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.
760 projects
Anjok07
Deep-learning desktop GUI for vocal and stem separation from any audio track.
can1357
MIT-licensed terminal AI coding agent with hash-anchored edits, LSP refactoring, persistent Python and JavaScript kernels, subagents, 40+ providers, and a Rust core under a TypeScript CLI.
nesquena
MIT-licensed browser interface for Hermes Agent, a self-hosted autonomous agent with persistent memory, multi-provider support, 10+ messaging integrations, and WebAuthn passkey login.
FareedKhan-dev
MIT-licensed PyTorch Jupyter notebook that builds a GPT-style transformer end to end from The Pile data through tiktoken tokenization to text generation, scaling from 13M to 2B+ parameters.
aaif-goose
Apache-2.0 Rust-based open AI agent from Block (now Linux Foundation AAIF) with native desktop, CLI, and API surfaces, 70+ MCP extensions, and 15+ LLM providers including local Ollama.
pengzhangzhi
Apache-2.0 fully open diffusion language model for code, shipping data pipeline, pretraining code, evaluation suite, and 0.5B Open-dCoder checkpoints with representation-alignment-based 4x training speedup.
lightseekorg
LightSeek Foundation's MIT-licensed inference engine targeting TensorRT-LLM-level performance with vLLM-level usability, purpose-built for agentic workloads on Blackwell and Hopper GPUs.
HKUDS
HKUDS's MIT-licensed multi-agent video generation framework with director, screenwriter, producer, and generator roles that assembles minute-scale narrative video from ideas, novels, or scripts.
p-e-w
Automated directional ablation tool that removes refusal behavior from open LLMs while preserving capability through Optuna-tuned per-layer ablation kernels.
OpenBMB
OpenBMB's tokenizer-free 2B-parameter TTS model emitting native 48kHz audio across 30 languages with voice design, controllable cloning, and an OpenAI-compatible endpoint.
galilai-group
Open-source platform from galilai-group, with authors including Yann LeCun, that unifies data collection, training, and model-predictive control evaluation for world model research across 25+ environments.
LlamaIndex
Fast, local-first open-source document parser from run-llama with Rust core, spatial text plus bounding boxes, bundled OCR, and bindings for Python, Node.js, Rust, and WASM.