Skip to content
Sunk Cost

Open source alternatives to Sunk Cost

200 open source apps like Sunk Cost, closest match first.

Top picks

  1. W

    whatcani.run

    Launch

    whatcani.run helps you find the best AI models to run locally and how to run them, based on real data from trials that people ran on their own hardware. Each model is listed with its runtime, decode and prefill speed, time to first token, p

    FreeOpen source

  2. G

    Graviton

    Launch

    Graviton is an open-source engine that the project says can run language models with 500 billion or more parameters on a Mac Mini. Its approach is to compress models from 16-bit weights down to 4-bit or 1.58-bit, and to stream them from SSD

    FreeOpen source

  3. H

    HilbertRaum

    Launch

    HilbertRaum is local AI software for working with sensitive documents without uploading them to a cloud service. The software runs on your own computer, so documents, questions and answers never leave the device, and it works offline. You c

    FreeOpen source

  4. F

    Frugon

    Launch

    Frugon is a free, open-source command-line tool that estimates how much you could save on LLM bills. You give it the request logs your app already writes, in OpenAI or Anthropic-style JSONL, and it shows which calls a cheaper model could ha

    FreeOpen source

  5. L

    LocalAI

    Launch

    LocalAI is an open-source, MIT-licensed AI engine that runs language models, speech, vision, image and video generation and agents on your own hardware. Its API is compatible with OpenAI, and the site says it also speaks the Anthropic, Olla

    FreeOpen sourceSelf-hosted

  6. 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

    FreeOpen sourceSelf-hosted

More like Sunk Cost

7
P

Proxy

Local-first LLM proxy that meters what every agent run costs

Launch
8
M

Meterless

Local-first AI workspace for ownable desktop automation missions

Launch
9
N

Nativ

Local AI, native to your Mac

Launch
10
G

Guaardvark

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

Launch
11
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
12
S

Self-Hosted AI Stack

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

Launch
13
R

Reins

Local AI chat for iPhone, iPad and Mac

Launch
14
N

NadirClaw

Source-available LLM router and AI cost optimizer

Launch
15
D

DarkForest Protocol

The internet's open-source AI paywall

Launch
16
R

Replicate

Machine learning doesn’t need to be so hard

Launch
17
P

Pocketpaw

Your AI agent in 30 seconds

Launch
18
X

Xybrid

Cross-platform on-device AI toolkit

Launch
19
O

Ollama

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

Launch
20
C

ChatLLM-Web

Private local model studio, AI chat

Launch
21
L

LocalScore

Local AI Benchmark

Launch
22
L

Locally Uncensored

The all-in-one local AI studio for your desktop: chat

Launch
23
P

Phosphene

Run MiniMax Hailuo H3 and LTX-2.5 video generation locally on a Mac

Launch
24
L

Lnwjud

Local AI-agent runtime & MCP gateway

Launch
25
G

GoModel

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

Launch
26
L

Latitude

AI Agent Observability & Monitoring

Launch
27
L

Litmux

Unit tests for AI. Test prompts, compare models, save money

Launch
28
R

Routerly.ai

Self-hosted LLM gateway that routes requests across AI providers

Launch
29
C

CTX

CTX Fit finds the cheapest AI coding setup

Launch
30
M

MLX-LoRA-Studio

A native Mac App for LLM fine-tuning on Apple Silicon

Launch
31
S

Syrtis

AI token usage & quota monitor for the macOS menu bar

Launch
32
M

Manifest

A complete backend in a single YAML file

Launch
33
O

Omarchy Local AI

Local AI for Omarchy: the model validated for your GPU, one button on the bar

Launch
34
O

OpenRouter Model Price Comparison

Compare pricing across different AI models available on OpenRouter

Launch
35
M

Misceo

Local Anthropic-compatible AI gateway

Launch
36
M

MLX Tune

Fine-tune LLMs on your Mac with Apple Silicon

Launch
37
A

Agenvoy

Self-hosted 24/7 personal AI agent that runs on your own machine

Launch
38
M

Mix-Studio

The cleanest, responsive AI workspace

Launch
39
A

AI LLM Comparison

A website where you can compare every AI Model

Launch
40
1

10x

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

Launch
41
C

Claude Code Local

Run Claude Code 100% on-device with local AI on Apple Silicon

Launch
42
L

Llamafarm

Deploy any AI model, agent, database, RAG

Launch
43
P

Pipelex

Build AI methods with your coding agent

Launch
44
W

Wisp Science

Open-source, local-first desktop AI research workbench

Launch
45
O

Openclaw.net

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

Launch
46
B

BodhiApp

Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs

Launch
47
M

mlx-serve

Native LLM inference server for Apple Silicon

Launch
48
S

SourceWeft

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

Launch
49
A

Agentsystems

Self-hosted app store and runtime for AI agents

Launch
50
U

Unsloth

Local UI to run and train LLMs and diffusion models

Launch

About Sunk Cost

S

Sunk Cost

How long until local AI pays for itself?

Sunk Cost is a calculator that works out how long a machine for running local AI models takes to pay for itself, compared with paying for an API. You pick a machine such as a Mac mini, Mac Studio, DGX Spark or Strix Halo box, set how many tokens you use a day, the context window and the input-to-output ratio, and the site shows which open models fit and how fast they run. The break-even view can be adjusted for electricity cost, API speed, your own generation speed or your monthly bill. Where nothing has been measured, local speed is estimated from memory bandwidth and labelled as an estimate. The site is candid about the results. At 500k tokens a day on the strongest model, the quickest pay-back in its table is 26 years, on a GeForce RTX 3060 with 12GB, and nothing in the table pays back inside a decade at that usage. The table covers 56 machines, and the site also has best-buy lists by usage level. Your inputs are sent once you stop typing, with no cookies and no IP address.

Category
AI
Website
sunkcost.ai