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
OpenBMB
OpenBMB's dense 1B on-device LLM claiming 42.57 average across reasoning, code, and agentic benchmarks, shipped with hybrid thinking modes and an open pretraining corpus.
block
Block's self-hostable workspace where humans and AI agents share the same rooms, built on a Nostr relay so every message, patch, and workflow step is one signed event.
fla-org
Triton kernel library implementing 30+ linear, sparse, and state-space attention architectures, verified on NVIDIA, AMD, and Intel — the source of Qwen3-Next's Gated DeltaNet kernels.
XiaomiMiMo
Xiaomi's terminal coding agent, forked from OpenCode, adding SQLite-backed cross-session memory, a deterministic multi-agent workflow runtime, and /dream and /distill self-improvement commands.
img2threejs
An agent skill that rebuilds an object from one reference image as editable, animation-ready Three.js code instead of a mesh file — gated by a staged review pipeline and pure-stdlib Python scripts.
bytedance
ByteDance's 3B active-parameter unified multimodal model handling image and video understanding, generation, and editing in one checkpoint — 85.11 on VBench and 0.90 on GenEval, matching 7B rivals.
OpenMOSS
A 0.9B Apache-2.0 model that jointly transcribes and diarizes long multi-speaker audio in one pass, cutting speaker-attribution error roughly 10x versus commercial ASR on AISHELL-4.
MisoLabsAI
An 8.2B-parameter open-weights TTS model using an RVQ Transformer with a Llama-8B backbone and Mimi codec, built for dialogue-context-aware English speech and zero-shot voice cloning.
0xShug0
A pure C++ ggml inference engine that runs 35 audio model families — TTS, ASR, VAD, diarization, source separation, and music generation — with no Python dependency and CUDA speedups of up to 8x.
CVHub520
A GPL-3.0 desktop annotation tool with a built-in AI engine, using SAM 3, Grounding DINO, YOLO, and PaddleOCR to auto-label images and video across detection, segmentation, OCR, VQA, and tracking.
headroomlabs-ai
An Apache-2.0 local-first context compression layer for AI agents, cutting 60-95% of tokens on JSON and 15-20% on coding agents via content-aware, reversible compressors.
alibaba
Alibaba's production-hardened AI code review CLI, combining deterministic pipelines with an LLM agent for precise line-level comments at roughly one-ninth the tokens of general-purpose agents.