Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace. Discover projects across categories like LLM, Vision, Audio, and more.
886 projects
soniqo
Apache-2.0 Swift toolkit running speech AI entirely on Apple Silicon via MLX and CoreML — ASR from Qwen3 to Omnilingual's 1,672 languages, plus TTS, diarization, enhancement and a brew-installable CLI, each model its own SPM library.
Finrandojin
MIT-licensed audiobook generator that has an LLM annotate a book into speakers, dialogue and per-line delivery directions, then voices the whole cast with Qwen3-TTS — voice cloning, LoRA training, and M4B or Audacity export.
sgl-project
Apache-2.0 multi-stage serving runtime from the SGLang project for TTS, ASR and omni models — stage-specialized scheduling, transport-aware execution across NCCL/NIXL/Mooncake, and OpenAI-compatible audio endpoints.
Tencent
Tencent Zhuque Lab's Apache-2.0 AI red teaming platform combining AI infra CVE scanning across 100+ components, MCP and Agent Skills scanning, agent workflow assessment and multi-turn jailbreak evaluation.
mayocream
Apache-2.0 Rust desktop app that chains detection, OCR, inpainting and LLM translation into one local-first manga pipeline, with CUDA, ROCm, Metal and Vulkan backends and layered PSD export.
AlexsJones
MIT-licensed Rust TUI that detects your RAM, CPU and GPU, then ranks hundreds of local models by memory fit, speed, quality and context — with MoE-aware sizing and community benchmarks that replace estimates with measured numbers.
vercel-labs
Vercel Labs' Apache-2.0 coding agent written in Zig — a 7.8 MiB Unix-shell-style CLI that also embeds into editors via ACP or into JavaScript hosts as WebAssembly.
pwilkin
A standalone C++/GGML port of Microsoft's TRELLIS.2-4B image-to-3D pipeline — three flow DiTs, mesh extraction and UV-textured GLB export with no Python at runtime, on CUDA, ROCm, Vulkan or CPU.
mudler
The LocalAI team's from-scratch C++20 port of vLLM's serving core — a 66 MiB binary against a 9.1 GiB install, token-for-token identical output, GGUF native, on CUDA, CPU, Metal and Vulkan.
tiiuae
TII's Apache-2.0 inference stack for Falcon Perception (0.6B) and Falcon OCR (0.3B) — early-fusion single-Transformer VLMs that emit full-resolution masks in one shot and read documents to text, LaTeX or HTML.
QuentinFuxa
Apache-2.0 self-hosted real-time speech-to-text: SOTA simultaneous-ASR commit policies, Sortformer diarization, 200-language translation, and swappable Whisper/Voxtral/Canary/Qwen3 backends behind OpenAI- and Deepgram-compatible APIs.
OHF-Voice
The Open Home Foundation's fast, fully local neural TTS engine behind Home Assistant and NVDA — VITS voices on ONNX Runtime across 44 locales, with v1.7.0 adding a pitch-accent-aware Japanese phonemizer.