Skip to content
Tiny TPU

Self-hosted alternatives to Tiny TPU

200 self-hosted apps like Tiny TPU, closest match first.

Top picks

  1. H

    HappyTorch

    Launch

    A PyTorch coding practice platform — covering LLM, Diffusion, PEFT, and more A friendly environment to help you deeply understand deep learning components through hands-on practice. Like LeetCode, but for tensors. Self-hosted. Supports both

    Open sourceSelf-hosted

  2. P

    Pyre Code

    Launch

    A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.

    Open sourceSelf-hosted

  3. S

    Sipp

    Launch

    AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider routing. Built with Rust & C++.

    Open sourceSelf-hosted

  4. N

    Netron

    Launch

    This Snap is deprecated. Please migrate to .deb or .rpm. https://github.com/lutzroeder/netron/issues/1500

    Open sourceSelf-hosted

  5. S

    SapienAI

    Launch

    Coming soon: SapienAI, one workspace for agentic AI research, collaborative LaTeX, Typst and Markdown writing, Python and R notebooks and a knowledge base.

    Open sourceSelf-hosted

  6. P

    Pipelex

    Launch

    Pipelex lets you build AI methods with your coding agent and run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

    Open sourceSelf-hosted

More like Tiny TPU

7
M

Minion

A tiny single-file coding agent for self-hosted models

Launch
8
T

Texlyre

A local-first LaTeX & Typst web editor

Launch
9
G

Guaardvark

Self-hosted AI studio on your own GPU: chat with your files

Launch
10
S

Streamcore Server

Open-source realtime voice agent server in Go with WebRTC

Launch
11
T

Tessera

A workspace for organizing AI coding sessions across projects

Launch
12
T

Torra Community

Open-source visual platform for AI agent and workflow development

Launch
13
S

Self-Hosted AI Stack

Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document…

Launch
14
P

Prismical

✏️ Open-source AI note taker - 🎙️ Transcribe meetings, lectures, and voice…

Launch
15
N

Nautilo

AI goes multiplayer. A self-hosted workspace for people and machine people

Launch
16
K

Kitten-TTS-Server

Self-host the ultra-lightweight Kitten TTS model

Launch
17
A

ATLAS

Adaptive Test-time Learning and Autonomous Specialization

Launch
18
S

selfie

An educational software system of a tiny self-compiling C compiler

Launch
19
O

open-notebook

Organizes research with the self-hosted Open Notebook alternative to NotebookLM

Get
20
K

Kokoro Web

Free AI text-to-speech, online or self-hosted, OpenAI compatible!

Launch
21
O

OpenTranscribe

Self-hosted AI-powered transcription platform

Launch
22
A

AgentsMesh

Self-hostable AI Agent Workforce Platform

Launch
23
A

Airunner

Offline inference engine for art, real-time voice conversations

Launch
24
1

10x

Up to 20x faster AI coding with multi-step Superpowers

Launch
25
W

Willow Inference Server

Open source, local, and self-hosted highly optimized language inference…

Launch
26
C

Chatterbox-TTS-Server

Self-host the powerful Chatterbox TTS model

Launch
27
A

Amux

Open-source control plane for AI coding agents

Launch
28
R

Remiqora

Free, open-source local AI music studio: ACE-Step 1.5 and YuE2-3B text-to-music

Launch
29
L

LLMKube

Kubernetes operator for self-hosted LLM inference with pluggable runtimes

Launch
30
T

TurboOCR

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

Launch
31
S

Syll

[New] Syll is a self-hosted companion runtime

Launch
32
M

Matrixhub

An Open-source, self-hosted AI model hub

Launch
33
T

Taskosaur

Open Source Project Management with Conversational AI Task Execution

Launch
34
M

Muxi

Deploy intelligence. Open-source infrastructure for AI agents in production

Launch
35
D

Dia-TTS-Server

Self-host the powerful Dia TTS model

Launch
36
A

Agentic Signal

Visual AI agent workflow automation platform with local LLM integration

Launch
37
S

Self Host N8n On GCR

Self-host n8n on Google Cloud without the subscription fees or server headaches

Launch
38
L

LoomFlow

Lightweight AI-native workflow builder for individuals and small teams

Launch
39
A

AReno

An easy-to-use, fast toolkit to scale up RL post-training on a single node

Launch
40
P

Pneumaticworkflow

Free and source-available Apache 2.0 licensed lightweight workflow automation

Launch
41
S

Synapse

Self-hosted AI workspace with shareable AI teammates, shared conversations

Launch
42
T

TaOS

Self-hosted AI agent OS

Launch
43
M

MarketMAI

AI Newsletter

Launch
44
L

LangGraph-GUI

Visual node-edge graph GUI editor for LangGraph and run

Launch
45
Z

Zosma Cowork

A web-based AI workspace with a local execution daemon

Launch
46
T

Torollo

Torollo is an open-source interactive visual playground

Launch
47
D

Duragraph

Self-hosted, enterprise-ready AI workflow orchestration

Launch
48
S

SourceWeft

Open-source, self-hostable alternative to ChatGPT and NotebookLM

Launch
49
J

Jeff

A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer

Launch
50
C

Chatterbox TTS API

Local, OpenAI-compatible text-to-speech

Launch

About Tiny TPU

T

Tiny TPU

An attempt to understand and build a TPU—by complete novices

Tiny TPU is a write-up of an attempt by four complete novices to understand and build a tensor processing unit, the kind of accelerator Google uses for machine learning. The project is documented as a slideshow with sections on why the team started, what a TPU is, how they developed their toy design, and why they used XOR as a first problem. It walks through batching and dimensions, the systolic array of processing elements that performs matrix multiplication, input and weight scheduling with staggering and FIFOs, bias and leaky ReLU activation, pipelining and double buffering, and a forward pass walkthrough. The authors describe a strict philosophy of trying the hacky way first and consulting outside sources only after, and they say they wrote the code without relying on AI tools.

Price
Open source
Category
Design
Website
tinytpu.com