Local & Self-Hosted AI Tools

PhotoGlimmer is an AI photo editor for photographers who want to brighten underlit people without changing the whole image. It separates people from the background so you can correct portrait lighting while keeping the surrounding scene as it is.

Llama Guard is a family of AI content moderation models for developers who need to check what users submit to an LLM and what the model returns. It supports text and image checks for applications that accept more than written prompts.

Snowflake Arctic Embed is an open-source family of text embedding models for developers building semantic search and document retrieval. It represents queries and documents as vectors so a search system can match them by meaning.

CAMEL is a Python framework for developers and researchers building AI agent teams with models running locally through Ollama or through remote providers. Its Ollama integration connects agents to a local model service; choosing OpenAI instead sends model requests to OpenAI and requires an API key. The framework is open source under Apache 2.0.

Wake is a desktop app for developers who need to find past coding-agent conversations across tools. It gathers session histories into a library organized by project and agent.

Kodus is an AI code reviewer for engineering teams that want automated pull request feedback and control over where the reviewer runs. Its reviewer, Kody, checks changes in the context of the surrounding code.

Accentize dxSplit is an AI audio plugin for dialogue editors and post-production mixers who need to clean up speech recordings. It separates dialogue into voice, room reverb and background noise so you can adjust each component independently.

Laya brings work notifications into one feed for people managing email, tickets, pull requests, and team messages. It gathers related context and prepares action cards with drafts you can review before sending.

SwarmVault is a self-hosted knowledge base for people organizing research, notes or code documentation for themselves and AI agents. It turns collected sources into a persistent Markdown wiki with connections you can inspect.

Tesseract is an OCR engine for developers and document-processing workflows that need to extract text from images. It includes a command-line tool and an embeddable library, but doesn't include a graphical app.

Tutor-GPT is a self-hosted browser application for learners who want an AI tutor that adjusts to their learning needs. You can host its Next.js server yourself, including through Docker. Model responses come from a separate inference provider, with OpenRouter integration sending requests to an external service.

Haplo AI runs language models on iOS and macOS for people who want to ask questions, write code or examine photos without sending that material to a hosted assistant. After downloading a model, chat works offline without an account.

GFPGAN is an AI face restoration tool for repairing low-quality photos and adding restoration to image workflows. It reconstructs facial detail using a pretrained generative model, so results can alter a person's likeness.

Hovor is a dictation app for people who want to speak text into their Mac apps and choose between local speech recognition and a cloud service. On supported Apple Silicon Macs, it runs downloaded Parakeet or Whisper models on the device, so on-device transcription happens on your Mac.

Discourse AI adds community assistants, search and moderation to a Discourse forum you can host on your own server. It's for forum operators who want AI features inside their community site. Forum hosting and AI processing are separate choices: the plugin supports a choice of providers, and its AI API services have a self-hosting option.

claudectl manages multiple Claude Code sessions for developers who need to track parallel work and intervene when an agent gets stuck. Its terminal dashboard brings session activity, approvals and spending into one view.

Write-the is a locally installed Python command-line tool that sends code to a selected OpenAI or OpenRouter API to generate documentation and tests. It's for developers who want generated drafts alongside their codebase. The CLI handles local files while the selected provider handles generation.

Instructor is a library for developers who need to turn text into structured data using an LLM. Its focus is extraction, with typed outputs that applications can use and validation rules that check the model's responses.

DL4MicEverywhere lets microscopy researchers train and use deep learning models on their own computers through graphical Jupyter notebooks. It builds on ZeroCostDL4Mic, bringing its bioimage analysis workflows to local machines and remote computing infrastructure. You don't need coding skills to use the notebook interfaces.

MyAgents is a desktop AI agent workspace for people who want help with coding, research and recurring work on their own computers. Agents can use project files, a terminal and an embedded browser while you review their results.

PenEcho is a visual workspace for people working through ideas with handwritten notes, equations and sketches. AI uses the canvas as context and places answers or interactive results beside your work.

DiffRhythm is an AI music generation model for musicians and developers who want to create full-length songs on their own hardware. It uses diffusion to generate songs from lyric and reference-audio inputs.

PhotoLife, formerly Phototheca, is a paid photo and video manager for people organizing large collections on a PC. Its AI face recognition runs locally using the computer's CPU and GPU, without sending photos to the cloud for recognition. It groups photos of the same person into named albums, so you can browse a collection by who's in it.

Speaches is a self-hosted speech server for developers building transcription services and voice applications. Its OpenAI-compatible API lets existing clients and SDKs work with speech models running on hardware you control.

DVC is a data version control tool for individual data scientists and small machine learning projects. It links datasets and model artifacts to code history so you can recover the inputs behind an experiment and reproduce its results.

OpenTutor is a local AI learning workspace for students who want to study their own course materials with a tutor that adjusts to their progress. It targets individual study rather than shared classroom use.

LMDeploy is an open-source toolkit for developers who want to run language and vision-language models on their own GPU hardware. It supports offline batch processing and model servers for applications.

Stirling PDF is a PDF workspace for editing individual documents and automating larger document workflows. It runs through a browser on your own server, with Docker deployment, or as a desktop application for Windows, macOS and Linux.

DeepEval is an LLM evaluation framework for developers testing AI agents, RAG pipelines and chatbots. It helps compare prompts and models and catch quality regressions within Python tests or CI/CD.

OpenManus is a Python framework for developers who want to run and extend a general AI agent on their own machine. You give it tasks through a terminal, and it connects a language model to tools that can act on those tasks.

OpenRAG is a self-hosted platform for searching documents and asking questions about them through an AI chat interface. It brings Langflow, OpenSearch, and Docling together for developers and teams that want a document knowledge base with control over its retrieval workflows. It's open source under Apache 2.0 and supports self-managed deployment with Docker or Podman.

Hiring Agent helps hiring teams rank resume PDFs to decide which applications to review first. HackerRank built it for intern applications, with human reviewers making the hiring decisions.

Capka is a self-hosted AI agent for people and teams whose work ends in a document, spreadsheet or code patch. It works with uploaded files, runs code and returns editable outputs you can revise through conversation. The app and its Linux sandboxes run on your own server.

Karakeep is a bookmark manager for people collecting articles, notes, images and PDFs for later use. It keeps saved material searchable and can preserve pages after their original links disappear.

Kition is a desktop AI workspace for writing, research, and project planning. Its agent works directly with editable project files, so you can inspect proposed changes in the documents and boards they affect.

Liquid Apollo is a local AI playground for people who want to interact with AI without relying on cloud processing. It focuses on low-latency interaction.

Feeds Fun is an RSS reader for people who want to prioritize articles across their subscriptions. It assigns tags automatically and uses your scoring rules to decide which entries appear first.

Extended OpenAI Conversation is a custom conversation agent that runs inside your Home Assistant instance and uses OpenAI's remote API for model calls. It builds on Home Assistant's OpenAI Conversation integration for people who want chat to control their smart home. The component runs locally, but conversations and exposed device context go to OpenAI, so it requires an internet connection.

OpenLIT helps developers investigate failures and assess the quality of existing AI applications and coding agents. It connects model requests with the tools, retrieval and agent steps involved in producing an answer.

Avalanche is a Python library for researchers and practitioners studying continual learning, where models learn across a sequence of data or tasks. Built on PyTorch, it brings benchmark datasets, training strategies and evaluation into one framework, reducing the custom code needed to compare experiments. It's open source under the MIT license and can train models on your own CPU or CUDA GPU.

Intel Neural Compressor is a Python library for developers who want to compress AI models for deployment on their own hardware or servers. It supports LLMs and other deep learning models, with extensive testing on Intel platforms.

Langfuse helps teams debug LLM applications and AI agents, then test changes against production examples. It brings traces, evaluations and prompt revisions into one place.

HilbertRaum is a local AI workspace for people working with confidential documents, research, or personal archives. It lets you use AI without sending your files or conversations to an external service.

Surya is a local OCR toolkit for developers who need text and page structure from document images. It handles multilingual documents and preserves reading order for use in document-processing applications.

Whisper Desktop turns audio and video recordings into transcripts and subtitles on your computer. It's for people working with interviews, lectures, podcasts or videos who want a desktop interface for transcription and captioning.

HolaOS is a desktop AI workspace with a self-hostable runtime for teams that want agents to work with their apps and files. Claude Code, Codex and its built-in agent share tools and project memory. Workspace storage is local. Default built-in model access uses your HolaOS account and hosted inference; you can also configure your own provider or compatible endpoint.