Local & Self-Hosted AI Tools

RTK filters command output before an AI coding assistant reads it. It's for developers whose agents spend too much context on build logs, passing tests and repetitive terminal output.

Skills (mattpocock) is a collection of small engineering workflows for developers using Claude Code, Codex and other AI coding agents. You can adapt and combine individual skills to address specific problems without adopting a complete development process.

Cua supplies desktops and automation tools for developers building AI agents that operate native apps and browsers. You bring your own agent and model; Cua provides the computer environment and ways to interact with it.

WhisperLive turns speech into text as audio arrives, using OpenAI's Whisper models. It's for developers and teams who want to run transcription on their own machine or server and connect it to live audio or recorded files.

ECC adds reusable engineering workflows to AI coding assistants. It's for developers who want editable plans, test-first development and separate review contexts across sessions.

OpenChatCut is an AI video editor for creators who want to direct edits through conversation and refine them manually. Agent changes become editable clips, captions, effects and audio tracks, so you can inspect or undo them in the same project.

BERTopic is an open-source Python library for researchers and developers who need to find themes in document collections. It groups texts using transformer embeddings, then uses class-based TF-IDF to identify words that describe each group. Those keywords give you a way to inspect what a topic covers and which documents belong to it. The license is MIT.

AI Job Search is a job application framework for people who want to assess roles and prepare tailored documents from their own career profile. It runs through Claude Code on your machine, but AI work uses Anthropic's service and requires paid Claude access or API credits, so it isn't fully offline.

OpenCode is an AI coding agent for developers who want help writing code or exploring unfamiliar projects. You can choose a local model running on your hardware or connect a cloud provider.

Apache TVM is a machine learning compiler for developers optimizing models for deployment on their own hardware. It compiles model computations into modules that applications can embed, with targets spanning data center GPUs and edge devices. Code is licensed under Apache 2.0.

XERJ is a local search engine for developers building AI agents that need to retrieve code, documents or stored knowledge without reading whole files into their context. It runs on a laptop or self-hosted server.

agentacct is a local dashboard for developers who want to see what coding agents did across projects and compare their work with resource use. It brings recorded activity and results into task receipts rather than relying on an agent's claim that a job is finished.

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.

Context Mode is a local MCP plugin for developers whose AI coding agents fill their context windows with logs, file reads and search results. It stores large tool outputs on your machine so the agent can retrieve relevant passages as needed.

Activepieces is a self-hosted automation platform for teams that want AI agents and app workflows on their own servers. It runs with Docker or Kubernetes, alongside a managed cloud offering. Self-hosting controls where the app runs; connections to Anthropic, OpenAI, AWS Bedrock or Google Gemini still send model requests to those providers using your credentials.

Kokoro Clipboard TTS reads selected or copied text aloud on Windows and macOS using Kokoro-82M. It's for people who want to listen to text across desktop apps while keeping it private. Speech generation works offline, and both clipboard text and audio stay on your machine. It doesn't require an account or API key, and it has no telemetry.

Superpowers adds a development workflow to AI coding assistants. It's for developers who want to approve a design before implementation and have the agent work through a plan with testing and review.

Agent Safehouse is a local macOS sandbox for developers who want coding agents to edit a project while limiting their access to unrelated files. The operating system enforces the restrictions, so they don't depend on the agent following written instructions.

GLiNER is a Python framework for extracting named entities from text using small models that run locally on CPUs and consumer hardware. It's for developers building document processing, personal data detection or search systems who need to choose their own entity types without training a model for each task.

Free Claude Code lets developers use coding agents with local models or a choice of cloud providers. It connects existing clients to a shared model catalog rather than requiring a separate coding workflow.

Browser Use is an AI browser agent for developers automating tasks across websites. It can work through pages and forms to complete jobs such as booking an appointment.

Stable Baselines3 is a Python library for training reinforcement learning agents on your own hardware using PyTorch. It builds on Stable Baselines and gives researchers and developers tested algorithm implementations for comparing approaches or building their own projects. It's free and open source under the MIT license.

FreeLLMAPI gives developers one API for experimenting with cloud models and local backends. The router runs locally, but cloud inference still sends requests to the providers you enable.

Open WebUI is a self-hosted chat workspace for individuals and teams using local LLMs and cloud models. It can work entirely offline with local models.

Numen provides hands-free voice control and dictation for Linux. It is for people who want to operate their computer through speech, including users who cannot comfortably type or want to reduce hand strain.

PPT Master turns documents or topics into PowerPoint presentations for people who expect to edit the generated slides. It creates native PowerPoint objects that you can revise individually.

QualityScaler is a local AI upscaler for people who want to enlarge photographs and videos and reduce noise through a Windows desktop app. It processes media on your PC without an internet connection.

Sandbook is an offline text-to-speech reader for iPhone and iPad, for people who want to listen to books and documents without uploading them. It runs Kokoro-82M on the device through Apple MLX, with the speech model and voices included in the app. It needs no account and has no ads or tracking.

Moli is a headless browser for developers building AI agents, web scrapers and retrieval pipelines on their own machines or servers. It reads page content and executes JavaScript without continuously rendering a visual page.

LiteLLM is an AI gateway for platform teams managing model access across applications and providers. It puts cloud and self-hosted models behind a shared interface so developers can switch providers without rewriting their integration.

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.

CC Switch is a desktop manager for developers who use multiple AI coding assistants or API providers. It brings their settings into one interface and preserves existing plugins, hooks and other custom settings when switching providers.

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.

spaCy is a Python library for developers and data scientists who need to extract structured information from text in their own applications. It runs on macOS, Windows and Linux, with model packages that become part of your application. It's free and open source under the MIT license.

OpenMontage is an AI video production engine for creators who want an agent to produce a complete video or handle a specific editing task. It can start with a brief or work with material you already have.

LLaMA-Factory is a local model training platform for developers and researchers who want to adapt pretrained models to their own tasks. Its web UI lets you fine-tune models without writing code.

SHAP is a Python library for data scientists and machine learning researchers who need to understand how input features contribute to a model's predictions. It uses Shapley values from game theory to assign contributions to individual features. The library is open source under the MIT license and runs in your own Python environment.

MoneyPrinterTurbo is a self-hosted AI video generator for creators producing shorts from topics or keywords. It automates the production workflow while letting you supply your own content at each stage.

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.

LiteRT-LM is Google's open-source framework for developers building apps that run language models on the user's device. It uses LiteRT for local inference across mobile devices, desktops and browsers, with GPU and NPU acceleration. The project uses the Apache 2.0 license.

Firecrawl turns web pages into content that developers can use in AI apps and agents. Its self-hosted API suits teams that want to collect web data on infrastructure they control.

OCRmyPDF makes scanned PDFs searchable and lets readers copy recognized text from them. It's a command-line tool for people digitizing paper records and developers adding OCR to document workflows.

PyOD is a Python library for detecting unusual records and behavior in data on your own machine or server. A shared fit/predict interface lets developers and data scientists compare classical and deep learning anomaly detectors without changing the surrounding application for each algorithm. Its code uses the BSD 2-Clause license.

Hermes Agent is a self-hosted AI agent from Nous Research for people who want an assistant that remembers past work and handles recurring tasks. It runs on macOS, Linux and native Windows, or on a server you control. Model connections include Nous Portal, OpenRouter, OpenAI and your own endpoint; choosing a hosted provider sends model requests to that service.

PyGPT is a desktop AI assistant for people who want to chat with models, work with their documents and delegate tasks from one application. It supports local AI through Ollama alongside cloud providers.

Accentize dxRevive is a proprietary AI speech restoration plugin for macOS and Windows that reconstructs missing frequency content as well as reducing noise. It's aimed at podcast editors, content creators and dialogue editors working with damaged or poorly recorded speech. All audio processing stays on your computer, without cloud uploads or special hardware.

Claude Mem gives coding assistants persistent project memory, so developers can carry earlier decisions and failed approaches into later sessions without explaining them again.

Goose is a general-purpose AI agent for people who want help with coding, research, writing, automation or data analysis. It runs on your computer and lets you choose the model provider behind the agent.