Tools that run models locally with Ollama

We're tracking 37 of these, and 34 are still live today. 2 we couldn't reach — we don't claim those are dead.

Watching this group for 18 days · how we check

This week14 new arrivals1 stopped answering

Narrow it down

Free12 No sign-up3 Works offline8 Open source12 Data stays with you5 No subscription4

FluentDB

Live

An AI-assisted SQL client for developers who want query help without sending their actual data to a cloud model.

Data stays with you

What to know▼

How it works: Models see your schema, not your data; every AI-generated SQL query requires approval by default.
Best for: Developers using Postgres/MySQL/SQLite/SQL Server on Mac.
Watch out: Mac-only for now.

Watched for 2 days · last checked 2d ago

SiteQuest

Live

A desktop overlay browser for Windows and macOS that pops up over any app with a hotkey, so you can check a site or AI tool without switching windows.

What to know▼

How it works: global hotkey opens a browser overlay on top of your current app
What's different: works alongside your existing browser rather than replacing it; supports local Ollama or cloud AI

Watched for 5 days · last checked today

Batuk is a sovereign AI chat workspace

Live

Gives teams a sovereign AI chat workspace connecting multiple models instead of depending on one vendor's cloud.

Open source

Watched for 1 day · last checked 1d ago

TradeHelp

Live

A local-first trading journal with an offline AI coach that reviews your trades and notes to flag costly habits, for traders who don't want their data on someone else's server.

No sign-upWorks offlineNo tracking

What to know▼

How it works: stores trades and notes in a single local file; AI coach runs against a local model (Ollama, LM Studio)
What's different: open source so the no-cloud claim is verifiable, plus a 'Leak Finder' that prices out bad habits
Best for: prop-firm traders needing drawdown and payout tracking

Watched for 5 days · last checked today

BDFL - Benevolent Delegator for LLMs

Live

Open-source terminal supervisor that manages planning and worker AI agents for Codex, Claude Code, and Ollama sessions.

Open source

What to know▼

How it works: An open-source terminal supervisor where a planning agent proposes versioned plans you approve, then isolated worker agents implement the work while it handles scheduling, review, and recovery.

Watched for 4 days · last checked today

LayerAI

Live

A Chrome extension that batch-translates web pages with AI drafts you finalize and reuse, using BYOK or local Ollama.

Works offline

What to know▼

How it works: A local-first Chrome extension that collects text, batch-drafts AI translations, and auto-applies your finalized translations on revisit.
What's different: Keeps editable translation assets, glossary control, a background queue for large sites, and supports BYOK or local Ollama.

Watched for 5 days · last checked today

Melaya Device Control

Live

A visual builder that gives AI agents (Claude Code, GPT, Ollama) approval-gated control of your phone's apps.

What to know▼

How it works: A visual builder that gives AI agents (Claude Code, GPT, Ollama) control of your real phone apps, requiring your approval on every action.

Watched for 4 days · last checked today

MoilStack .md (markdown)

Live

A desktop Markdown editor with AI-assisted editing, built-in Ollama integration, and automatic local backups.

Domain registered 6 months ago

What to know▼

How it works: Markdown editing with live preview, built-in AI editing, and automatic backups on the desktop.
Best for: People wanting a private-feeling Markdown editor with AI editing help.
Watch out: The tagline advertises OpenAI integration alongside Ollama, which sits at odds with the description's claim that everything runs privately with no cloud accounts.

Watched for 7 days · last checked 1d ago

Make Claude Code cheaper and smarter

Live

A lightweight proxy that sits in front of coding-agent tool calls to block repetitive failing calls, mutate strategy when the agent is stuck, and compress bloated tool outputs, working across Claude, OpenAI, DeepSeek, Ollama, and OpenCode.

What to know▼

How it works: Runs as a background proxy (installed via pip) that detects and blocks repetitive failing tool calls, mutates strategy on loops, and compresses tool outputs, with a real-time dashboard and savings report.
Best for: developers running coding agents who want to cut token waste and loops.

Watched for 18 days · last checked today

Jharu -A disk cleaner that can think.

Live

Free disk cleaner for your AI model and dev caches

FreeOpen sourceNo tracking

What to know▼

How it works: AI model önbellekleri ve geliştirici çöplerini tanıyıp gigabaytlarca yer açar; telemetri yok, kalıcı silme yok.
What's different: Ücretli CleanMyMac'e karşı ücretsiz alternatif.

First seen today · last checked today

LLMconfigurator.com

Live

A free tool that checks whether a given GPU can run specific local LLMs and estimates VRAM usage and cloud-vs-local cost.

Domain registered 8 months ago

Free

What to know▼

How it works: compares GPU specs against 75+ models and includes setup guides for tools like Ollama and LM Studio
Pricing: free
Best for: people deciding whether their hardware can run a local LLM

Watched for 11 days · last checked 5d ago

Freebird AI

Live

A free, lighter AI coding assistant built for indie developers and small teams as an alternative to Cursor and Copilot, running fully private and local via Ollama.

Free

What to know▼

How it works: Multi-file agent mode, inline edits, semantic codebase search, and AI commit messages, running fully private and unlimited via Ollama.
Pricing: 20 real AI edits/day forever free; Pro $6/mo or Team $25/mo for more.
Best for: Indie developers and small teams who want an AI coding assistant without enterprise pricing or throttled quotas.

Watched for 12 days · last checked 6d ago

TokenAssemble

Live

Tells you which local LLMs your specific GPU or Mac can actually run before you download a model, based on VRAM/memory and quantization.

What to know▼

How it works: Checks hardware specs against model requirements for tools like Ollama, LM Studio, llama.cpp, vLLM
Best for: People running local LLMs who don't want to guess at hardware fit

Watched for 6 days · last checked 5d ago

VRAM Shield

Live

A lightweight Windows utility monitors and manages GPU memory temperature during AI inference or gaming, for owners of high-performance laptops trying to avoid thermal throttling.

Domain registered 5 months ago

FreeNo subscription

What to know▼

How it works: Monitors GPU memory junction temperature via low-level hardware telemetry and applies software-defined duty-cycling (millisecond-level pulse throttling) to prevent thermal-driven performance drops during AI inference or gaming.
What's different: Targets memory junction temperature specifically, which standard tools like MSI Afterburner only tune for the GPU core, not the memory hotspot that triggers emergency throttling.
Pricing: Pulse Throttling is free.
Best for: Owners of high-performance gaming or AI laptops running sustained local inference (Stable Diffusion, llama.cpp, Ollama) who see performance drop from memory overheating.

Watched for 9 days · last checked 9d ago

Pudding

Live

A local-first macOS AI workspace that combines chat, a shared canvas, browser, terminal, and widgets in one place, letting you connect your own API keys for various AI providers.

What to know▼

How it works: Each session keeps its own context and tools while results stay visible on a shared canvas; connects to OpenAI-compatible APIs, OpenRouter, DeepSeek, Gemini, Ollama, and more with your own credentials.
Watch out: Public preview, macOS only, and described as local-first rather than fully offline since it can call external AI APIs.

Watched for 11 days · last checked 8d ago

PopGuy

Live

A Mac text-selection toolbar that improves, translates, defines, or runs custom AI actions on selected text, using your own AI key or fully local models via Ollama.

FreeNo subscription

What to know▼

How it works: Select text in any Mac app, use the floating toolbar to run built-in or custom AI actions, either with your own API key or 100% locally through Ollama or built-in models.
Pricing: Free tier included; one-time $15 Pro upgrade, no subscription.

Watched for 12 days · last checked 8d ago

Codeteel

Live

A self-hosted, open-source AI coding agent that runs on your local Ollama models and can be driven from Slack, Telegram, Discord, or the web, with human-in-the-loop plan approval before it edits code.

FreeData stays with youOpen sourceSelf-hosted

What to know▼

How it works: Uses a ReAct architecture with human-in-the-loop plan approval, deterministic edits, and PR creation; supports DeepSeek, Llama, Qwen, Mistral, OpenAI, Claude, and Gemini models.
Pricing: Free and open source.

Watched for 12 days · last checked 9d ago

Askora Cloud

Turns your website, PDFs and docs into a RAG-powered AI chatbot deployed in minutes — answers sourced only from your own content, captures leads 24/7, and can self-host with Ollama for full data privacy.

Self-hosted

First seen today

ShadowLock

Live

Detects and blocks risky use of AI tools (ChatGPT, local LLMs, desktop AI apps) on company devices before sensitive data leaves the endpoint, for MSPs and IT teams.

What to know▼

How it works: Browser extension classifies risky pastes to AI sites; Windows agent blocks desktop AI apps via existing RMM; multi-tenant dashboard for auditing
Best for: MSPs and IT teams managing AI usage risk across client devices
Watch out: Windows agent only currently

Watched for 6 days · last checked today

Smeltcore

Live

Benchmark database showing which open-weight AI models run on which consumer GPUs, with install recipes and a GPU advisor.

Domain registered 2 months ago

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.
What's different: No invented numbers.
Pricing: Free under CC BY-SA, no signup.

Watched for 9 days · last checked 3d ago

Linggen

Live

An open-source Mac app that runs local AI mini-apps, including a private finance analyzer that redacts data before AI sees it.

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.
Watch out: macOS only.

Watched for 8 days · last checked 6d ago

Willow

Live

A local-first Mac AI agent you own outright for a one-time fee, using your own API key or a fully offline Ollama model, built for technical builders.

Domain registered 1 month ago

Works offlineNo subscription

What to know▼

How it works: A local-first desktop AI agent that runs on your Mac, can drive the browser and desktop, and completes multi-step tasks while data stays on-device.
What's different: A one-time lifetime fee instead of a subscription, with your own API key/model or a fully offline Ollama setup.
Pricing: €299 lifetime, no subscription.
Best for: Technical builders who want to own their AI agent outright rather than rent a cloud subscription.

Watched for 14 days · last checked 8d ago

Atlarix

Live

A desktop coding harness built specifically around open-weight models like DeepSeek, Qwen and Kimi, instead of bolting them onto a Claude or GPT-first interface as an afterthought.

FreeWorks offline

What to know▼

How it works: A desktop AI coding harness built around open-weight models (DeepSeek, Qwen, Kimi, MiniMax) instead of Claude/GPT, using a structural + lexical code-retrieval engine (Blueprint) that builds a real dependency graph of the codebase rather than embeddings or a vector DB.
What's different: Built specifically for open-weight models' weaker context discipline, instead of treating them as an afterthought behind a Claude/GPT-first interface.
Pricing: Free.
Best for: Developers who want to use open-weight models like DeepSeek, Qwen, or Kimi for coding with retrieval built for their limitations.
Watch out: Depends on local tools like Ollama and MCP — offline/no-cloud setup requires configuring those dependencies yourself.

Watched for 18 days · last checked 2d ago

growths.dev

Live

A guide site teaching setup of Claude Code, Codex, OpenRouter, and local LLMs like Ollama.

Domain registered 2 months ago

Free

What to know▼

How it works: Beginner-friendly guides covering how to install Ollama, run LLMs locally, and set up Claude Code, Codex, and OpenRouter.
Pricing: Free.

Watched for 9 days · last checked 6d ago

Adaptora - Open Source

Live

A self-hosted agent that lets you talk to any REST API in plain English through its MCP layer, using your own LLM such as Ollama — built for developers.

Open sourceSelf-hosted

What to know▼

How it works: A self-hosted agent with an MCP layer that lets you talk to any REST API in natural language, using your own LLM (e.g. Ollama) instead of a hosted one.
What's different: Bring-your-own-LLM and fully self-hosted, so API credentials and data stay under your control.
Best for: Developers who want to interact with REST APIs conversationally while keeping their own LLM and data ownership.

Watched for 18 days · last checked 3d ago

EchoFlow

Live

A native Android AI chat app that keeps your conversation history stored locally on the device instead of the cloud.

No sign-upData stays with youOpen sourceSelf-hosted

What to know▼

How it works: A native Android AI chat app.
What's different: Chat history is stored locally on the device rather than in the cloud.
Best for: Android users who want an AI chat app without their conversations stored in the cloud.

Watched for 18 days · last checked 10d ago

Vellium

Live

A free, open-source desktop app for AI character chat, roleplay and long-form writing, where your data stays in a local database even with a cloud AI backend.

FreeWorks offlineOpen source

What to know▼

How it works: A desktop AI workspace for character chat, multi-character roleplay, and long-form writing with RAG, LoreBooks, and MCP tools and plugins; you bring your own backend, such as OpenAI-compatible APIs, OpenRouter, LM Studio, Ollama, or KoboldCpp, while chats, characters, projects, and knowledge are stored in a local SQLite database.
What's different: Keeps your data in a local database even when you connect a cloud AI backend, and is free and open source.
Pricing: Free and open source.
Best for: Writers and roleplayers who want to choose their own AI backend while keeping their data local. Native builds are available for macOS, Windows, and Linux.

Watched for 14 days · last checked 3d ago

Interview Coach

Live

An open-source mock-interview app that can run entirely on your own local LLM for privacy - setup and model choice will suit technical users most.

Domain registered 8 months ago

Works offlineOpen source

What to know▼

How it works: Runs mock interview practice with voice conversations and instant feedback, using OpenAI, Anthropic, Gemini, Groq, or a local Ollama model for fully offline use.
What's different: Can run entirely on a local LLM via Ollama for complete privacy and offline use, unlike cloud-only interview tools.
Best for: Technical users comfortable choosing and configuring their own AI model, including those who want offline privacy.

Watched for 13 days · last checked 7d ago

ZettelkastenAI

Live

Connects your Obsidian vault to any AI provider (OpenAI, Anthropic, Ollama or compatible) for chat over your notes, semantic search, auto-generated Zettelkasten notes and custom commands.

What to know▼

How it works: Connects an Obsidian vault to any AI provider (OpenAI, Anthropic, Ollama, or any OpenAI-compatible endpoint) to chat with your notes via RAG, run semantic search, auto-generate atomic Zettelkasten notes, and run custom commands.
What's different: Works with any AI provider including locally-run Ollama models, not locked to one vendor.
Best for: Obsidian users practicing the Zettelkasten note-taking method who want AI-assisted search and note generation over their own vault.

Watched for 16 days · last checked 10d ago

WisprFree

Live

A voice-to-text app that transcribes on-device and optionally cleans up grammar with a user-chosen AI, positioned as a free alternative to Wispr Flow.

FreeWorks offlineOpen source

What to know▼

How it works: Transcribes speech on-device (Parakeet/Whisper/Cohere), then optionally uses a chosen AI (Gemini, OpenAI, OpenRouter or local Ollama) to remove filler words and fix grammar; API keys stay in the Keychain.
What's different: Positioned as a free alternative to Wispr Flow, fully offline if you skip the AI cleanup step.
Pricing: Free, open-source.
Best for: People wanting private voice-to-text across any app.

Watched for 3 days · last checked 1d ago

Mutagen

Live

Open-source agentic AI fuzzer that finds bugs across languages and generates verified security patches automatically.

Open source

What to know▼

How it works: Uses a multi-agent LLM swarm to analyze source code or decompiled binaries, synthesize payloads, reproduce crashes and generate verified security patches automatically.
What's different: Supports C/C++, Rust, Python, Go, JS/TS and multiple LLM providers including Gemini, Claude, OpenAI and Ollama.
Pricing: Free, open-source.
Best for: Security researchers and developers doing automated fuzzing and patching.

Watched for 3 days · last checked 1d ago

Oryn

Live

A desktop AI coding agent for Windows that writes code from plain-language instructions, using your own AI key or a fully local Ollama model.

Works offlinePay onceNo subscription

What to know▼

How it works: Reads your codebase and writes code from plain-language task descriptions on Windows.
What's different: Works with your own AI key or fully local via Ollama.
Pricing: One-time payment, no subscription.
Best for: Developers on Windows who want a desktop AI coding agent.
Watch out: Windows only.

Watched for 18 days · last checked 4d ago

Eudora

Live

Logs and HMAC-verifies every AI agent action with an approval workflow, so enterprises can prove AI governance under the EU AI Act and DORA to auditors.

What to know▼

How it works: Logs every AI agent action with a timestamp, human owner attribution, and HMAC integrity verification, routing agents through an approval workflow before they reach production and generating compliance reports for EU AI Act Article 50 and DORA audit mandates.
What's different: Also does DLP scanning to catch credentials and PII before the model sees them, plus real-time policy enforcement and prompt injection detection.
Best for: Enterprises that must demonstrate AI agent governance to regulators and auditors under the EU AI Act or DORA.
Watch out: Works with OpenAI, Anthropic, Google Gemini, Azure OpenAI, and Ollama — check it covers whichever model providers your agents actually run on.

Watched for 18 days · last checked 10d ago

NudgeFile

Live

A Windows app that auto-sorts, renames and routes your Downloads, Screenshots and Documents using local AI via Ollama — nothing leaves your device.

Data stays with you

What to know▼

How it works: A Windows desktop app that watches selected folders and automatically renames, sorts and routes files using local AI, with duplicate detection and undo-safe operations.
What's different: Runs entirely on-device through Ollama rather than sending files to the cloud.
Best for: Windows users with messy Downloads, Screenshots or Documents folders who want automatic organization without a cloud service.
Watch out: Requires a local Ollama installation to power the AI features.

Watched for 14 days · last checked 3d ago

VeritasGraph

Live

An open-source, fully on-prem GraphRAG framework combining knowledge-graph reasoning with governed AI agents that cite every answer, for teams that can't send data to the cloud.

Open sourceSelf-hosted

What to know▼

How it works: An open-source, on-prem GraphRAG framework combining tree-search navigation with knowledge-graph reasoning so an LLM answers multi-hop questions and cites every claim to its source; VeritasGraph Studio wires the knowledge graph into governed AI agents with guardrails, memory, tools and MCP bridges.
What's different: Runs 100% on-prem via Ollama with no data egress, and ships an MCP server plus a deterministic policy engine.
Pricing: Open-source.
Best for: Teams that need multi-hop, source-cited RAG answers but can't send data to the cloud.

Watched for 15 days · last checked 3d ago

Bonacci Studio

An agentic data engineering platform that connects to your database, writes and runs PySpark/SQL, and includes a visual DAG builder.

What to know▼

How it works: An agent connects to a database, inspects schemas, writes PySpark or SQL, executes it on Spark, streams logs back, and debugs its own failures; also includes a visual drag-and-drop DAG builder, Kafka streaming, Apache Camel API integration, RAG knowledge bases, and native MCP support, letting users bring their own model (Claude, GPT, Gemini, Groq, or local via Ollama).
What's different: Goes beyond generating a code snippet — it actually runs and debugs the code itself.

Watched for 9 days

DreamerSky AI Workspace

Not responding

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.

Watched for 10 days · last checked today

Tools that run models locally with Ollama — the short answers

Every number here comes from our own daily check — not from a vendor list.

Tools that run models locally with Ollama — how many are there?: Tablif is tracking 37 of them. 34 answered our check today, and 2 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. 34 of these 37 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?: 12 of the live ones say so in their own words, and 3 let you start without making an account. Tablif records the claim the product makes; we don't verify pricing.
Any open-source options?: 12 of the live ones on Tablif mention being open source.
What's the newest one?: Jharu -A disk cleaner that can think. — Tablif first saw it today.
Did a person actually look at these?: 37 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.