InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. web-llm

    AI repositories

    High-performance In-browser LLM Inference Engine

    Stale GitHub, mlc-ai 19.3k ★Apache-2.0Updated 36 days ago

    git clone https://github.com/mlc-ai/web-llm.git
  2. pegainfer

    AI repositories

    Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    Stale GitHub, pegainfer-project 729 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/pegainfer-project/pegainfer.git
  3. Flide

    Agents & frameworks

    🔥🔥 The extremely fast inference engine for decision model

    Stale GitHub, OmniJev 396 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/OmniJev/Flide.git
  4. Halfrost-Field

    AI repositories

    ✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field 冰霜之地:源码解析、系统设计与工程实践笔记

    Stale GitHub, halfrost 13.2k ★CC-BY-SA-4.0Updated 47 days ago

    git clone https://github.com/halfrost/Halfrost-Field.git
  5. uzu

    AI repositories

    A high-performance inference engine for AI models

    Indexed GitHub, trymirai 3,351 ★MITUpdated today

    git clone https://github.com/trymirai/uzu.git
  6. TensorFold

    AI repositories

    LLM Inference Engine for Metal, CUDA and Vulkan.

    Indexed GitHub, ashhart 2,266 ★Apache-2.0Updated today

    git clone https://github.com/ashhart/TensorFold.git
  7. kvcached

    AI repositories

    Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

    Stale GitHub, ovg-project 2,033 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/ovg-project/kvcached.git
  8. TensorSharp

    AI repositories

    A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability

    Stale GitHub, zhongkaifu 675 ★BSD-3-ClauseUpdated 4 days ago

    git clone https://github.com/zhongkaifu/TensorSharp.git
  9. zero-to-sglang

    Docs & tutorials

    Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.

    Indexed GitHub, datawhalechina 2,148 ★Updated today

    git clone https://github.com/datawhalechina/zero-to-sglang.git
  10. rtp-llm

    AI repositories

    RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

    Indexed GitHub, alibaba 1,400 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/alibaba/rtp-llm.git
  11. MNN

    AI repositories

    MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

    Indexed GitHub, alibaba 16.5k ★Apache-2.0Updated today

    git clone https://github.com/alibaba/MNN.git
  12. kimi-k3-in-c

    AI repositories

    A 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.

    Stale GitHub, FareedKhan-dev 9,049 ★Apache-2.0Updated 45 days ago

    git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git
  13. tokenspeed

    AI repositories

    TokenSpeed is a speed-of-light LLM inference engine.

    Indexed GitHub, lightseekorg 2,932 ★MITUpdated today

    git clone https://github.com/lightseekorg/tokenspeed.git
  14. halogen-flash-server

    AI repositories

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    Stale GitHub, peonist-ai 1,258 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/peonist-ai/halogen-flash-server.git
  15. janas

    AI repositories

    37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

    Indexed GitHub, prabanta-dev 717 ★GPL-3.0Updated today

    git clone https://github.com/prabanta-dev/janas.git
  16. PolyStrata

    AI repositories

    Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.

    Stale GitHub, VecSzn 722 ★MITUpdated 16 days ago

    git clone https://github.com/VecSzn/PolyStrata.git
  17. slotstream

    AI repositories

    Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

    Indexed GitHub, carloslfu 673 ★MITUpdated today

    git clone https://github.com/carloslfu/slotstream.git
  18. crit

    MCP servers

    Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

    Stale Official MCP Registry, io.github.crit-labs Updated 7 days ago 1 note

    crit@0.17.2
  19. Atomic-Chat

    AI repositories

    Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V

    Stale GitHub, AtomicBot-ai 1,808 ★Custom licence (see repository)Updated 30 days ago

    git clone https://github.com/AtomicBot-ai/Atomic-Chat.git
  20. imp

    Agents & frameworks

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    Stale GitHub, kekzl 124 ★MITUpdated 12 days ago

    git clone https://github.com/kekzl/imp.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.