Local & Self-Hosted AI Tools

Radiant Photo 2 is a paid AI photo editor for Windows and macOS that processes photos entirely on your computer. It's for beginners who want automatic corrections and photographers who need a starting point for manual editing or large batches. Photos never go to Radiant's servers or third-party cloud services.

GenericAgent runs tasks on your computer using cloud models to decide what to do. It's for people who want an AI agent to work across websites, files and desktop apps, then save successful workflows for reuse. Model calls require API keys and an internet connection, with requests going to the selected provider. It supports Claude, Gemini, Kimi and MiniMax.

Codeg is an AI coding workspace for developers who use several agents and want to coordinate their work without losing context between tools.

gptel is an Emacs LLM client for people who want model responses alongside their writing and code. It connects to local inference backends including Ollama, llama.cpp, Llamafile and GPT4All. The client runs in Emacs; cloud connections such as OpenAI, Anthropic and Gemini send requests to those providers and require their credentials.

Kokoro-FastAPI generates speech on your own machine or server using Kokoro-82M. It's for developers adding narration to reading apps, audiobooks or voice assistants through an OpenAI-compatible speech API.

Voicebox combines speech creation and dictation for people producing audio or working with AI agents. It's a free, open-source alternative to ElevenLabs and WisprFlow that processes voice data on your own machine.

OpenLLM is a self-hosted LLM server for developers connecting applications to models on their own hardware or servers. Its OpenAI-compatible interface lets existing clients use those models without adopting a separate API.

Memori's BYODB edition is a memory library for developers who want agents to retain context in their own SQLite file or self-managed database. It generates embeddings locally, but its default Advanced Augmentation sends conversation messages and summaries to Memori's cloud API for memory extraction. The documented OpenAI connection also sends model requests to OpenAI.

Wren AI is a self-hosted context and query engine for developers and data teams building AI analytics. It queries your databases using business definitions you control. Model execution depends on the connected agent: using Claude Code’s standard cloud connection sends prompts and model responses to its remote provider, even when Wren's engine runs on your servers.

CDAF saves reusable text descriptions alongside videos so AI agents don't have to analyze the same footage for every task. It's for developers building video agents and editors that repeatedly search or ask questions about a clip library.

digiKam is a free, open-source photo manager and image editor for photographers managing large collections of photos and videos. It combines library organization with editing and tools for finding images by their content or metadata.

Ralph TUI coordinates AI coding agents on your machine or servers as they work through a task backlog. It's for developers who want autonomous execution with progress and agent output visible in a terminal.

SurrealDB is a database for developers building AI agents, knowledge graphs and applications with several kinds of data. It lets application records and retrieval data share one engine.

Anarlog, formerly Hyprnote, is a desktop AI meeting notetaker for people who want to keep sensitive conversations on their own hardware. It's an open-source Granola alternative that combines personal notes with meeting transcripts.

Abogen turns books, documents and subtitle files into narrated audio for readers making audiobooks and creators producing voiceovers. It can generate matching captions or follow timestamps for timed narration.

Langflow is a visual builder for developers creating AI agents and applications that answer questions using connected data. It lets you assemble workflows visually and customize their components in Python.

Agenvoy is a personal AI agent for people who want to automate research, file work, and recurring tasks on their own computer. It runs continuously and retains context between sessions.

Codex Security is a locally run vulnerability scanner for developers and security teams, available as a CLI and TypeScript SDK. It can run on your machine, in CI or in containers, but sends AI analysis requests to a cloud model provider. Scans require provider credentials and an internet connection.

Waves Clarity Vx is a proprietary AI audio plugin for removing background noise from recorded voices. It handles both speech and singing, so it's relevant to music producers working on vocal tracks as well as podcast creators and video editors cleaning up dialogue.

funes gives coding agents a searchable memory of past work. It's for developers who want earlier decisions, reasoning and findings to remain available when they start another session or switch agents.

RipX DAW is an AI audio workstation for musicians and remixers who want to change individual sounds within a finished recording. It separates a mix into stems and extracts notes, harmonics and other sound components, letting you work below the level of an entire vocal or instrument track.

Riffado turns recordings from Plaud Note, Note Pro, and NotePin devices into searchable transcripts and summaries. It's for recorder owners who want control over AI processing and storage. Recording sync requires a Plaud account and access to Plaud's cloud, so the full workflow isn't offline.

GitHub MCP Server connects compatible AI assistants to GitHub so developers can ask about code and have an assistant act on repository activity. It's GitHub's official connector for the Model Context Protocol (MCP).

Chonkie is a library for developers preparing documents for retrieval-augmented generation (RAG). It brings document preparation and ingestion into one pipeline, with optional components to keep dependencies small.

XTuner is an LLM training engine for researchers working with very large mixture-of-experts (MoE) models. Its focus is reducing memory pressure and improving distributed training efficiency when model experts receive uneven workloads.

ACE-Step Studio is a desktop AI music generator for musicians and anyone who wants to create songs on their own hardware. It turns a short idea, or a description with lyrics, into a full vocal track or instrumental.

Mem0 provides a self-hosted memory server and libraries for developers whose AI applications need to remember user preferences and earlier interactions. The code is open source under Apache 2.0. Its default language and embedding models are OpenAI's gpt-5-mini and text-embedding-3-small, so self-hosting still sends model requests to OpenAI and requires internet access.

TrendRadar collects news and trending topics for people tracking public opinion, industry developments, or specific interests. It brings feeds and platform rankings into one place so you can follow relevant stories without checking each site separately.

nanobot is a self-hosted personal AI agent for people who want an assistant that can act on files and continue work across conversations. Its Python framework also suits developers building their own assistant integrations.

OLMo Core is a Python library for researchers and developers building and training OLMo language models. Its PyTorch components and official training scripts suit teams working with model training code on their own hardware or servers.

docuchat is a local AI document assistant for attorneys, especially solo and small firms working with confidential case files. It answers questions across contracts, pleadings, exhibits and transcripts, then checks cited quotes against the source text. Answers point to the file, page and exact passage; deposition citations include verified line numbers.

Spec Kit gives developers structured processes for working with AI coding agents. It turns requirements, assessments and verification results into project documents you can review alongside the code.

Octop is a self-hosted AI assistant for households and small teams that want personal agents in a shared deployment. Each user can switch between specialists with separate workspaces, model connections and scheduled tasks.

RealtimeTTS is a Python text-to-speech library for developers building voice assistants and other apps that need spoken responses before the full text is ready. It accepts both complete text and incoming LLM output.

FableCut is a local video editor for people who want to make cuts themselves and work alongside an AI agent. Both can edit the same project, with agent changes appearing live in the browser.

Whispering is a speech-to-text app for people who want to dictate text into other applications and choose where transcription happens. Its desktop app runs within Epicenter, but the project currently lists it at compile status after a storage migration.

Vocaldi is a paid Mac app that combines voice typing with read-aloud for people who prefer speaking to typing or listening to written text. Transcription, dictation cleanup and speech synthesis run on your Mac, so the audio and text you process stay on the device. It requires Apple Silicon and macOS 14 or later.

napari Chat Assistant brings local AI into the napari image viewer for researchers, imaging facility staff, and educators working with microscopy and multidimensional datasets. It uses the layers and regions of interest already open in your session to interpret requests and carry out analysis. Image data stays on your workstation.

Atomic is a personal knowledge base for people who want to find connections across their notes and saved reading. It organizes Markdown notes, web clips, and articles into a knowledge graph you can search and explore.

Mochi Diffusion is a native macOS app for people who want to generate images on their own Mac. Generation works fully offline, and the app sends no generation data to the cloud or collects telemetry.

Hollama is an LLM chat interface for people who want to use Ollama or OpenAI servers through a browser. It supports multiple server connections, so you can keep access to different model servers in one app.

Grist is a relational spreadsheet for teams building shared data tools beyond a flat grid. Linked tables, typed columns and custom layouts let users organize records into applications for their own workflows.

usecomputer lets AI agents interact with desktop applications through screenshots, mouse actions and keyboard input. It's for developers who want computer control in agent workflows, including those built around OpenCode or Claude Code.

Command A is an open weights language model from Cohere and Cohere Labs for researchers and developers building document assistants, chatbots and AI agents. It handles text input and output, with a focus on multilingual business tasks.

MCPHub is a self-hosted gateway for developers and teams connecting AI clients to multiple MCP servers. It gives them one place to manage shared tools and decide what each user or project can access.

Blue Iris is paid video security software for people managing cameras at home or on business premises. It runs on a Windows PC and combines recording, built-in AI services and remote viewing.