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
antirez
MIT from-scratch C engine running MiniMax-H3 video generation natively on Apple Silicon Metal, with measured speed/quality dials and SSD streaming that cuts DiT memory from 36.5 GiB to 2.0 GiB.
huangruiteng
MIT provider-neutral control plane that keeps objectives, gates, todos, evidence, and quota durable across long-running agent loops on Codex, Claude Code, Cursor, or a custom runner.
VAST-AI-Research
MIT single-image-to-3D-Gaussian model from VAST-AI with an arbitrary Gaussian budget up to 262,144, ~2,000 lines across two files, near-zero dependencies, and official ComfyUI support.
jingyaogong
Apache-2.0 0.1B Omni model trained from scratch that listens, sees, and speaks — Thinker-Talker dual-path with streaming speech and barge-in, runnable end to end on one RTX 3090 in ~2 hours.
AudarAI
Arabic-first generative ASR ranking #1 of 36 on the Open Universal Arabic ASR Leaderboard — a Qwen3 decoder over a Whisper-style encoder, tuned on 300k+ hours across every major Arabic dialect.
studio-dots-ai
Apache-2.0 2B text-to-speech model with no discrete tokens anywhere — continuous autoregressive synthesis over a 48 kHz AudioVAE, reporting SOTA Seed-TTS-Eval scores with a distilled 204 ms-latency variant.
FareedKhan-dev
Apache-2.0 C99 inference engine that runs the 2.78T-parameter Kimi K3 on a CPU in 8.24 GB of RAM by streaming a 1.56 TB checkpoint — byte-identical output at every memory budget, from 8 GB to 224 GB.
arcships
Apache-2.0 offline OCR for Node.js and C++ — PP-OCRv6 with Core ML, Vulkan, and D3D12 acceleration, plus a bundled PDF renderer and model in one npm install with no runtime downloads.
livekit
Apache-2.0 Python framework for realtime voice AI agents — mix any STT, LLM, and TTS behind one session loop with transformer-based turn detection, telephony, MCP tools, and a built-in test harness.
tirth8205
MIT-licensed Tree-sitter code graph that serves AI coding tools blast-radius-scoped context over MCP, with published token-reduction benchmarks and one-command setup across 15+ platforms.
superlinked
Apache-2.0 self-hosted inference engine serving 100+ open models — embeddings, rerankers, OCR, extraction, safety, and generation — behind one OpenAI-compatible API and a full Terraform/Helm production stack.
PrimeIntellect-ai
Prime Intellect's MIT-licensed self-improving coding agent, built on a persistent IPython REPL where subagents are function calls and daemon-backed sessions survive terminal disconnects.