We check every product on this page once a day and record whether it still answers.
Open-source control plane that detects your hardware and configures/runs the right local LLM engine automatically.
Open source
What to know▼
How it works
Detects your RAM and VRAM, recommends models that fit, applies hardware-tuned settings, downloads weights, and starts an OpenAI-compatible server via llama.cpp, MLX-LM, or vLLM.
What's different
Coordinates proven runtimes rather than building another inference engine, and shows the launch plan before executing.
We check every product on this page once a day and record whether it still answers.
A local, privacy-first app that uses one on-device Gemma model to capture, transcribe, search, and automate your screen and audio history.
Watch out · Requires a 4GB GPU to run.
Works offlineOpen sourceNo tracking
What to know▼
How it works
Uses one local Gemma model on-device for screen vision, audio transcription, chat, and reasoning; captures only when content changes and lets you search or chat with your screen history in plain English.
What's different
Compared against Microsoft Recall (needs $1000+ hardware) and Screenpipe (needs separate OCR + Whisper + external LLM) — this runs one local model for everything.
We check every product on this page once a day and record whether it still answers.
A self-hosted, MIT-licensed framework for running your own local-LLM AI agents over your tasks, money, knowledge and homelab data, built for developers who want to fork and customize it rather than use a hosted SaaS.
Open sourceSelf-hosted
What to know▼
How it works
A self-hosted platform where named agents run durable Temporal workflows over your own data (tasks, money, knowledge, homelab alerts), asking for a decision only when they truly need one.
What's different
Local-LLM-first and MIT-licensed, designed to be forked and customized rather than used as a hosted SaaS.
Pricing
Open source (MIT-licensed).
Best for
Developers who want to self-host and customize their own AI agent framework over personal data.
We check every product on this page once a day and record whether it still answers.
A free, open-source Chrome extension that cleans up copied web text into compact prompts, processing everything on-device rather than a server. For anyone who pastes a lot of text into AI chat tools.
FreeWorks offlineOpen source
What to know▼
How it works
A Chrome extension that compacts messy web copy into clean AI prompts, processing everything on-device.
What's different
Free, open source, and 100% on-device rather than sending text to a server; optional Gemini Nano support.
Pricing
Free.
Best for
People who frequently paste web text into AI chat tools and want it cleaned up first.
We check every product on this page once a day and record whether it still answers.
An open-source browser extension that turns selected webpage text into a structured civic report entirely on-device, with no cloud calls.
Works offlineOpen source
What to know▼
How it works
An open-source Chrome/Edge extension that turns selected webpage text into a structured civic report, classifying the issue, estimating urgency, and drafting a report.
What's different
All AI inference runs locally on-device, with no backend, API key, account, or telemetry.
We check every product on this page once a day and record whether it still answers.
Turns a topic into a two-host AI video podcast with lip-synced avatars and captions, driven from the CLI or a studio UI using your own AI API keys. Open source.
Open source
What to know▼
How it works
Turns a single topic into a two-host video podcast with mixed AI voices, lip-synced avatars, and word-timed captions, rendered to MP4, driven from the CLI or a live studio interface.
What's different
Open source and runs on your own API keys, so you pay the underlying provider's rates directly.
Best for
Developers or creators who want to generate AI video podcasts from the command line.
We check every product on this page once a day and record whether it still answers.
Open-source, local-first desktop app for training, evaluating and explaining ML models without cloud services.
Works offlineOpen source
What to know▼
How it works
Local-first desktop app for importing data, training predictive and generative models, evaluating them, and applying explainability techniques, without cloud services, external authentication, or API keys.
We check every product on this page once a day and record whether it still answers.
An open-source AI workspace bridging terminal, a local-first desktop app and mobile remote control using your own API keys for Anthropic, OpenAI or Gemini — built for developers wanting provider flexibility.
Works offlineOpen source
What to know▼
How it works
An open-source AI workspace where you bring your own API keys for Anthropic, OpenAI, or Gemini, bridging a terminal, a local-first desktop app, and mobile remote control with a command approval mechanism.
What's different
Open-source and provider-independent — no lock-in to a single AI model provider — with a secure command approval step for agent actions.
Best for
Developers who want to run AI agents across terminal, desktop, and mobile using their own API keys instead of a single vendor's app.
We check every product on this page once a day and record whether it still answers.
An open-source Mac app that runs local AI mini-apps, including a private finance analyzer that redacts data before AI sees it.
Watch out · macOS only.
FreeOpen source
What to know▼
How it works
Runs AI mini-apps locally on Mac; the lead app is a private CFO that turns bank/card CSV or PDF exports into spend reports (trends, subscriptions, duplicate charges) with account numbers redacted before any AI sees them. Also includes a music DJ with karaoke, a Mac health scanner, and cross-agent memory shared with Claude Code and Codex.
Pricing
Open source; free hosted tier, or bring your own OpenAI-compatible/Ollama model.
We check every product on this page once a day and record whether it still answers.
A physical open-source USB device that watches your screen and can operate your phone or computer by voice, entirely offline with zero data collection. Built for makers and privacy-focused tinkerers.
Works offlineOpen sourceSelf-hosted
What to know▼
How it works
A physical USB device that plugs into any phone or computer, watches the screen over HDMI, and sends taps and keystrokes over USB HID to operate real apps the same way a person would — no app install, jailbreak, developer mode, or API required. It captures the screen, sends it to an AI model of your choice, decides the next action, and repeats until the task is done; voice mode runs on-device.
What's different
Works one layer below software integrations, so it can operate any app you can see and tap, including ones with no API or accessibility layer.
Best for
Makers and privacy-focused users who want to automate phone or computer tasks entirely offline without granting an app API access.
We check every product on this page once a day and record whether it still answers.
A self-hostable AI chat platform that routes queries to the cheapest LLM and adds live market data, positioned as an alternative to ChatGPT or Claude you run yourself. For developers and cost-conscious teams.
FreeOpen sourceSelf-hosted
What to know▼
How it works
A self-hostable, open-source AI chat platform that runs on your own infrastructure, integrates live financial market data into chat, and routes each query to the best/cheapest LLM automatically across OpenAI, Anthropic, SiliconFlow and others.
What's different
Self-hosted with full data ownership and no vendor lock-in, plus intelligent model routing claimed to cut API costs by up to 60% versus using a single provider.
Pricing
Free forever to self-host, with Free / Pro / MAX tiers and per-model quotas.
Best for
Developers and cost-conscious teams who want a ChatGPT/Claude alternative running on their own infrastructure.
We check every product on this page once a day and record whether it still answers.
A 1.2GB AI model that runs fully offline on your laptop and claims to beat GPT-5 on coding benchmarks. Open source with no subscription, built for developers wanting a local coding assistant.
Watch out · The listing claims it beats GPT-5 on coding benchmarks and cites a 68.4% SWE-bench Lite score — an unverified vendor claim.
Works offlineOpen sourceNo subscription
What to know▼
How it works
A 1.2GB AI model that runs fully offline on a laptop, using a neuro-symbolic architecture combining neural pattern recognition with symbolic logic for software engineering tasks.
Pricing
Open-source, no subscription.
Best for
Developers wanting a local, offline coding assistant without cloud dependence.
Watch out
The listing claims it beats GPT-5 on coding benchmarks and cites a 68.4% SWE-bench Lite score — an unverified vendor claim.
We check every product on this page once a day and record whether it still answers.
A native macOS app for running AI agents fully offline with persistent memory and cryptographic identity — open-source infrastructure for developers building local agents, not a consumer chat app.
Works offlineOpen source
What to know▼
How it works
A native macOS harness for running AI agents fully offline, with persistent memory, autonomous execution and cryptographic identity, built in Swift.
What's different
Fully offline and open source, unlike cloud-based agent harnesses.
Pricing
Open source.
Best for
Developers building local AI agents on Mac who want offline execution and no cloud dependency.
We check every product on this page once a day and record whether it still answers.
A self-hosted WordPress plugin combining a visual workflow automation engine with an open-source AI agent that builds workflows and asks before acting, using your own LLM API keys.
FreeNo sign-upData stays with you
What to know▼
How it works
A low-code workflow builder plus an open-source AI agent and local executor run inside WordPress, with no SaaS component and data staying on your own server.
Pricing
Agent and executor are free; one license covers both paid plugins for the rest of the stack.
Best for
WordPress site owners who want automation without sending data to a third-party SaaS.
We check every product on this page once a day and record whether it still answers.
An on-device dictation, rewriting, translation and local AI agent tool for Apple Silicon Macs - free and open-source (MIT), with no cloud, no accounts, and MCP support.
Watch out · Requires Apple Silicon and macOS 26; some listed models (Gemma 4, Qwen3.6, Ornith 1.0) are described as coming next, not yet available.
FreeWorks offlineOpen source
What to know▼
How it works
Runs on-device dictation, rewriting, and translation using multiple transcription models (Parakeet, CTC, Nemotron, Qwen3-ASR), plus a local agent that plans and calls tools like Apple Notes, clipboard, files, and MCP.
What's different
Fully local processing with no cloud and no accounts, and lets you swap or customize any underlying model or prompt.
Pricing
Free and open-source (MIT license).
Best for
Apple Silicon Mac users who want dictation and an AI agent without sending data to the cloud.
Watch out
Requires Apple Silicon and macOS 26; some listed models (Gemma 4, Qwen3.6, Ornith 1.0) are described as coming next, not yet available.
We check every product on this page once a day and record whether it still answers.
A local-first AI platform bundling chat, a coding agent, a terminal and uncensored open models, with no cloud or accounts. For technical users, not really a mobile app despite the Android companion.
Watch out · Ships uncensored models with zero filters — outputs are not moderated.
No sign-upWorks offlineOpen source
What to know▼
How it works
A local-first AI platform bundling end-to-end encrypted P2P chat, a bare-metal terminal with real PTY shell access, autonomous coding agents, hybrid RAG, and bundled uncensored Qwen/Gemma models, with a native Android companion app for LAN discovery.
What's different
Runs fully offline with no cloud, accounts, or subscriptions, and ships uncensored model variants with no filters.
Pricing
Open-source (AGPL-3.0).
Best for
Technical users on Linux or Windows who want a self-hosted AI toolkit with no cloud dependency.
Watch out
Ships uncensored models with zero filters — outputs are not moderated.
We check every product on this page once a day and record whether it still answers.
An open-source, self-hosted AI video surveillance system where footage and detection models stay on your own hardware.
Works offlineData stays with youOpen source
What to know▼
How it works
Runs entirely on hardware you own with footage never leaving your network; AI detectors are pluggable via an open contract (~30 lines of Python) for models like YOLOv8, license plates, or faces; a local LLM can answer spoken questions about live camera frames.
What's different
100% open source and self-hosted, unlike cloud NVRs such as Ring, Nest, or Verkada.
Pricing
No cloud, no subscriptions, no per-camera fees.
Best for
Developers who want full ownership of their video surveillance stack.
We check every product on this page once a day and record whether it still answers.
Open-source, local-first AI system that coordinates multiple agents to plan, build, verify, and ship real software.
Watch out · Local-first operation.
Works offlineOpen source
What to know▼
How it works
Coordinates specialized AI agents to plan, build, verify, recover, and ship software, with persistent memory, browser evidence, and real deployment integrations.
We check every product on this page once a day and record whether it still answers.
An open-source Windows desktop AI agent that performs approved computer actions and automations while keeping data and model choice under the user's control.
Works offlineOpen source
What to know▼
How it works
An open-source Windows desktop agent for secure conversations, approved computer actions, durable missions, and reusable automation, letting users bring their own model provider.
What's different
Keeps credentials, data, and control in the user's hands, open source.
We check every product on this page once a day and record whether it still answers.
An open-source, fully local agentic AI platform that runs multi-agent workflows and vector-database ingestion entirely on-device, for organizations and technical users who want AI automation without sending data to the cloud.
Works offlineData stays with youOpen source
What to know▼
How it works
100% local data processing with optimized vector-database ingestion and multi-agent orchestration to run business workflows securely on-device.
Best for
organizations and developers building AI workflows that require full data privacy.
We check every product on this page once a day and record whether it still answers.
A free, open-source iOS app that connects Meta Ray-Ban glasses to an on-device AI model so photos and questions can be processed offline without the cloud, keeping history on the phone.
FreeWorks offlineOpen source
What to know▼
How it works
Runs models 100% on-device with Apple MLX, or lets you pick Apple Intelligence, OpenAI, Gemini Live, or OpenClaw; ask by voice, analyze what you see, recognize faces, search the web.
What's different
on-device mode works offline with no cloud or API key.
We check every product on this page once a day and record whether it still answers.
An open-source browser automation engine that finds page elements from plain-English descriptions instead of CSS selectors, for developers writing automation scripts.
Open source
What to know▼
How it works
An open-source browser automation engine that resolves page elements from plain-English descriptions instead of CSS selectors, using self-healing scripts and local NLP.
What's different
No mandatory AI dependency and no CSS selectors to maintain - scripts self-heal when the page changes.
Best for
Developers writing browser automation or scraping scripts who are tired of selectors breaking.
