:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
Repository Index
47,133 repositories indexed
625–648 of 837 · Most stars
seamless neovim integration with goose - work with a powerful AI agent without leaving your editor
TranslatedMCP desktop companion for AI agent status, usage tracking, and everyday tools. Anything Universe · Desktop companion and entry point to everyday tools.
TranslatedMeetDo — open-source Meeting-to-Action AI by 筑听 (Zhuting, "build listen") · JKinco Listen. Self-hosted live meetings, local ASR/LLM, structured minutes, DOCX/PDF.
- docker
- fastapi
- funasr
- local-first
TranslatedHire a private AI tutor for anything — it reads how you actually learn and teaches the next lesson just for you. Bloom's 2-Sigma research as a Claude Code skill + self-hostable web app · Chinese-first Socratic AI tutor
- agent-skills
- ai-tutor
- chinese
- claude-code
Open-source DeepWiki alternative — generate comprehensive wiki documentation for any codebase from terminal or browser
- cli
- deepwiki
- documentation
- llm
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
TranslatedA multimodal AI chat assistant that organizes memory through: concurrent multiple LLMs / real-time linear algorithms / automatic AI optimization
Small portable Elliptic-Curve Diffie-Hellman in C
- elliptic-curve-diffie-hellman
- ecdh
- public-key-cryptography
- c
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
- ai-agents
- mathematics
- neuro-symbolic
- reasoning
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
TranslatedOfficial Document Writing Skills | AI official document writing assistant: prevents fabrication, keeps confidentiality, one-click GB/T 9704 formatting, covers 22 types of documents, supports Claude Code / Codex / Cursor
- agent-skills
- ai-writing
- ai-writing-tool
- chinese-writing
Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.
50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.
Vim Plugin For ChatGPT
TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.
- agent-memory
- claude-code
- codex
- context-compression
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.
TranslatedTreat agents as functions, and write ideas as programs. Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
TranslatedLLM teaching material for high school students: based on Karpathy's microgpt, for Google Colab
Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.
- ai-agents
- autonomous-agents
- kali-linux
- llm-agents
TranslatedAccount management center for new-api / sub2api relay stations: balance, API Key, usage, rate multipliers, model price comparison | https://nvcenter.cc
- api-key-management
- api-relay
- claude
- dashboard
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
TranslatedBig Blue Fish desktop pet with local LLM. A Windows AI desktop pet with a built-in 4B local large model. It uses a whale-girl persona that combines weather, tech news and the current application to keep you gentle company through text bubbles. Supports one-click installation and pausing inference when off power.
- ai-companion
- deepseek
- desktop-companion
- desktop-pet