Local & Self-Hosted AI Tools

Auteur is an AI web design skill for coding agents building animated landing pages and products with several screens. It sets visual direction before code and supplies recipes and automated checks for the resulting site.

tsai is a Python library for researchers and developers building machine learning models for time series and sequences. Built on PyTorch and fastai, it brings model training, prediction and data preparation into one package. It's open source under Apache 2.0.

TPOT is a Python AutoML library for data scientists and researchers who want to automate machine learning pipeline selection on their own hardware. It uses genetic programming to search candidate pipelines, reducing the manual work of comparing models and tuning their parameters. It's free and open source under LGPL-3.0.

TensorRT is NVIDIA's inference toolkit for developers deploying AI applications on NVIDIA GPUs. Its compilers, runtimes and model optimizations target lower response latency and higher throughput on local machines, self-hosted servers and edge devices.

Garak is an LLM vulnerability scanner for developers and security teams assessing models or dialogue systems. It attempts to provoke unwanted responses so teams can identify weaknesses in the systems they test.

Paxm gives AI coding assistants persistent memory of project decisions, conventions and past work. It's for developers who want later sessions or another coding agent to recover context they've already explained.

open·kritt helps security researchers and developers investigate code for vulnerabilities through focused AI agent tasks. It gives teams control over the research prompts, workflows, model providers, and infrastructure they use to review a codebase.

VoxInput is an open-source dictation tool for Linux and macOS that types spoken words into the active application. It's for people who want speech input across their desktop, including applications without their own dictation feature. On Linux, it also works in the system console.

Heretic modifies language models to reduce safety-related refusals without expensive post-training. It's for people who want fewer restrictions in models they run themselves, without manually tuning model internals.

Captain Memo gives developers a shared memory across coding assistants, so project decisions and lessons remain available between sessions and tools. Claude Code, Codex, Gemini CLI, Cursor and other MCP-compatible assistants can access the same corpus.

Higress is an AI gateway for teams building AI apps and agents that need shared controls across model requests and tool calls. It brings model APIs, MCP services and Kubernetes inference workloads behind one entry point.

Instant NGP is neural graphics software for researchers and developers working on 3D reconstruction and rendering. It trains representations of scenes and images on a single GPU, then lets you explore the results interactively.

vLLM Metal lets developers serve language models on Apple Silicon Macs through vLLM. It's for people who want to use their Mac's hardware for local AI inference while keeping vLLM's API server and request scheduling.

EmbeddingGemma is a local AI embedding model for developers adding search and retrieval to applications. It represents text, images, audio and video in a shared space so apps can find related content across media types.

AutoAgent lets people create AI agents by describing the work they want done. It's for users who want custom agents without writing the agent code themselves, or a ready-made research assistant for gathering information and producing reports.

Jupyter AI is an extension you run with your own JupyterLab server, giving agents access to notebooks, files and terminal commands in that environment. Model access comes from your separately installed agent; Claude Code’s standard connection, for example, sends prompts to its cloud provider. Its built-in Jupyter MCP server connects agents to notebook operations, alongside file editing and terminal commands. Chat sits beside the work.

Lucebox is a local AI workstation for developers and teams who want to run models on their own hardware. Its inference engine is also available separately for supported AMD and NVIDIA machines.

CrewAI is a Python framework for developers automating work with teams of AI agents. It combines agents that make decisions with explicit workflow logic, so a process can include both autonomous work and predictable steps.

Qwen3-Embedding is a family of models for developers building search and text analysis on their own hardware or servers. It represents text as numerical vectors so applications can compare passages by meaning.

PixArt-Sigma generates images from text prompts on your own machine or a self-hosted server. It's for developers and researchers who want downloadable image models and the code to train their own.

Acme is a Python reinforcement learning library for researchers who need reference agents and reusable components for their own experiments. Its agents provide baselines for comparing algorithm performance, while the underlying building blocks let researchers develop new approaches without starting from scratch.

RealScaler is a local AI upscaler for people who want to enlarge photos and videos and reduce noise without uploading their media. Its Windows desktop interface uses Real-ESRGAN models, and processing works offline once the required files are available on your PC.

Morphic is an AI search engine for people who want answers they can check against web sources. It searches the web and reads URLs to gather information for a question.

Coqui TTS is a text-to-speech toolkit for developers and speech researchers who want to generate voices locally or train their own models. The idiap fork builds on coqui-ai/TTS.

Wordflow is an AI writing assistant for writers and researchers who want to reuse editing prompts across their work. Its browser editor lets you revise a paragraph or selected passage with a choice of local and external models.

Excire Search is a Lightroom Classic plugin for photographers who need to find material in large catalogs and choose between similar shots. Its AI analyzes photos and video clips locally without transferring them to a cloud service.

Locally Uncensored is a desktop AI studio for people who want to chat, create media and work on code on their own PC. It includes mainstream models and variants with fewer refusal restrictions.

ModernBERT is a family of text encoder models for developers building search and classification systems on their own hardware. The base checkpoints predict masked words; retrieval, classification and question answering require task-specific fine-tuning.

Mini SWE Agent is a command-line AI coding assistant for developers tackling GitHub issues and everyday coding tasks. Its small Python core also suits researchers who want to inspect and modify an agent for model evaluations.

CosyVoice is a text-to-speech system for developers building speech applications on their own hardware or self-hosted servers. It can generate speech in a reference speaker's voice, including in another language, without training a separate model for each speaker.

SkillHub is a self-hosted registry for teams that share reusable AI agent skills and need control over who can publish or access them. It gives organizations a private place to manage internal skill collections.

ComfyUI Frame Interpolation adds AI frame interpolation to ComfyUI workflows for people working with video or animation. It generates frames between existing images to make motion smoother.

kodo coordinates coding agents for developers who have a clear goal and want work to continue unattended for hours. It divides implementation and review across agents and multiple context windows.

CyberScraper 2077 turns web pages into structured data through a conversational interface. It's for analysts and researchers who want to describe the information they need and export the results.

TensorFlow Model Optimization Toolkit is an open-source Python library for developers preparing TensorFlow and Keras models for deployment on mobile, IoT and other edge devices, or in the cloud. It helps reduce inference latency and cost, and adapt models to limits on memory, processing power, energy use and storage.

Speech AI Forge is a self-hosted text-to-speech app for people making spoken audio or adding speech generation to their software. It brings several speech models into one Gradio web interface and also provides a separate API server.

Optio coordinates coding agents and automated work for teams using their own infrastructure. A shared feed tracks pull requests, recurring jobs, interactive sessions and agents that stay available between tasks.

Mylio Photos organizes photos, videos and documents scattered across devices and drives into one library. It's for personal collections, family archives and business media libraries whose owners want to choose where their files live.

Edit Mind is a self-hosted AI video knowledge base for editors, creators and people with large footage archives. It helps you find a moment by what someone says or what appears on screen, without remembering the filename. The self-hosted project isn't production-ready and may have incomplete features or bugs.

ColPali is a document retrieval library for developers and researchers building search or retrieval-augmented generation systems. It matches text queries to page images, using visual content alongside text. The colpali-engine package is deprecated, and maintainers recommend Sentence Transformers for new projects and production use.

SUB/WAVE is a self-hosted internet radio station for people who want to broadcast music from their own library. An AI DJ picks tracks and speaks between them while every listener hears the same live Icecast stream.

Continue is a coding agent for developers working in a terminal, VS Code or JetBrains. Its Ollama integration can run models on your computer; Standard OpenAI and Anthropic service connections use cloud models. The repository is read-only and no longer actively maintained.

OpenHands is an AI coding agent platform for developers and teams that want agents to carry out code changes and recurring engineering work. Agent Canvas provides a control center for agent conversations and automations.

iAi Personal Memory Engine gives AI assistants persistent memory on your machine. It's for people using coding agents who want past conversations, project details and preferences available across sessions.

Yuxi is a self-hosted AI agent platform for teams that need answers from their documents and agents that can carry out multi-step work. Its browser workspace brings knowledge sources, task progress and generated files into the same conversation.

Open-Sora is an AI video generation project for researchers, developers and creators who want to run or adapt a model on their own GPUs. It focuses on animating reference images with text guidance and also accepts text alone.