We check every product on this page once a day and record whether it still answers.
A no-code AI workspace where teams update workflows and capture data via chat, voice, or image, running on local AI or your own API key.
Works offlineData stays with you
What to know▼
How it works
A no-code workspace where teams update workflows, automate tasks, and capture data via chat, voice, or image, running on local AI or your own API key so data stays in-house.
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.
An on-device reading companion for dyslexia, ADHD and visual differences, with OCR scanning and a local AI reading coach — no accounts or cloud. Built by a student contestant, not aimed at students.
Watch out · Built as an Apple Swift Student Challenge project (2026 winner), a student project rather than a funded company product.
No sign-upWorks offline
What to know▼
How it works
A reading companion for dyslexia, ADHD and visual differences offering customizable text transformation, camera OCR scanning, 8 gamified training exercises, and an AI reading coach called Lexi.
What's different
Runs 100% on-device, with no accounts or trackers — all AI and OCR processing happens locally rather than in the cloud.
Best for
People with dyslexia, ADHD or other visual reading differences.
Watch out
Built as an Apple Swift Student Challenge project (2026 winner), a student project rather than a funded company product.
We check every product on this page once a day and record whether it still answers.
A native macOS AI workspace with local-first chat, writing assistance, and browser automation, extensible by developers via an MCP registry.
Watch out · macOS only.
Works offline
What to know▼
How it works
A native macOS AI workspace with a multi-provider chat interface, local-first data handling, system-wide writing assistance, browser automation, file creation, and study tools that generate linked quizzes and flashcards.
What's different
Developers can extend it via an MCP registry, @-tools, and Prism Hosted capabilities.
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.
Routes your question to the best of 100+ AI models and fact-checks the answer with a second model, letting you choose how private each chat stays.
Works offline
What to know▼
How it works
A best-model router picks the top AI model for each question across 100+ models; a second model fact-checks the answer and flags unsupported claims, and answers cite sources via always-on web search.
What's different
Lets you choose how private each chat is: a Cloud encrypted enclave that can't read your prompts, fully local/offline in your browser, or an incognito mode with zero data retention that never trains on your data.
Pricing
The fully local, offline browser mode is free.
Best for
People who want control over how private their AI chats are, without giving up answer quality.
We check every product on this page once a day and record whether it still answers.
Local-first AI tooling for finance teams' monthly close (bank reconciliation, CSV sorting, PDF parsing, cash forecasting) that keeps sensitive financial data off cloud AI services.
Works offlineData stays with you
What to know▼
How it works
Local-first AI tools for finance teams' monthly close — bank reconciliation, sorting CSV line items, parsing PDFs, and building 90-day cash forecasts — without uploading sensitive financial data to cloud AI services.
We check every product on this page once a day and record whether it still answers.
A Windows screenshot tool that adds designed backgrounds, annotation, and on-device background removal, built as a CleanShot X equivalent for Windows users.
Watch out · Built and maintained by a single solo developer.
Works offlineNo subscription
What to know▼
How it works
Captures a region, applies a styled backdrop and annotations, and removes backgrounds using on-device AI that never uploads images.
Pricing
$9 one-time, lifetime license, no subscription, 30-day money-back guarantee.
We check every product on this page once a day and record whether it still answers.
Records and transcribes Mac meetings entirely on-device, then turns them into searchable AI notes, for people who don't want audio leaving their machine.
FreeWorks offlineData stays with you
What to know▼
How it works
records mic+system audio, transcribes locally with Whisper, generates TL;DR/decisions/action items
What's different
100% on-device transcription, optional bring-your-own ChatGPT/Claude for notes
We check every product on this page once a day and record whether it still answers.
Agentic coding assistant that runs on cloud, local, or self-hosted models with voice and supervised Mac computer use.
Self-hosted
What to know▼
How it works
Runs agentic coding workflows on cloud, local, or self-hosted models, with agents that work across files, Git, and terminals, plus voice and supervised Mac Computer Use.
What's different
Lets you keep model choice and control instead of being locked into one provider.
We check every product on this page once a day and record whether it still answers.
Local, auditable memory engine for Open WebUI that preserves raw messages instead of hidden summarized prompts.
Works offline
What to know▼
How it works
Preserves every raw message unchanged in a local ledger with deterministic sentence segmentation and exact character offsets, so every memory claim traces back to the exact words that produced it.
What's different
Unlike hidden-prompt summarization, raw messages are treated as evidence rather than memory.
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 budget tracker that runs its AI models entirely on your Android phone, so your spending and income never leave the device — free, no account, no ads, no tracking.
FreeNo sign-upWorks offline
What to know▼
How it works
Tracks income and spending using five AI models that run entirely on the Android device itself, from a 135M-parameter model up to Phi-4 Mini 3.8B, plus a tax engine covering 45 countries.
What's different
Unlike other AI finance apps that send your salary and spending to a server, the models run on-device so financial data never leaves the phone.
Pricing
Free on Android.
Best for
Android users who want AI-assisted budgeting without sending financial data to a company's server.
We check every product on this page once a day and record whether it still answers.
A free voice-to-structured-markdown notes app that runs entirely offline on Mac/iOS using a local LLM, for people who don't want their dictation sent to the cloud.
Watch out · Local LLM only — no cloud/API-key option mentioned, unlike some competitors.
FreeWorks offline
What to know▼
How it works
Global dictation shortcut, live markdown editor with on-the-fly LLM fixes, all local.
Pricing
Free.
Watch out
Local LLM only — no cloud/API-key option mentioned, unlike some competitors.
We check every product on this page once a day and record whether it still answers.
Turns a Google Play Store link into an on-device SWOT-style app diagnosis with prioritized improvement suggestions.
Works offline
What to know▼
How it works
Turns a Google Play link or manual inputs into an on-device SWOT-style diagnosis, highlighting weak signals and suggesting prioritized actions across product, marketing, and monetization.
What's different
Analysis history is stored in an encrypted local database; optional local AI can deepen results without sending analysis to a developer server.
Best for
App developers and marketers assessing their own app.
We check every product on this page once a day and record whether it still answers.
Private save-everything app for iPhone that files shared links, screenshots and videos into the right collection automatically and lets you search by meaning, not exact words.
No sign-upWorks offlineNo ads
What to know▼
How it works
On-device AI files shared content and fetches titles/previews; semantic search finds items by meaning
What's different
No accounts, ads or tracking; data stays on-device and in private iCloud
Best for
iPhone users who save a lot of links and want them organized without manual folders
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.
On-device AI video player for iPhone/iPad that generates smoother intermediate frames locally (RIFE neural networks, no cloud), with real-time 2x frame generation on newer devices, NAS playback, HDR and subtitle support.
Works offline
What to know▼
Best for
Anime fans and video enthusiasts wanting smoother mobile playback.
We check every product on this page once a day and record whether it still answers.
A local, on-device AI search engine for Mac that finds specific moments across your videos, photos and audio by natural-language description instead of filenames.
Works offline
What to know▼
How it works
Search your media library with natural language (a person, scene, conversation, or on-screen text); powered by on-device AI.
We check every product on this page once a day and record whether it still answers.
An offline iPhone app that generates AI images locally using Stable Diffusion, for people who want image generation without sending prompts to the cloud.
Works offline
What to know▼
How it works
Runs Stable Diffusion locally on iPhone, fully offline with no internet connection or API costs.
Best for
iPhone users who want AI image generation without sending data to the cloud.
We check every product on this page once a day and record whether it still answers.
Offline Windows speech studio offering local text-to-speech, speech-to-text and system-wide dictation with a local API.
Watch out · Runs fully offline after models download; works on GPU or CPU.
Works offlineData stays with you
What to know▼
How it works
A Windows speech studio offering multi-engine local TTS with custom voices, speech-to-text with speaker labels, global hotkey dictation into any field, and a localhost HTTP API for scripts and AI agents.
Watch out
Runs fully offline after models download; works on GPU or CPU.
We check every product on this page once a day and record whether it still answers.
A native Mac app that does local AI semantic photo search, storing embeddings on-device so search works even with drives disconnected.
Watch out · macOS only.
Pay onceNo subscription
What to know▼
How it works
A native macOS app that does local AI semantic photo search using CoreML, storing embedding vectors and previews on-device so search still works with external drives disconnected. Includes a 'Semantic Bridge' to find the conceptual link between two images and 'Constellation' auto-grouping.
We check every product on this page once a day and record whether it still answers.
A local MCP server that gives AI assistants like Claude, Cursor and ChatGPT tools to act on your Mac — iMessage, Teams, WhatsApp, Mail, files — with nothing sent to the cloud.
FreeWorks offlineData stays with you
What to know▼
How it works
A local Model Context Protocol server running on a Mac that gives AI assistants like Claude, Cursor and ChatGPT 143 tools to act on iMessage, local Microsoft Teams chats, WhatsApp, Apple Mail, Calendar, Contacts, Notes, Reminders, Finder files, OneDrive, Outlook and Office documents.
What's different
Runs 100% locally with no cloud connection, reaching apps like iMessage and local Teams chats that cloud-based connectors can't access.
Pricing
Free.
Best for
Mac users who want their AI assistant to act across native apps like iMessage and Mail without sending data to the cloud.
We check every product on this page once a day and record whether it still answers.
A local Windows app bundling agent automation, a code editor and a local LLM runner as a one-price replacement for a stack of $100/month cloud tools.
Watch out · Windows only.
Works offline
What to know▼
How it works
Bundles AI agents (via Krew), trigger-based automation, a code editor, a local LLM runner, DNS protection, and a content studio into one local Windows app.
What's different
Replaces roughly 8 separate $100/month cloud tools with one price and nothing sent to the cloud.
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.
Transcribes meetings, interviews, and recordings on-device using local Whisper models, with speaker labels and a local AI summarizer.
FreeWorks offlineCan export my data
What to know▼
How it works
Records or imports audio/video and transcribes it on-device using local Whisper models, with speaker labels, editing, export, and a local AI assistant for summaries and action items.
Pricing
Free to download, with optional Pro access.
Best for
Sensitive, privacy-conscious meeting or interview transcription.
We check every product on this page once a day and record whether it still answers.
Encrypted vault app with a fully on-device AI assistant, private browser and camera that saves directly into the vault.
Watch out · Version 2.0 launches on the App Store July 30th; currently available via TestFlight.
FreeWorks offline
What to know▼
How it works
Encrypted vault with a fully on-device AI assistant for chat, summarizing, and image generation with zero internet; combines private storage, a tracker-blocking browser, and a camera that saves straight into the vault.
What's different
AES-256 encryption with no vendor key or backdoor; optional cloud AI (OpenAI/Gemini/Anthropic) is off by default.
Pricing
Free on iOS.
Watch out
Version 2.0 launches on the App Store July 30th; currently available via TestFlight.
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.
Lets you play Texas Hold'em against or watch several AI models (Claude, ChatGPT, Gemini, Grok, DeepSeek) bluff and bet against each other in real time.
Free
What to know▼
How it works
bring your own API key to play or spectate model-vs-model poker
We check every product on this page once a day and record whether it still answers.
An offline AI companion app for people who want an ongoing personalized chat relationship without their conversations ever leaving their own computer.
Works offlineData stays with you
What to know▼
How it works
A desktop AI companion for Mac and Windows that runs entirely offline, remembering past interactions and learning about the user over time to build a personalized relationship.
What's different
All processing happens locally on the machine rather than in the cloud.
Pricing
No recurring subscription fees.
Best for
People who want an ongoing personalized AI companion without their conversations leaving their computer.
We check every product on this page once a day and record whether it still answers.
An iPhone and iPad code editor with syntax highlighting, SSH/SFTP server access, Git management, live web project preview, and an on-device AI chat that works fully offline.
No sign-upWorks offlineNo subscription
What to know▼
How it works
Connects to servers over SSH/SFTP, manages Git repos, previews web projects live, and runs an AI chat 100% on-device.
Pricing
No subscription.
Best for
Developers who want to edit and manage code from an iPhone or iPad without a cloud dependency.
We check every product on this page once a day and record whether it still answers.
A free desktop chatbox for running local open-source models (Llama, Mistral) or plugging in your own API key for GPT, Claude, or Gemini, instead of paying for a hosted AI subscription.
FreeNo subscription
What to know▼
How it works
Runs Llama, Mistral, and other models locally for free, or connects your own API key for GPT-5, Claude, and Gemini in one app.
We check every product on this page once a day and record whether it still answers.
Turns a screen recording or a prompt into a narrated, edited video grounded in your company's own docs via MCP connectors, then localizes it into 25+ languages.
What to know▼
How it works
Turns a screen recording or a text prompt into a narrated, edited video: Velo writes the script, narrates it in your own voice, and builds the finished cut, staying grounded in your company's docs and tools connected via connectors and MCP.
What's different
Grounds itself in your actual company knowledge through MCP connectors, and localizes the finished video into 25+ languages in one click.
Best for
Teams that need training or sales videos built from their own docs and product knowledge, not generic stock-style videos.
We check every product on this page once a day and record whether it still answers.
Say gm to AI | One private API for Claude, GPT & Gemini
What to know▼
How it works
OpenAI uyumlu tek uç noktadan Claude, GPT ve Gemini'ye bağlanırsınız; gateway donanım imzalı enclave içinde çalışır, açık modeller de enclave içinde çalıştığı için istem kimse tarafından görülmez.
What's different
OpenRouter'a göre daha ucuz ve donanım seviyesinde doğrulanabilir gizlilik iddiası var.
We check every product on this page once a day and record whether it still answers.
A locally-run personal AI assistant that automates tasks, writes code, manages workflows, and generates UGC-style videos and speech, with optional cloud model support.
Works offline
What to know▼
How it works
Runs an AI assistant locally (with optional cloud models) that automates tasks, writes code, manages workflows, and creates UGC videos plus TTS/STT.
We check every product on this page once a day and record whether it still answers.
A fully on-device AI app for Android — chat, vision, voice and image generation that runs offline with no cloud calls, translated into 11 languages.
Works offline
What to know▼
How it works
A fully on-device AI app for Android offering offline chat, vision, voice input, offline text-to-speech, file attachments, AI agents and on-device image generation, with CPU/GPU acceleration via Vulkan and OpenCL and UI translations in 11 languages.
What's different
Runs entirely on-device with no cloud calls.
Best for
Android users who want private AI features without sending data off their phone.
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 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.
An offline AI chat companion that runs fully on-device with no account, cloud sync or ads — explicitly not a therapist or productivity tool, just a private space to think out loud.
No sign-upWorks offlineNo ads
What to know▼
How it works
An AI chat companion that runs entirely on-device for calm, private conversations, with no registration, cloud connection, or internet needed; it remembers past conversations and adapts over time.
What's different
Explicitly not positioned as a therapist or productivity tool — it's built to just be a quiet, non-judgmental presence, with no ads or notifications.
Best for
People who want a private space to think out loud without their conversations leaving their device.
We check every product on this page once a day and record whether it still answers.
A local tool that runs multiple AI models on your own hardware and has them compete or deliberate to pick the best answer, so no data leaves your device.
Works offline
What to know▼
How it works
Runs 4 AI models locally, routing simple questions to a fast model and complex ones to a full deliberation where models compete; includes Sequential Mode (draft/critique/refine), Compare Mode, and a routing transparency panel.
Pricing
Beta: $3 USD.
Best for
People wanting multi-model AI answers without sending data to the cloud.
We check every product on this page once a day and record whether it still answers.
A privacy-first AI workspace combining Gemini and Ollama with local RAG for chatting over your own documents.
Nothing to installData stays with you
What to know▼
How it works
Combines Google Gemini, Ollama, and Local RAG into one application so users can chat with their own documents, switch between cloud and local AI models, and build reusable prompt libraries.
What's different
Keeps data under user control via browser-based storage and backup.
We check every product on this page once a day and record whether it still answers.
A Mac dictation app that turns your voice, screenshots, and screen recordings into a clean AI-ready Markdown prompt for Claude Code, Cursor, or ChatGPT, running fully offline via local Whisper.
Works offline
What to know▼
How it works
Local Whisper and open models on a Mac turn voice, screenshots, and screen recordings into a clean Markdown prompt.
Best for
Developers using Claude Code, Cursor, or ChatGPT who want offline, private dictation without per-token billing.
We check every product on this page once a day and record whether it still answers.
Local-first multi-agent runtime binary usable from terminal, scripts, or HTTP, with editable agent "constitutions" and tool allowlists.
Works offline
What to know▼
How it works
A single native binary agent runtime usable from the terminal, scripts, or over HTTP, with agents living in editable "constitutions" that enforce hard tool allowlists.
What's different
Local-first with network use optional.
Best for
Developers building multi-agent workflows who want local control over tool access.
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.
A free Chrome extension that automatically sorts your open tabs into labeled groups by category, Development, Docs, Shopping, Social and more, with one click and no configuration.
FreeWorks offline
What to know▼
How it works
A Chrome extension that automatically organizes open tabs into labeled groups with one click, either by category (20+ categories like Development, AI Tools, Finance) or by domain (all tabs from the same site grouped together).
What's different
A 'Smart Group with AI' mode uses Chrome's built-in on-device AI (Prompt API) to read tab titles and page content and group by actual meaning rather than fixed rules, falling back to rule-based grouping otherwise.
Pricing
Free.
Best for
Chrome users who accumulate many open tabs and want them sorted without manual setup.
We check every product on this page once a day and record whether it still answers.
A free suite of 50+ browser-based tools for PDFs, images, documents, and code, including AI features like background removal and OCR, for people who want quick private tools without creating an account.
FreeNo sign-up
What to know▼
How it works
Over 50 fast tools for PDFs, images, documents, and code, most running in the browser including AI background removal and OCR.
We check every product on this page once a day and record whether it still answers.
Runs speech and visual AI models locally to auto-generate YouTube chapter timestamps — free, no upload, no signup, built for YouTubers who don't want to type timestamps by hand.
Watch out · The 18/19 accuracy figure comes from a single 68-minute test video, not a broad benchmark.
FreeNo sign-upWorks offline
What to know▼
How it works
You upload a video and it uses Whisper for audio and Moment-DETR for visual analysis to detect natural chapter breaks, then outputs timestamps to paste into a YouTube description.
What's different
Cross-validates chapter breaks using both audio (Whisper) and visual detection, rather than relying on one signal; on a 68-minute test video it got 18 of 19 chapters correct.
Pricing
Free, no signup.
Best for
YouTubers who don't want to manually type out chapter timestamps.
Watch out
The 18/19 accuracy figure comes from a single 68-minute test video, not a broad benchmark.
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.
Benchmark database showing which open-weight AI models run on which consumer GPUs, with install recipes and a GPU advisor.
FreeNo sign-up
What to know▼
How it works
Provides honest benchmarks for 84 open-weight AI models across 27 consumer GPUs from RTX 3060 to Apple Silicon, each pair rated as runs, tight fit, or won't fit with real speed and VRAM numbers, plus 800+ step-by-step install recipes for llama.cpp, Ollama, ComfyUI, and MLX, and a GPU Advisor.
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.
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.
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.
Every number here comes from our own daily check — not from a vendor list.
Tools that run AI locally — how many are there?
Tablif is tracking 231 of them. 228 answered our check today, and 1 we couldn't reach — we don't claim those are dead.
Which ones are still maintained?
Tablif knocks on every door once a day and records the answer. 228 of these 231 responded on the latest run, so that number is what "still here" means on this page — not a review score.
Are any of them free?
47 of the live ones say so in their own words, and 37 let you start without making an account. Tablif records the claim the product makes; we don't verify pricing.
Any open-source options?
43 of the live ones on Tablif mention being open source.
What's the newest one?
FutureScope AI™ 2.0 — Tablif first saw it 2 days ago.
Did a person actually look at these?
231 of them Tablif opened and read, then wrote a one-line summary in our own words instead of reusing the founder's tagline. The rest carry keyword labels we haven't confirmed by reading yet — and we say so rather than hiding it.
.png){kind=small}
