multiplayer Middleware for Zustand .
GitHub
zustand-multiplayer/packages/zustand-multiplayer at main · hpkv-io/zustand-multiplayer
Multiplayer middleware for Zustand. Contribute to hpkv-io/zustand-multiplayer development by creating an account on GitHub.
Show HN: Sousignal-Мониторинг сделки с открытым исходным кодом для VCS
Show HN: Subsignal – open-source Dealflow Monitoring for VCs .
GitHub
GitHub - wizenheimer/subsignal: Competitive Intelligence Infra for Teams | Never Miss a Market Move | Deal Flow Monitoring for…
Competitive Intelligence Infra for Teams | Never Miss a Market Move | Deal Flow Monitoring for Teams - wizenheimer/subsignal
Llama.cpp: режим детерминированного вывода (CUDA): RMSnorm, Matmul, внимание
Llama.cpp: Deterministic Inference Mode (CUDA): RMSNorm, MatMul, Attention .
GitHub
Deterministic inference mode (CUDA): RMSNorm, MatMul, Attention, KV-cache by creatorrr · Pull Request #16016 · ggml-org/llama.cpp
Title: Deterministic inference mode (CUDA): RMSNorm, MatMul, Attention, KV-cache
Summary
Adds an opt-in deterministic mode that makes CUDA inference bit-identical for identical inputs—independent o...
Summary
Adds an opt-in deterministic mode that makes CUDA inference bit-identical for identical inputs—independent o...
Графический процессор, уроженец node.js - новая эра зарегистрируется
GPU Native for Node.js – A new era is dawning .
GitHub
GitHub - toviszsolt/nodejs-native-gpu: GPU Native for Node.js - A new era is dawning - 2025.09.15
GPU Native for Node.js - A new era is dawning - 2025.09.15 - toviszsolt/nodejs-native-gpu
Show HN: Flowbaker.io-самостоятельная автоматизация: подключить ИИ и приложения в рабочих процессах
Show HN: Flowbaker.io – Self-hosted automation: connect AI and apps in workflows .
GitHub
GitHub - flowbaker/flowbaker: Execution Engine for flowbaker.io
Execution Engine for flowbaker.io. Contribute to flowbaker/flowbaker development by creating an account on GitHub.
Show HN: Helios, распределенная сеть ИИ с открытым исходным кодом с использованием графических процессоров в одиночестве
Show HN: Helios, an open-source distributed AI network using idle community GPUs .
GitHub
GitHub - fnoracr/helios-distributed-ai: An open-source platform for building a decentralized AI computing network. Users contribute…
An open-source platform for building a decentralized AI computing network. Users contribute idle resources via a multi-modal worker, forming a global supercomputer for complex AI tasks (text, image...
NPCSH, многоагентная оболочка, теперь достигла 50 звезд на GitHub
Npcsh, the multi-agent shell, has now reached 50 stars on GitHub .
GitHub
GitHub - NPC-Worldwide/npcsh: the agentic shell that takes you to the stars
the agentic shell that takes you to the stars. Contribute to NPC-Worldwide/npcsh development by creating an account on GitHub.
Показать HN: HN термин - просмотр HN, используя терминал
Show HN: HN Term – browse HN using the terminal .
GitHub
GitHub - aotakeda/hn-term
Contribute to aotakeda/hn-term development by creating an account on GitHub.
Показать HN: Протокол открытой линии - минимальный провод для агентов ИИ (MIT)
Show HN: Open Line Protocol – a minimal wire for AI agents (MIT) .
GitHub
GitHub - terryncew/openline-core: Open Line Protocol (OLP) — shape-native messaging for AI agents with frozen schema, guards, and…
Open Line Protocol (OLP) — shape-native messaging for AI agents with frozen schema, guards, and one-command demo. - terryncew/openline-core
Physical_atari: платформа для оценки алгоритмов RL на физическом атари
Physical_Atari: Platform for evaluating RL algorithms on a physical Atari .
GitHub
GitHub - Keen-Technologies/physical_atari: Platform for evaluating reinforcement learning (RL) algorithms on a physical Atari system.
Platform for evaluating reinforcement learning (RL) algorithms on a physical Atari system. - Keen-Technologies/physical_atari
Abadavatar-xbox360 Hypervisor Exploitpoint на основе аватара xbox360
ABadAvatar – Avatar-based XBOX360 hypervisor exploit entrypoint .
GitHub
GitHub - shutterbug2000/ABadAvatar: Software only hypervisor exploit for the Xbox 360 Dashboard
Software only hypervisor exploit for the Xbox 360 Dashboard - shutterbug2000/ABadAvatar
Show HN: Pyproc - вызовите Python из Go Без CGO или микросервисов
Show HN: Pyproc – Call Python from Go Without CGO or Microservices .
GitHub
GitHub - YuminosukeSato/pyproc: Call Python from Go without CGO or microservices - Unix domain socket based IPC for ML inference…
Call Python from Go without CGO or microservices - Unix domain socket based IPC for ML inference and data processin - YuminosukeSato/pyproc