AwesomeRepos
Sign in

Repository Index

82,588 visible repositories in the index

Tags: LLM tools
Tags

A repository shows when it has any selected Tag.

Clear Tags
Filters

Filters

Clear all filters

1–21 of 21 · Most stars

ilysenko / codex-desktop-linux

JavaScript 3.9K 511

Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE (.rpm), Arch (pacman), Nix/NixOS, and AppImage, with Wayland and X11 support.

Prat011 / free-cluely

TypeScript 1.7K 467

Cluely - The invisible desktop assistant that provides real-time insights, answers, and support during meetings, interviews, presentations, and professional conversations.

  • ai-note-taking-app
  • cheating
  • cluely
  • fireflies

jasonxu114514 / opencode2api

Go 1.5K 260

A Go-based OpenCode Zen / Zen Go API proxy with OpenAI & Anthropic API compatibility, key/proxy pooling, automatic routing, and WebUI.

peonist-ai / halogen-flash-server

Shell 1.3K 95

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

  • amd
  • gfx1151
  • gpu-inference
  • hip

gufo-org / gufo

C++ 1.2K 206

The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.

  • amd
  • llm
  • strix-halo
  • gfx1151

Indras-Mirror / Xolotl

C++ 520 65

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

JakeATX / llamAmpere

C++ 380 44

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.

  • ampere
  • consumer-gpu
  • cuda
  • ggml

brian901106 / japanese-tutor-mugi

TypeScript 104 36

TranslatedA mobile web app where the hamster Mugi (むぎ) practices Japanese conversation with you one-on-one. Core idea: the LLM outputs structured replies using a JSON Schema, with the Japanese lines and the Chinese tips in separate fields, and the frontend uses partial JSON parsing to display the reply as it streams in; prompt caching and voice caching are maintained even during long chats. Kanji readings are annotated by the LLM, and any that it misses are filled in by kuromoji on the server side. Corrections are automatically saved into a tips notebook, so you can practice speaking until you have mastered them. For voice, you can choose local VOICEVOX or cloud Google/Azure, and the keys stay only on the local server. Developed in collaboration with Claude Code (Opus 5.5); originally for personal use, it was released as open source with a brand-new git history that contains no personal data or third-party assets. Records of each decision are in docs/decisions/.