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
facebookresearch
Meta AI's third-generation self-supervised vision foundation model — frozen backbones from 21M to 6.7B params that deliver high-quality dense features and beat specialized SOTA without fine-tuning.
kyutai-labs
Kyutai's full-duplex speech-text foundation model for real-time voice dialogue (~200ms latency), built on the streaming Mimi neural audio codec — Apache-2.0 code, CC-BY-4.0 weights.
SparkAudio
An efficient LLM-based text-to-speech model built entirely on Qwen2.5 with BiCodec single-stream tokens — zero-shot voice cloning and controllable voice creation in Chinese and English (Apache-2.0).
AI4Finance-Foundation
AI4Finance's open-source project for efficiently fine-tuning LLMs on financial data — powering low-cost sentiment analysis, forecasting, and robo-advisory (MIT).
milvus-io
High-performance, cloud-native open-source vector database for billion-scale ANN search — the storage layer behind RAG, semantic search, and recommendation (Apache-2.0).
xorbitsai
Open-source framework to serve LLMs, speech, embedding, and multimodal models behind one OpenAI-compatible API, backed by engines like vLLM and llama.cpp (Apache-2.0).
illuin-tech
A vision language model approach (and colpali-engine library) that retrieves documents straight from page images, replacing brittle OCR pipelines with ColBERT-style late interaction (MIT).
langchain-ai
LangChain's low-level orchestration framework for building durable, stateful, long-running agents with human-in-the-loop control and persistent memory (MIT).
ZiYang-xie
Open-source project that generates full, 360-degree explorable 3D scenes in seconds from a text prompt or single image, for games, simulation, and VR (Apache-2.0).
suno-ai
Suno's fully generative text-to-audio model — speech, music, and sound effects from one transformer, with nonverbal cues like [laughs] and 100+ voice presets (MIT).
RVC-Project
The de facto open-source voice-conversion framework — trains a usable voice clone from 10 minutes of audio via top-1 feature retrieval, with a ~170ms real-time GUI (MIT).
argmaxinc
Argmax's Swift SDK bringing on-device Whisper speech-to-text (plus TTS and speaker diarization) to Apple Silicon — CoreML-accelerated, no audio leaves the device (MIT).