Stars
- All languages
- Assembly
- Astro
- Awk
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Crystal
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- Go
- HTML
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Koka
- Kotlin
- Lua
- MDX
- Markdown
- Mustache
- Nim
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- Odin
- PHP
- PLpgSQL
- Perl
- PostScript
- Protocol Buffer
- Python
- R
- Reason
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Slash
- Solidity
- Svelte
- Swift
- TeX
- TypeScript
- V
- Vim Script
- Vim Snippet
- Vue
- Zig
- hoon
- mupad
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
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 an…
Offline knowledge AI, maps and videos for survival and rebuilding
Speed and samples benchmark: for all types of text to speech (TTS) models on Windows/Linux/Mac.
Use your locally running AI models to assist you in your web browsing
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Official PyTorch inference for Breeze TTS 2
A 4.5M-parameter two-voice English text-to-speech model, trained from scratch
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Guardrails for Pi that steer instead of interrupt: enforces your project rules on every write, holds only hard-to-undo actions (3 per 1,000 calls, measured on real sessions), catches unverified "do…
Inference engine for basal: fast, calibrated typed decisions (choice / yes-no / score) for Polish and English
Write an app once. It runs natively on the web, macOS, iOS, and Linux, and an AI agent can build it, run it, see it, and test it on every one of them.
An open source design system that's fully customizable and agent ready
DeepSeek Harness: Everything is a Plugin.
Orchestrate multiple coding agents from desktop and mobile
Open-weight, Jev-inspired decision model finetuned on top of Qwen3.5 4B
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
[mirror of https://gitlab.com/veloren/veloren] An open world, open source voxel RPG inspired by Dwarf Fortress and Cube World. This repository is a mirror. Please submit all PRs and issues on our G…
Xiaomi Home Integration for Home Assistant
NVR with realtime local object detection for IP cameras
Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.
Incremental rust builds up to 92x faster than cargo/rustc. Backed by Y Combinator (F26).




