Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Underdog-Woof
Modelstext to speech model by ConwayResearch · numpy
ConwayResearch/Underdog-Woof -
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 -
mojo-dllm
AI repositoriesLocal inference for diffusion language models (LLaDA, Dream), written in Mojo
git clone https://github.com/vladimirrott/mojo-dllm.git -
Inflect-Micro-v2
Modelstext to speech model by owensong
owensong/Inflect-Micro-v2 -
jev
AI repositoriesjevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
git clone https://github.com/feder-cr/jev.git -
indra-ocr
Modelsimage to text model by datalab-to · onnx
datalab-to/indra-ocr -
git clone https://github.com/FlameProudspark/windows-tweak-checker-rpocket-team.git
-
parakeet-redux
Modelsautomatic speech recognition model by moondream
moondream/parakeet-redux -
Mach-Boom
Modelstext to speech model by SyzygyResearch
SyzygyResearch/Mach-Boom -
Execute cgroup-cpu-throttler-mcp
MCP serversPremium agentic endpoint for cgroup-cpu-throttler-mcp.
-
PiVo-1.4M
Modelstext to speech model by empero-ai · onnx
empero-ai/PiVo-1.4M -
antalia-mini
Modelstext to speech model by cloud0day3 · antalia-mini
cloud0day3/antalia-mini -
earshot
Agents & frameworksEars for coding agents: let AI hear, review and make sound. CPU-only, open source.
git clone https://github.com/Leonxlnx/earshot.git -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.git -
CPU Performance Engineering
MCP serversA CPU performance engineering brain: a vetted reading list, benchmarks and cited source passages
cpu-perf@0.1.1 -
handy-ollama
AI repositories动手学Ollama,CPU玩转大模型部署,在线阅读地址:https://datawhalechina.github.io/handy-ollama/
git clone https://github.com/datawhalechina/handy-ollama.git -
v8-cpu-profile-decoder-mcp
MCP serversMCP server that decodes V8 CPU profiles into token-efficient bottleneck summaries for AI agents
v8-cpu-profile-decoder-mcp@0.3.0 -
Maskbolt Segment Anything on CPU
MCP serversSegment Anything on CPU for agents: cut out objects, find every object, export masks and outlines.
https://github.com/skulitom/Maskbolt/releases/download/v0.1.0/maskbolt-windows-x64.mcpb@0.1.0 -
chatllm.cpp
AI repositoriesPure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)
git clone https://github.com/foldl/chatllm.cpp.git -
janas
AI repositories37 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.
git clone https://github.com/prabanta-dev/janas.git -
Phocinae-Largha-150M-v1
Modelstext classification model by Phocinae
Phocinae/Phocinae-Largha-150M-v1 -
GenieX
AI repositoriesRun frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
git clone https://github.com/qualcomm/GenieX.git -
qwenputer
AI repositoriesA computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
git clone https://github.com/divagr18/qwenputer.git -
dotnet-diagnostics
MCP serversOn-demand .NET runtime diagnostics for live CoreCLR apps — no code changes. Ships an MCP server (let an LLM drive the investigation), a standalone CLI, and a BenchmarkDotNet diagnoser, all on one engine: counters, CPU/off-CPU/alloc sampling, heap & thread snapshots, GC/contention/threadpool events, dumps.
git clone https://github.com/pedrosakuma/dotnet-diagnostics.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.