Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
litellm
AI repositoriesThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
git clone https://github.com/BerriAI/litellm.git -
litert-samples
AI repositoriesLiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.
git clone https://github.com/google-ai-edge/litert-samples.git -
xtuner
AI repositoriesA Next-Generation Training Engine Built for Ultra-Large MoE Models
git clone https://github.com/InternLM/xtuner.git -
LlamaFactory
AI repositoriesUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
git clone https://github.com/hiyouga/LlamaFactory.git -
vllm
AI repositoriesA high-throughput and memory-efficient inference and serving engine for LLMs
git clone https://github.com/vllm-project/vllm.git -
Box
AI repositoriesThe most advanced, fully offline client-side AI suite on Android today.
git clone https://github.com/jegly/Box.git -
GLM-4.5
AI repositoriesGLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
git clone https://github.com/zai-org/GLM-4.5.git -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
morphik-core
AI repositoriesOpen-source multimodal retrieval engine (Morphik Core)
git clone https://github.com/morphik-org/morphik-core.git -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git -
OlliteRT
AI repositoriesTurn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source
git clone https://github.com/NightMean/OlliteRT.git -
SwiftLM
AI repositories⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
git clone https://github.com/SharpAI/SwiftLM.git -
llm-architecture-from-scratch
AI repositoriesImplementing LLM architectures from scratch in PyTorch
git clone https://github.com/YeonwooSung/llm-architecture-from-scratch.git -
diy-llm
AI repositoriesCovers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识
git clone https://github.com/datawhalechina/diy-llm.git -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
ms-swift
AI repositoriesUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
git clone https://github.com/modelscope/ms-swift.git -
tools
AI repositoriesA set of tools that gives agents powerful capabilities.
git clone https://github.com/strands-agents/tools.git -
ScienceClaw
AI repositoriesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
git clone https://github.com/beita6969/ScienceClaw.git -
kimi-k3-in-c
AI repositoriesA 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git -
Open-Generative-AI
AI repositoriesUncensored Open-source alternative to AI video platforms — Free AI image & video generation studio with 800+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
git clone https://github.com/Anil-matcha/Open-Generative-AI.git -
pegainfer
AI repositoriesPure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
git clone https://github.com/pegainfer-project/pegainfer.git -
slide-deck-ai
AI repositoriesCo-create PowerPoint slide decks with AI
git clone https://github.com/barun-saha/slide-deck-ai.git -
PaperLens
AI repositoriesAI-Powered Research Assistant for Academic Paper Discovery, Analysis, and Citation Intelligence
git clone https://github.com/vanthree31/PaperLens.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.