Local & Self-Hosted AI Tools

GluonTS is a Python library for data scientists and researchers who need forecasts that express uncertainty. Its models predict a probability distribution over future values, so you can examine prediction intervals alongside the forecast. You train and use models within your own Python environment.

agentchattr is a local chat server for developers coordinating multiple AI coding agents. Humans and agents share a conversation and can mention one another to trigger responses without carrying messages between terminals.

iCode is a terminal development workspace for developers who want to work with AI agents and inspect their changes. It brings conversations, agent workflows and a working shell into one interface.

Pi Interactive Shell lets developers give the Pi coding agent control of terminal programs that need ongoing input. You can watch the session in an overlay and take control when a task needs your attention.

Pathrule gives AI coding agents project knowledge that stays attached to the relevant workspace and file paths. Memories, rules and skills can follow a repository across agents and sessions, so developers can retain decisions and constraints without pasting the same instructions into each conversation.

AudioWhisper is a macOS menu bar app for dictating into other apps and converting recordings to text. It suits people who want on-device speech recognition with the option to use cloud transcription.

Automated AI Web Researcher investigates a topic using a locally running LLM. It's for people who want to delegate web searches and keep the collected material for review, rather than gather each page themselves.

Wallfacer helps developers find and return to AI coding conversations scattered across projects and assistants. Its terminal browser gathers sessions from Claude Code, Cursor CLI, Kiro CLI and Codex, including conversations started outside Wallfacer.

Nowen Note is a self-hosted note app and knowledge base for individuals and teams who want to keep documents on their own server or NAS. Writing, connected notes and task management share one workspace.

OpenCLIP is a Python library for developers and researchers building image-text matching and zero-shot classification applications. It supports pretrained CLIP models and training models on your own hardware.

Fisper is a voice-to-text app for Apple Silicon Macs that puts dictated text into the app you're using. It runs Whisper locally and works offline after the initial model download. It's for people who want to dictate in everyday apps or talk to terminal-based AI agents without sending their audio to a cloud service.

RepoGPT is a self-hosted GitHub AI assistant for developers who want to ask questions about a repository in plain language. Its web app runs on your machine and opens in a browser, while AI features use the OpenAI API. It's open source under the MIT license.

PraisonAI is a Python framework for developers building AI agents that research, write code, or carry out tasks across apps. It supports single agents and coordinated teams for work that needs several steps or specialist roles.

Team Tasks is a local command-line tool for developers coordinating AI agents through OpenClaw or another orchestration system. Shared JSON files keep task assignments, progress and results in one project record.

memU gives connected AI agents a shared memory of preferences, project decisions and learned workflows. It's for people who move between agents or sessions and want useful context to carry into later tasks.

LangBot is an AI bot platform for teams handling customer support, internal questions, or community chats. It brings agents and existing AI workflows into the messaging services people already use.

Synaplan is an open-source AI platform for teams that want assistants to answer questions from company files and handle customer conversations. It brings internal knowledge and customer support into a shared system on infrastructure you control.

SetFit is a framework for developers and NLP practitioners who need to train text classifiers with a small amount of labeled data. It adapts pretrained Sentence Transformers to a classification task without requiring handcrafted prompts or words that stand in for class labels. Sentiment analysis is one supported use case.

Qwen-Image generates images from text and edits existing pictures. It's for creators and developers who want to run an image model on their own hardware, especially for work that needs readable text within images.

Kerlig is a paid AI writing assistant for Mac that helps with emails, Slack replies and Jira tickets in the apps you already use. It combines text editing with document chat and an agent that can read your screen and use your apps.

Future AGI helps teams test AI agents, investigate production failures and compare prompt changes. It brings evaluation and monitoring into the same platform so teams can connect poor responses to the steps that caused them.

Vyact is a desktop workspace for people who want a local LLM to help with files, writing and code. It brings conversations and searchable documents together, with optional connections to email services and Chrome.

Typesense is a self-hosted search engine for developers building site search, product catalogs or AI search over their own data. It combines keyword matching with searches based on meaning.

Claudio coordinates multiple Claude Code sessions on one repository. It's for developers who want agents to tackle separate coding tasks in parallel, with each session working on its own branch.

Pixelmator Pro is a paid image editor for Mac and iPad that combines AI photo editing with layered graphic design and vector drawing. It's for photographers and designers who want to retouch images and build compositions in the same app. Its built-in image-processing tools use Apple hardware and machine learning, while feature availability and network requirements vary.

Open Cowork is a desktop AI agent for Windows and Apple Silicon macOS that uses cloud model APIs to carry out tasks on your computer. It's a Claude Cowork alternative for people who want a graphical interface for document work and app automation. The app is free and open source under MIT, but the agent needs an API key and internet access; model requests go to your chosen provider.

WorkAny Desktop is an AI agent for people who want to delegate file work, document creation and coding tasks in plain language. The app executes tasks on your machine and connects to Anthropic, OpenAI, OpenRouter or custom model providers. Requests to external providers leave your machine, so local task execution doesn't make it an offline AI app.

AutoTS is an open-source Python package for people who need forecasts across many time series without choosing a model and preprocessing method for each one. It runs in your own Python environment and uses automated search to compare forecasting approaches for your data. The license is MIT.

DeepImageJ brings pretrained neural networks into ImageJ and Fiji for life-science researchers who want to analyze microscopy images without writing code or learning how to train models. It runs image-to-image predictions on your own computer, using a standard CPU or a compatible GPU.

VoiceCraft generates speech from text and edits existing recordings using a few seconds of a speaker's voice as reference. It's for researchers and developers who want to work with voice generation on their own hardware without training a separate model for each speaker.

Tellama is a local LLM chat app for Android users who want conversations to stay on their phone. Chat with an installed compatible model works offline, and you don't need an account.

Vigil SOC is an open source AI SOC for security teams that want agents to investigate alerts and carry out incident response within their own environment. It connects investigations, containment, and reporting through editable playbooks.

Open Multi Agent is a TypeScript framework for developers building self-hosted AI agent teams. It lets you coordinate work across agents, require human decisions before consequential actions, and inspect what happened afterward.

Optimum is a collection of Python packages for developers adapting Hugging Face models to their deployment hardware. It extends Transformers, Diffusers, TIMM and Sentence Transformers with tools for faster inference and training.

AutoGen is a framework for cooperating AI agents, with local Playwright browser automation, code execution and an experimental OllamaChatCompletionClient for local models. Its orchestration can run on your machine or across servers. Standard OpenAI and Azure OpenAI service connections send model requests to remote services; compatible endpoint overrides are separate configurations.

Potpie's open-source CLI gives developers and coding assistants a local store of project context, backed by a daemon and a browser graph explorer. It's for teams that need agents to understand code alongside engineering decisions and project history. With Claude Code’s standard cloud connection, prompts and model outputs travel to a remote model provider over the network.

Stella is a legal workspace for law firms and legal teams that want matter files, contract review and research in one place. Its AI agent answers questions about a matter with citations that open the relevant source passage.

RESTai is a self-hosted AI platform for developers and teams building document assistants, agents and AI services for other applications. Its web interface manages projects with separate models, prompts and tools, plus a chat playground for testing them.

BotSharp is a C# framework for .NET developers building AI assistants into business applications. It coordinates agents with different responsibilities and keeps track of conversation state.

KoboldCpp runs language models on your own hardware for chat, creative writing and roleplay. It's a fork of llama.cpp with a bundled KoboldAI Lite browser interface.

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.

OpenZiti LLM Gateway is a self-hosted API proxy for developers and teams connecting AI applications to inference servers across private networks and cloud services. Its optional zrok integration uses OpenZiti for identity-based access and end-to-end encryption, so clients and backends can connect across network boundaries without opening inbound ports.

RWKV is a language model architecture for developers and researchers building LLM applications or training models. Its recurrent design keeps inference memory constant as text grows, making it relevant when a growing context cache would strain available memory.

Chatterbox TTS Server turns text into speech on your own computer or server. It's for people making narration and audiobooks, or adding speech to apps through an API.

Cheshire Cat is a Python framework for learners, researchers and creatives building custom AI assistants. It supports hands-on experiments through a web chat interface and an API. It isn't recommended for production use because it's unstable and may have breaking changes or incomplete features.

Humanizer Stack is a pair of Claude Code skills for writers and editors revising public-facing AI drafts. It checks sentence-level habits and the shape of a piece, rather than limiting edits to word substitutions.