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
secureagentics
Apache-2.0 runtime security layer for AI agents that watches both tool-call activity and reasoning traces to catch prompt injection, tool poisoning and out-of-remit actions, with Python/TypeScript SDKs and a self-hostable Docker stack.
zengxiao-he
A solo-built, from-scratch LLM stack spanning teacher-student distillation, custom Triton/CUDA kernels, a paged-KV speculative-decoding serving engine and a Rust gateway, with a parallel JAX implementation used as a numerical parity check.
huawei-csl
A Huawei CSL vLLM fork that quantizes the KV cache to 4-bit keys / 2-bit values via Hadamard rotation and iterative variance normalization, adding 3-5x more context capacity at FP16-level accuracy without calibration.
cosmo-wander-ai
Apache-2.0 C++17 edge AI engine running video analytics and on-device VLM across Sophon, Rockchip and x86 — GroundingDINO open-vocabulary detection, browser-based pipeline orchestration, and MQTT/webhook event delivery.
NomaDamas
AGPL-3.0 browser-based 3D previs studio built on Three.js — block scenes, pose characters and author camera moves, then drive the whole thing from Claude or any MCP client.
truefoundry
MIT-licensed TypeScript agent harness from TrueFoundry running the full execution loop — MCP tools, git-backed skills, on-demand sandboxing, approvals and context engineering — behind a chat UI, HTTP API and embeddable UI SDK.
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.