Local & Self-Hosted AI Tools

GTE is Alibaba's family of text embedding models for developers building semantic search and text matching into applications. The models turn text into vectors that let an application compare queries with documents by meaning.

AQBot is a desktop AI workspace for people who want model chat, coding agents and document search in one app. It keeps application data and user files locally, while requests to cloud models go to their providers.

Memanto is a companion memory agent for developers whose AI assistants lose project decisions and preferences between sessions. It manages shared knowledge across tools such as Claude Code, Cursor and Codex, then briefs agents when they start work.

Janus-Pro is a multimodal AI model for developers and researchers who want to interpret images and generate pictures on their own hardware. It combines both tasks in one model.

Elia is a keyboard-focused terminal chat client for people who prefer to keep AI conversations alongside their command-line work. It connects to local LLMs and cloud services through the same interface.

HotClip turns long recordings into short vertical videos for creators editing livestreams, podcasts, courses and spoken presentations. It suggests highlights with reasons and scores, so you can review the selections before exporting.

Short Video Factory is a desktop app that edits and renders supplied footage locally on Windows, macOS and Linux. It helps creators produce product marketing clips and topic-based short videos in batches. Script generation uses a configured OpenAI-compatible API; remote providers receive those prompts. EdgeTTS narration uses Microsoft Edge’s online speech service.

Scira is an AI search engine for researching questions across live sources and checking the evidence behind an answer. You can self-host the application, but live research needs internet access and external services.

Soundlabs MicDrop is a proprietary audio plug-in that transforms a voice or instrument performance into another voice or instrument sound. Producers can use its model library for singing, narration, synthetic vocal effects and vocal-controlled instrument parts. Model packs extend the available sounds within the same application.

Paperwise turns PDFs, scans and records into a searchable library for people managing private documents. It answers questions across files and links its answers to the source pages so you can check the evidence.

Handy is a desktop speech-to-text app for people who want to dictate into the apps they already use. It transcribes speech on your computer and inserts the text into the active text field.

AgentField is a self-hosted AI agent platform for developers building services that need to coordinate tasks under shared access rules. It combines execution, identity and audit records in infrastructure you control.

Aiden is a local AI agent for people who want help carrying out coding, research, and file management tasks. It plans multi-step work and keeps records you can inspect to check what happened and whether the result meets the goal.

node-llama-cpp is a library for developers adding local AI to JavaScript and TypeScript applications. It uses llama.cpp to run GGUF models on your hardware and works in Node.js, Bun and Electron.

Moltis is a personal AI agent server for people who want an assistant that remembers earlier conversations and carries out tasks on their own hardware. You can reach the same agent through a browser or messaging apps.

OwnOrbit AI, formerly LifeOS AI, is an alpha self-hosted personal AI assistant for people who want help finding forgotten commitments in their own notes. It reads a Markdown folder you control and can surface deadlines, renewals, and unfinished work. The assistant runs on your computer, with a paired mobile browser app for phone access.

Skill Seekers prepares documentation and code for AI assistants. It's for developers and teams who want reusable skills, coding context or retrieval-augmented generation (RAG) data without preparing the same sources separately for each tool.

WebOperator is an AI browser agent for automating tasks in the Chrome tabs you already use. It retains your existing logins and sessions, and can use a local model or a remote provider.

Context7 is a locally runnable MCP server and CLI that connect coding assistants to its hosted documentation service. It's for developers who want library references and code examples in their assistant's context. The local component is the connection to that service: the API backend, document parsing and crawling engines remain private hosted components.

Usertour helps teams build in-app guidance for browser applications. It's an alternative to Appcues and Userflow for teams that want to host their onboarding platform themselves.

sonible pure:level is a proprietary AI audio leveling plugin that runs in a DAW on macOS or Windows. It's for music producers and creators working with vocals, dialogue or instruments whose volume varies across a recording. It combines level stabilization with level riding to keep tracks steady in a mix while preserving the performance's natural dynamics.

OpenViking is a self-hosted context database for developers who want AI agents to retain preferences and task experience across sessions. Its open source server runs on your own machine or server, including Docker deployments. It needs embedding and vision-language models, with support for local Ollama and cloud providers such as OpenAI and Volcengine; self-hosting the database alone doesn't keep model requests local.

TripoSG generates 3D meshes from visual references for people creating 3D assets or testing shape ideas. It accepts finished images as well as rough scribbles paired with a text prompt.

NeMo RL is NVIDIA's Python library for researchers and engineering teams adapting language and multimodal models on their own hardware. It supports experiments on a GPU workstation and distributed training across multiple nodes.

Apache TVM is a machine learning compiler for developers optimizing models for deployment on their own hardware. It compiles model computations into modules that applications can embed, with targets spanning data center GPUs and edge devices. Code is licensed under Apache 2.0.

Vela is a desktop AI writing editor for novelists and web fiction authors who need to manage a long story's characters, settings and chapters. It brings planning, drafting and revision into one workspace.

Reverify helps developers and reverse engineers check AI-generated claims against actual binary files and code behavior. It returns verified, refuted or inconclusive verdicts with evidence, so an assistant's proposed explanation can be checked before you rely on it.

Enclave AI is a local AI assistant for people who want to chat, work with documents or use voice conversations on their Apple devices. Downloaded models handle these tasks offline.

Nextcloud Assistant brings AI tasks into Nextcloud Hub for teams working with shared files, email and conversations. It lets an organization choose local processing on its own server or a hosted model provider.

Willow Inference Server is a self-hosted speech server for developers building voice assistants, transcription apps, and accessible interfaces. It handles speech recognition and speech generation on your own hardware.

Zerobox is a local process sandbox for developers running AI agents, generated code, builds or tests with restricted access to their machine. It builds on OpenAI Codex's sandbox runtime and can contain a whole agent or individual tool calls.

Noted is a desktop notebook for people who want connected notes and AI help while keeping their writing in ordinary Markdown files. Notes live in a folder on your machine, where other editors and backup tools can use them.

ECA is an AI coding assistant for developers who want to use their chosen models across different editors. It brings coding help into the editor while keeping the same settings across supported clients.

Agentic Security is an LLM vulnerability scanner for developers, researchers and security teams testing AI models and agent workflows. It probes how systems respond to hostile inputs and attempts to bypass their safety controls.

Nanobrowser is a browser AI agent for people who want to delegate repetitive web tasks and research. It carries out actions inside the browser while letting you choose the models that handle the work.

BabyAGI is a self-hosted Python framework for experienced developers exploring AI agent development. Its local application manages reusable code and provides a browser dashboard. Functions can depend on external services and API keys, including an OpenAI API key.

quackd lets robot builders give language-based goals to robots with existing movement and manipulation skills. It runs the planning on a computer while the robot's own controllers carry out the actions. Real-hardware use covers the LeRobot SO-101 arm; the other adapters have only run in simulators or mocks.

Data Formulator is a local AI data analysis workspace for analysts who want to explore questions through charts and keep track of alternative investigations. This Microsoft Research project combines natural language requests with direct chart editing. You can revisit an earlier result and branch into a different analysis without losing the original path.

Bolt.diy is an AI coding assistant for building full-stack Node.js web applications with your choice of model. It's a fork of Bolt.new that combines generated code with an editable development workspace.

Jev Chat helps people interpret tense or ambiguous conversations and choose a reply. It estimates the other person's intent and the risk of friction before suggesting wording, though its assessments can be wrong.

Framelink MCP connects Figma designs to AI coding agents so developers can implement interfaces using their project's own components and conventions. It supplies design details without prescribing a framework or generated code.

TruLens helps developers assess AI agents and retrieval-augmented generation (RAG) apps, then trace poor results to the steps that caused them. It connects evaluation scores with execution traces so teams can compare changes in quality, latency and cost.

Aphelion is a desktop app for people who want character conversations, creative writing and coding help from models running on their own computer. It works offline after the first model download and doesn't require an account.

Claude Code Local lets developers use Claude Code with a model running on their own computer. It suits people who want to keep coding offline or continue working when they hit cloud usage limits.

Eclaire is a self-hosted AI assistant for people who want to ask questions about their saved information and act on it in one place. It brings documents, notes, photos, bookmarks and tasks into a shared library.

DiffusionBee is an AI image app for Mac users who want to create and edit artwork locally through a visual interface. Artists and designers can work with text prompts, existing images and drawings without writing code.