Local & Self-Hosted AI Tools

DeepPoseKit is an open-source Python toolkit for researchers measuring animal movement and behavior in images or video. You define the body points you want to track and train a model on your own annotations. It runs through TensorFlow and Keras on your own hardware, with Windows support documented, and uses the Apache 2.0 license.

ScrapeGraphAI extracts data from websites and documents based on a plain-language request. Developers can use its self-hosted Python library or call a separate managed cloud API.

Klaat Code is a terminal AI coding agent for developers who want an assistant to read code, make changes, and run commands in their projects. Its default model routing runs through hosted Klaatu, which receives your messages; file edits and shell commands happen on your machine.

big-AGI is a browser-based AI workspace for developers, researchers and people who need to compare answers across models. It lets you examine separate responses and combine them while keeping control over model choice and reusable context.

My Virtual Office gives people running AI agents a visual way to follow their work. Agents appear as characters in a retro 2D office, so you can see who's active without relying only on logs.

Whisper Notes transcribes interviews, lectures and meetings for people who need recordings to stay on their own device. It works without an internet connection or account.

Browser MCP connects AI applications to your everyday browser so they can automate tasks in services you're already signed into. It's for people who want browser automation through their AI assistant without opening a separate browser session.

Murmur is a desktop dictation app for people who want to speak into the apps they already use. It turns speech into text and inserts it at the cursor.

File Brain is a desktop search app for people who remember a document's subject but can't recall its name or location. You can describe what you're looking for and search the contents of files on your computer.

Open Interpreter is a locally installed terminal coding agent for developers on macOS, Linux and Windows. It's a fork of OpenAI's Codex that focuses on adapting agent behavior to lower-cost models. Commands run on your computer inside native sandboxing; model requests go to your selected provider, so local installation alone doesn't mean local inference.

Unstructured is a document processing library for developers preparing files for LLM applications. It turns text documents and images into structured output that applications can work with.

Octop is a self-hosted AI assistant for households and small teams that want personal agents in a shared deployment. Each user can switch between specialists with separate workspaces, model connections and scheduled tasks.

VoiceInk is a local AI dictation app for Mac users who want to speak emails, notes, and prompts into the applications they already use. Speech transcription works offline.

TorchAO is a PyTorch library for developers who want to train and run models on their own hardware with less memory. It supports language models and image or video generation, and works with torch.compile and FSDP2 across most Hugging Face PyTorch models.

XTuner is an LLM training engine for researchers working with very large mixture-of-experts (MoE) models. Its focus is reducing memory pressure and improving distributed training efficiency when model experts receive uneven workloads.

subgen creates subtitles from audio and video for personal media libraries. It's useful for films and shows that lack usable subtitles, with automatic generation tied to your media server.

Guidance is a Python library for developers who need language model responses in a defined format. It controls output during generation for applications that expect structured data or specific syntax.

Second Me is an open-source prototype for people who want to train and host an AI representation of themselves. It uses personal memories to shape a model around their identity and context.

AutoGluon is a Python AutoML library for developers and data scientists who want predictive models without selecting every algorithm themselves. It chooses combinations of classic machine learning and foundation models for the task.

Tracely helps developers trace AI agents and turn production failures into tests that catch the same problem before another release. It uses recorded runs as test cases, so teams can build regression coverage from failures their agents have actually encountered.

Llama Desktop runs language models on your computer for private chat and use in other apps. It's for people who want a local ChatGPT alternative and developers connecting coding agents, editors or scripts to their own models.

ON1 Photo RAW is a desktop photo editor for photographers who want to manage and edit RAW photos in one application. It combines a photo browser with retouching and layered editing, covering work you might otherwise split between Lightroom and Photoshop.

IP-Adapter adds reference-image prompting to Stable Diffusion for artists and developers who want to guide generation with an image rather than describe every detail in words. It works with an existing text-to-image model and can combine image references with text prompts.

Superior Trade Trading Terminal is for traders who want to turn a chart idea into an automated trade on Hyperliquid. You can sketch a price path or describe a strategy, then review the agent's proposed setup before deployment.

Spec Kit gives developers structured processes for working with AI coding agents. It turns requirements, assessments and verification results into project documents you can review alongside the code.

Oriveo Community Edition is a free, open-source AI chat client for people who want local models and cloud providers in the same app, with their conversation history stored on their own device. It runs on iOS, Android and the web, and you can self-host the web client. It doesn't require an Oriveo account.

Palace gives AI coding agents persistent memory of project decisions, conventions and fixes. Developers can carry that context between sessions in Cursor, Claude Code, Codex and Claude Desktop.

InstantMesh generates 3D meshes from a single image. It's for creators working with image-based 3D assets and researchers studying 3D reconstruction.

AgileRL is an open-source Python framework for teams training AI agents on their own tasks, including LLM agents and agents for robotics, finance or logistics. Its evolutionary hyperparameter tuning adjusts training settings during a run, reducing the need for separate tuning trials. The framework uses the Apache 2.0 license.

PDFMathTranslate translates scientific papers for readers who need the text in another language while keeping equations and figures in context. It produces translated and bilingual PDFs so readers can compare the result with the original.

vllm-mlx is a local LLM inference server for developers who want to connect AI apps and coding assistants to models running on an Apple Silicon Mac. One process exposes both OpenAI-compatible and Anthropic-compatible APIs. It's open source under Apache 2.0 and runs on macOS with at least 8 GB of unified memory.

SQL Chat is a SQL client for people who want to work with databases using natural language. Its chat interface lets you ask for data and request database changes without writing every SQL statement yourself.

Accentize SpectralBalance is a proprietary dialogue EQ plugin that runs on macOS and Windows, with native Apple Silicon support. It's for dialogue editors, ADR mixers and podcast producers who need speech recorded across different takes or environments to sound consistent.

Steel is a browser API for developers building AI agents that interact with websites. It supplies real Chrome sessions for tasks involving clicks, forms, logins and pages that rely on JavaScript.

Axolotl is a free, open-source LLM fine-tuning framework for developers and researchers adapting models to their own data. It supports training on local hardware or cloud infrastructure you control.

AgentScope is a Python framework for developers building AI agent applications on their own servers. It includes an SDK, a FastAPI backend and a web UI for applications with multiple users and separate sessions.

TrustLLM is a research toolkit for teams comparing language models beyond answer quality. It evaluates local LLMs and models accessed through APIs for behaviors such as hallucination, harmful responses, bias, and information leakage.

PyTorch Forecasting is a Python library for developers and researchers who want to predict time series with neural networks on their own hardware. It combines ready-made forecasting architectures with data preparation, training, and evaluation tools. It's open source under the MIT license.

MonkeyOCR is a local AI document parser for developers and researchers who need to extract content from English and Chinese PDFs or images. It recognizes page structure and reading order alongside the content itself.

PandaWiki is a self-hosted knowledge base for teams publishing product guides, technical documentation, FAQs, or blogs. It gives readers AI-assisted ways to find answers within those documents.

Vinaya Journal is a desktop journal for people who want AI-assisted reflection while keeping their writing on their own machine. It's built for daily journaling, with AI that uses past entries as context for conversation.

KServe serves LLMs and predictive machine learning models on your own Kubernetes infrastructure. It's for teams that need to put models from different frameworks into production through one serving platform.

Toonflow is an AI creation platform for short dramas, animated stories and short videos. It takes novels or brief ideas through scriptwriting, storyboards and video production in a shared canvas workspace.

Transcription Stream turns recordings into transcripts with speaker labels for people who need to review audio on their own hardware. It works fully offline, including summaries through Ollama and Mistral.

CocoIndex is an open-source AI indexing framework for developers processing codebases and documents on their own hardware. Its code indexing example uses sentence-transformers for embeddings and writes to pgvector or LanceDB, giving it a concrete role in preparing searchable context for agents and LLM apps.

TypingMind is an AI chat frontend for people who want to use different model providers in one workspace. It brings conversations, project materials and custom AI agents into a shared interface.