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.
625 projects
kvcache-ai (Moonshot AI)
KV-cache-centric LLM serving platform open-sourced by Moonshot AI, featuring disaggregated prefill and decode, RDMA-based KV transfer, and adapters for vLLM and SGLang.
LMCache
Open-source KV cache layer that lets LLM serving systems reuse previously computed tokens across replicas, dramatically reducing time-to-first-token for RAG, long-context, and multi-turn workloads.
vLLM Project
Kubernetes-native control plane from the vLLM team for GenAI inference, providing autoscaling, cache-aware routing, distributed KV cache, and high-density LoRA adapter serving.
turboderp
MIT-licensed quantization and inference library for running large LLMs on single consumer-class NVIDIA GPUs, with the new EXL3 format and Marlin-inspired memory-bound GEMM kernels.
ModelTC
Pure-Python LLM inference and serving framework from ModelTC with tri-process asynchronous architecture, token-level KV cache management, and Nopad attention for high GPU utilization.
fastgs
CVPR 2026 Highlight: official implementation of 'FastGS' — a general framework that trains 3D Gaussian Splatting scenes in ~100 seconds at PSNR parity with the Inria reference. MIT licensed, 1,100+ stars.
zai-org
Z.ai's open-source GLM-4.1V/4.5V/4.6V vision-language family with explicit 'thinking' reasoning mode and RLCS training, released under Apache 2.0 with 2,300+ GitHub stars.
speaches-ai
MIT-licensed self-hosted server that speaks the OpenAI Audio API, with faster-whisper for streaming transcription and translation plus piper and Kokoro for TTS. 3,300+ stars and 398 forks.
Rohit Ghumare
Apache 2.0 persistent memory layer for AI coding agents. Runs as a single local server on port 3111, talks to Claude Code, Cursor, Codex, Gemini CLI, OpenClaw, Hermes, pi, and OpenCode via 53 MCP tools and 12 auto-hooks. Benchmarked at 95.2 percent recall and 92 percent fewer tokens.
Google Chrome DevTools
Google's official Apache 2.0 MCP server that gives coding agents the full Chrome DevTools surface — performance traces with CrUX field data, source-mapped console and network inspection, and Puppeteer-driven automation. Works with Claude Code, Antigravity, Cursor, Codex, Copilot, and any MCP client.
Jesse Vincent / Prime Radiant
MIT-licensed agentic skills framework that gives Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Copilot CLI a TDD-enforced, spec-driven, subagent-orchestrated software development methodology. Distributed via the official Anthropic plugin marketplace.
LightSeek Foundation
MIT-licensed speed-of-light LLM inference engine from the LightSeek Foundation, targeting TensorRT-LLM performance with vLLM usability. 9 to 11 percent faster than TensorRT-LLM on Kimi K2.5 on Nvidia B200. MLA kernel already adopted by vLLM.