47,133 repositories indexed
97–120 of 144 · Most stars
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Composable Elixir library for LLM interactions built on Req and Finch
Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen and Kimi, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.
TranslatedQoder international and China multi-account reverse proxy gateway, a multi-account OpenAI-compatible gateway hub for Qoder's international and China dual regions — COSY-signed inference, stable device fingerprints to avoid risk control, OAuth device authorization for client-free login, daily check-in and Pro benefits, background scheduled task scheduler, web monitoring dashboard, supporting Codex / Claude Code and standard OpenAI clients
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux. Private, and works offline.
A large language model (LLM) plugin for Neovim, provides commands to interact with LLM (like ChatGPT, Copilot, ChatGLM, kimi, deepseek, openrouter and local llms). Support Github models.
Your personal EQ coach. Build social skills and learn to handle conflict through realistic role-play and personalized feedback.
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
Speedrun for pretraining without backpropagation
A curated library of high-quality, professionally crafted prompts for common development tasks. Save time and improve your AI interactions with battle-tested prompt templates. You can install it as an Gemini CLI Extension.
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra.
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.
OpenAI (and DeepSeek, Azure OpenAI, YandexGPT, Ollama, GigaChat, Qwen) API wrapper for Delphi. Use ChatGPT, DALL-E, Whisper and other products.
The repository host gives no description.
Fast fork of llama.cpp designed for Qwen3.8-Flash-Next
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.
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
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.
Fast, cross-platform, real-time token usage tracker and cost monitor for Claude Code / Codex CLI / Antigravity CLI / Qwen Code / Cline / Zoo Code / Kilo Code / GitHub Copilot / OpenCode / Pi Agent / Piebald.
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.