Skip to content
shoehorn

Self-hosted alternatives to shoehorn

200 self-hosted apps like shoehorn, closest match first.

Top picks

  1. T

    TurboLLM

    Launch

    Run open AI models on your own machine — no cloud, no account, fully offline. Any GGUF model on any llama.cpp-compatible engine, auto-tuned to your hardware, with real measured tokens/sec before you download, a fast browser UI, and an OpenA

    Open sourceSelf-hosted

  2. M

    Minion

    Launch

    A tiny single-file coding agent for self-hosted models (llama.cpp / vLLM / SGLang).

    Open sourceSelf-hosted

  3. M

    Matrixhub

    Launch

    MatrixHub is an open-source, self-hosted model registry for AI models, built to work with vLLM and SGLang. It is meant to be a private replacement for Hugging Face inside your own infrastructure, in the way Harbor serves Docker Hub. Its tra

    Open sourceSelf-hosted

  4. L

    Llmaker

    Launch

    Models, vector DBs, embeddings, a retrieval agent, and evals: the whole modern LLM stack on your own hardware, from one command. OpenAI-compatible API + web UI per instance, GPU partitioning, no data leaving your machine.

    Open sourceSelf-hosted

  5. L

    LMRing

    Launch

    lmring is a web app for comparing AI models side by side. You pick up to four models from more than 50 providers, including OpenAI, Anthropic, Google, Meta, Mistral and DeepSeek, then write one prompt and send it to all of them at once. Res

    Open sourceSelf-hosted

  6. N

    NadirClaw

    Launch

    Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, n

    Open sourceSelf-hosted

More like shoehorn

7
F

Faster Chat

A blazingly fast, privacy first & OPEN AI Chat Interface

Launch
8
G

Ggrun

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched

Launch
9
P

Picollm

On-device LLM Inference Powered by X-Bit Quantization

Launch
10
O

OpenGateLLM

An open-source, unified interface for running and managing self-hosted LLMs

Launch
11
V

VoidLLM

Privacy-first LLM proxy and AI gateway

Launch
12
F

Free-GPT4-WEB-API

Not just GPT4! Easy to use, Self-Hosted

Launch
13
G

Guaardvark

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

Launch
14
S

Sipp

AI inference, packed simply

Launch
15
R

Routerly.ai

Self-hosted LLM gateway that routes requests across AI providers

Launch
16
N

Netron

Visualizer for neural network and machine learning models

Launch
17
G

GoModel

AI gateway written in Go with a unified OpenAI-compatible API

Launch
18
W

Webchat2api

OpenAI-compatible Web Chat API proxy

Launch
19
Q

Qwengate

Drop-in OpenAI-compatible API gateway for Qwen AI models

Launch
20
O

overtchat

A simpler self-hosted alternative to Open WebUI

Launch
21
S

SourceWeft

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

Launch
22
L

LLMKube

Kubernetes operator for self-hosted LLM inference with pluggable runtimes

Launch
23
O

Open Responses

Self-hosted alternative to OpenAI's Responses API compatible

Launch
24
O

OpenAgentCore

Open-source, self-hosted implementation of the OpenAI Agents API

Launch
25
O

Ollama

Load and run large LLMs locally to use in your terminal or build your apps

Launch
26
M

MOVO

Turn DeepSeek Harness into a self-hosted enterprise Agent platform

Launch
27
A

API7 cloud

Deploy and manage projects effortlessly

Launch
28
H

Honcho Self Hosted

Self-host Honcho memory layer for Hermes Agent

Launch
29
P

Paddler

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs

Launch
30
L

LangGraph-GUI

Visual node-edge graph GUI editor for LangGraph and run

Launch
31
M

Memory OS

A 7-layer memory operating system for Hermes Agent

Launch
32
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
33
L

Llamactl

Unified management and routing for llama.cpp, MLX and vLLM models

Launch
34
O

Openclaw.net

Self-hosted Enterprise and Personal AI + agent runtime in .NET

Launch
35
T

Textgen

Open-source desktop app for local LLMs

Launch
36
G

GPTPortal

A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI…

Launch
37
A

AIClient2API

Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro

Launch
38
L

Local-Multimodal-AI-Chat

Self-hostable multimodal chat with local LLMs

Launch
39
O

OmniKey-AI-Unified-Key-Manager

A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini…

Launch
40
M

Marm Memory

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok

Launch
41
U

Unsloth

Local UI to run and train LLMs and diffusion models

Launch
42
O

Olla

High-performance lightweight proxy and load balancer for LLM infrastructure

Launch
43
A

Aivory

Self-hosted AI chat platform with multi-step tool calls, persistent Python…

Launch
44
S

Self-Hosted AI Stack

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

Launch
45
G

GoGogot

Lightweight self-hosted AI agent. Open-source OpenClaw alternative in Go

Launch
46
M

MultitaskAI

Master Your AI, Maximize Your Productivity!

Launch
47
I

Inference Gateway

An open-source, cloud-native, high-performance gateway unifying multiple LLM…

Launch
48
C

CatGPT-Gateway

Turn your ChatGPT or Claude account into a fully working OpenAI-compatible API

Launch
49
M

Muxi

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

Launch
50
O

Otari

Open-source, OpenAI-compatible LLM gateway you run yourself

Launch

About shoehorn

S

shoehorn

Make any language model fit your machine

shoehorn is a tool for making a language model fit the memory your machine actually has. Preset quantizations ignore your hardware: you pick one that fits and either waste quality headroom or find out at load time that it does not fit. shoehorn starts from the memory you have, subtracts what inference needs, and solves a per-tensor mixed-precision assignment, so it spends the remaining budget on the tensors where extra precision buys the most quality. The site's example fits a Qwen3 4B model into a 519 MiB weights budget, using 99.998 percent of it. The workflow quantizes a BF16 GGUF file with an importance matrix, then runs the result with llama.cpp, which must be on your PATH. The command line tool includes a local web app, started with shoehorn ui, where you pick a model, press one button and chat. The site also has a Find models page that scans popular Hugging Face models for ones that fit a chosen machine, such as a Mac with 8 to 128 GB or a GPU with 8 to 32 GB of VRAM, and a context length setting. Installation is available through Homebrew, as release downloads for macOS, Linux and Windows, or from source with cargo. The tool is MIT licensed. Its quantizer is written from scratch in Rust, and it produces standard GGUF v3 files that llama.cpp based tools can load.

Price
Open source
Category
Finance
Website
notactuallytreyanastasio.github.io