Local & Self-Hosted AI Tools

Hindsight is a memory system for developers whose AI agents need to carry facts and experience across sessions. It combines stored memories into observations and maintains answers to recurring questions as more information arrives.

Stable Audio Open generates audio from text for artists and researchers experimenting with sound effects, field recordings and music samples. It performs better on effects and environmental sounds than music, and it can't generate realistic vocals.

PyTerrier is a Python framework for researchers and developers building search systems or the retrieval part of a RAG application. It builds on Terrier and lets you combine retrieval and reranking components into pipelines, then compare their search effectiveness on standard datasets.

Maid is an Android AI chat app for people who want to chat with models on their phone and access remote models from the same interface. Local conversations work without an internet connection.

Transcribe Anything turns recordings and online videos into text and subtitles using Whisper-based speech recognition. It's a command-line tool with a Python API for people processing media locally or adding transcription to their own applications.

Pyserini is an open-source Python toolkit for researchers and developers comparing document search methods or building the retrieval stage of a ranking or RAG system. It runs as a Python package on your own hardware and lets you search existing benchmark indexes or build indexes from your own documents. Its license is Apache 2.0.

Real-ESRGAN is a local AI upscaler for people enlarging images or restoring degraded images and video. It builds on ESRGAN, with dedicated models for general images, anime illustrations and animated video.

Flexible GraphRAG is a self-hosted platform for teams building document search and AI chat that use both text and relationships between entities. It extracts knowledge graphs from documents and combines graph retrieval with vector similarity and full-text search. You can run it standalone or in Docker. It's open source under Apache 2.0.

iZotope Neutron is a proprietary audio mixing suite for producers, musicians and mix engineers who want an assisted starting point and control over individual effects. Its AI-powered Mix Assistant helps shape a mix, while manual controls let you build your own processing chain.

DeePMD-kit is open-source software for molecular and materials researchers who want to train and run AI interatomic potentials on their own hardware. It learns atomic interactions from quantum-mechanical reference data, then uses those models in molecular dynamics simulations of molecules, solids and metals. It runs on CPUs and GPUs, with support for CUDA and ROCm source builds, and carries the LGPL-3.0-or-later license.

Ringer coordinates parallel AI coding agents on your machine. It's for developers who want to divide implementation work among workers and judge the results with executable checks.

ProPainter is an AI video inpainting tool for people who need to remove unwanted objects or fill missing areas in footage. It processes videos with masks that identify the regions to replace.

My Neuro is a local AI desktop companion for people who want to create a character with their own choice of appearance, voice and personality. It supports spoken and typed conversations, with character expressions and movements that respond to the dialogue.

Cloud CLI is a browser interface for developers who want to work with coding agents and manage projects from a computer or phone. It connects to Claude Code, OpenCode, Cursor CLI and Codex, so you can access agent sessions beyond the terminal.

Deltafin runs full Kimi K3 on a single device for researchers and developers exploring large models on their own hardware. It preserves the original expert weights and complete expert bank, but responses are slow and long conversations take substantially longer than short completions.

TorchMD-NET is an open-source Python library for researchers who train neural network potentials for molecular dynamics. It exposes its models as PyTorch modules and connects them to GPU-accelerated simulation software, including ACEMD, OpenMM and TorchMD. It's available under the MIT license.

TripoSR creates a 3D object from a single image on your own hardware. It's for artists, developers and researchers who want image-based reconstruction for their projects or software.

Pieces builds a searchable history of your work across apps for people who need to recover earlier decisions, find research or pick up an interrupted task. It runs in the background on your computer.

npcpy is a Python library for developers and researchers building AI agents and applications with language models. It supports local LLM backends as well as cloud providers, so projects can choose where model requests run.

Nemotron is NVIDIA's family of AI models for developers building agents that reason, write code and use tools. Teams can evaluate and adapt the models using published weights, training data and training recipes.

Deep Research is a self-hosted AI agent for people who want web research with traceable evidence and a library they control. It runs in Docker on your own machine or server, searches the web in successive rounds, and uses gaps in its findings to decide what to investigate next. Reports include citations, per-source notes with quoted evidence, and suggested follow-ups.

DevOpsGPT is a self-hosted AI development application for teams turning written requirements into code and deployment work. The browser interface and generated-code workspace run on your machine or server, while GPT requests use the OpenAI API with a token and incur provider charges.

SoloMD is a Markdown editor for writers, researchers and developers who want plain text notes with AI assistance. It combines a Typora-style writing interface with tools for searching a note collection and letting agents work on it.

Flash Linear Attention is a Python library for researchers and developers building language models on their own hardware. It supplies reusable components for exploring linear attention, sparse attention and state space architectures.

Reticle lets AI coding agents check changes against a running web or desktop app. It's for developers who need to catch failed requests, duplicate submissions and application state that disagrees with what the screen shows.

roborev reviews commits in the background for developers working with AI coding agents. It brings findings back into active coding sessions so bugs can be addressed before a pull request.

Onlook is a visual code editor for designers building websites and prototypes. Its open-source editor works on the app's code, so design changes become part of the working product rather than a separate mockup.

Adrian is a runtime security tool for teams whose AI agents can use tools or act on external systems. It checks planned actions against the agent's intended task and can intervene before an unsafe action runs.

Jido is an Elixir framework for developers who want to run cooperating agents inside their own application or self-hosted server. Its BEAM runtime handles agent state, tool execution and coordination. AI is optional: the core supplies the runtime, while jido_ai adds model integration separately.

PenguinHarness builds runnable AI agent applications from plain-language requirements on your computer or server. It's for developers who want agents to handle app creation, evaluation, tuning and deployment.

Claude Context adds repository search to AI coding assistants so they can retrieve relevant code without loading whole directories into their context. It's for developers working with large codebases that an assistant needs to understand.

Typebot is a visual builder for businesses creating chatbots and conversational forms for websites, mobile apps and WhatsApp. You can host it on your own server or use its managed cloud service.

LobsterAI is a desktop AI agent built on OpenClaw for office work and local projects. It operates tools on your computer and keeps sessions, configuration and memory there. You select each agent’s model separately from its workspace and tools.

Data-Juicer is a Python framework for researchers and teams preparing datasets for AI training, evaluation, agents or document retrieval. It processes data on your own machine or across a Ray cluster.

VoltAgent is a TypeScript AI agent framework for developers building assistants and automated workflows with local models through Ollama. Its VoltOps console can be self-hosted or used as a cloud service. Model execution depends on the provider: Ollama supports local inference, while OpenAI, Anthropic and Google connections send requests to those remote services.

TTS-Audio-Suite is a ComfyUI extension for creators producing narration, character dialogue and speech matched to subtitles on their own hardware. It brings several speech engines and audio editing tools into the same workspace.

Hypha is a TypeScript AI agent framework for developers building applications that need controlled tool use and recoverable work. It separates an agent's planning and tool choices from the execution layer that decides which actions may proceed.

MTPLX is a native Mac app, command-line tool and local LLM server for people running chat or coding models on Apple Silicon. It uses a model's own multi-token prediction heads to accelerate generation without a separate draft model.

VideoProc Converter AI is a proprietary desktop app for Windows and macOS that combines local AI media enhancement with conversion and compression. It's for creators working with camera footage, people restoring old photos and videos, and anyone preparing large media files for playback or sharing. It processes files on your computer, and batch conversion works offline.

Outlines is a Python library for developers who need LLM responses in a defined format. It constrains generation to produce structured data for tasks such as extracting service tickets from emails or limiting an answer to allowed choices.

SenseVoice is a local speech recognition model for developers building voice apps or analyzing recordings. Its SenseVoiceSmall model adds information about the language, emotion and surrounding sounds to speech transcriptions.

PhotoPrism is a self-hosted photo and video organizer for people who want to browse, search and share a personal media collection on their own hardware or server.

Loop.js is an AI agent framework for developers who want repeated attempts at a task with a separate check of the result. You define the goal and completion criteria, and the engine coordinates work until the verifier accepts it or a stopping condition ends the run.

WebVoyager is a Python AI agent that controls a browser on your machine or a Linux server to carry out tasks on live websites. It's a research project for developers studying browser automation. Model decisions depend on OpenAI's cloud API, which receives page observations and requires an API key and internet access; the local browser doesn't provide local model inference.

Vibe Workflow is a visual AI workflow builder for creators and developers who want repeatable image and video pipelines on their own server. Its editor is self-hostable, but the included generation features use MuAPI and require an account, API key, and internet access.

Apache Maka is an AI agent workspace for people who want an agent to work on tasks on their machine and keep an inspectable record of its actions. It suits developers who need to review commands, file edits and approvals, or continue work after an interruption.