Local & Self-Hosted AI Tools

GTE is Alibaba's family of text embedding models for developers building semantic search and text matching into applications. The models turn text into vectors that let an application compare queries with documents by meaning.

icefall is a speech model training toolkit for developers and researchers building recognition systems on their own hardware. Its Python recipes use k2 and lhotse to train, fine-tune, and evaluate models across speech datasets.

InstantID generates personalized portraits from a single reference photo without training a model for each person. Creators and developers can retain a person's facial identity while changing the image through text prompts. Its required InsightFace face models are restricted to non-commercial research.

FastCtx is a local MCP runtime for coding agents working in code repositories. It gives agents structured results for routine file work without relying on shell commands for every read or search.

TypeWhisper is a macOS dictation and transcription app for people who want to turn speech into text across their apps. Local speech models keep audio on your Mac; optional cloud transcription sends it to the selected provider.

ReScript is a video and audio editor for people cutting interviews, podcasts and voice notes through text. Deleting words from a transcript removes the matching sections of the recording.

RecurseChat is a Mac app for people who want private AI conversations and answers drawn from their own documents. Local models run without an internet connection or a separate server.

Neo4j LLM Graph Builder converts documents and web content into knowledge graphs for people building searchable collections or AI applications with Neo4j. It uses an LLM to identify entities, relationships, and their properties.

MedSAM is an open-source model for medical image segmentation that runs locally, aimed at researchers and developers working with medical scans. It builds on Meta's Segment Anything model and uses bounding boxes to identify the region you want to segment. The project uses the Apache 2.0 license and supports macOS.

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.

SearXNG is a self-hosted metasearch engine for people who want to combine search services without user tracking or profiling. It's a fork of searx, and web searches require internet access because external services supply the results.

Granite is IBM's family of AI models for developers and businesses building applications on their own hardware or servers. You can customize the models for enterprise tasks, including coding assistants and document analysis.

OpenRLHF is a self-hosted Python framework for researchers and teams training language models with human feedback or custom rewards. It supports fine-tuning and reinforcement learning on your own GPU hardware, including training agents that interact with an environment.

Brave Leo is an AI assistant inside the Brave browser for people who want help with what they're reading. Bring Your Own Model support lets you use a local LLM or a remote model for browser conversations.

Kilo Code is an AI coding assistant for developers who want an agent to edit, explain, and debug a codebase in their editor or terminal. You can choose local models, connect a provider with your own API keys, or use Kilo's hosted model access.

Assistant is a self-hosted AI agent for people who want to delegate work by email and receive the results in their inbox. It uses a dedicated mailbox, separate from your personal email, and also accepts tasks through a browser workspace or dashboard. You control how much autonomy it has.

SiYuan is a knowledge workspace for people who want to connect notes, reference material and individual passages. Its block-based editor lets you link directly to a piece of text rather than an entire document.

River is a Python library for models that learn from incoming data one observation at a time. It's for developers and data scientists working with event streams, changing data patterns, or applications that need to update models without revisiting past training data. It runs in your own Python environment on Linux, macOS and Windows, and is open source under the BSD-3-Clause license.

RemiAI is a self-hosted AI assistant for people who want chat to work with their files and remember context between conversations. It can act on permitted folders and delegate longer tasks to specialized agents.

FluidVoice turns speech into text in Mac apps, including email, documents, chat, terminals and code editors. It suits people who want local dictation with optional editing before text reaches the active app.

OpenClaw.NET is a self-hosted AI agent runtime for a personal assistant or a shared team gateway. It's an independent .NET implementation inspired by OpenClaw, with compatibility for supported parts of that ecosystem.

DINOv3 is Meta AI's family of vision foundation models for researchers and developers building image analysis systems on their own hardware. Its pretrained models extract features for individual image regions that can support multiple vision tasks without fine-tuning the backbone.

Yi is a family of language models from 01.AI for developers and researchers who want to run English and Chinese AI on their own hardware. It includes chat models for conversation and base models you can adapt to specific tasks.

Navigator is a self-hosted AI workspace for individuals and teams who want assistants to carry out tasks through connected tools. It combines chat with custom agents and reusable visual workflows.

Swarm Workspace Manager organizes parallel coding tasks for developers who need to keep agents, branches and terminals separate. Its Linux desktop app and CLI manage repositories, isolated workspaces and the sessions running inside them.

Anti Slop is a set of skills for developers who want AI coding agents to avoid generic interfaces and filler copy. It checks the agent's work while leaving visual direction to you.

Askimo is an AI desktop app for people who want to ask questions about their files and delegate work from the same place they chat. It supports local LLM backends and cloud providers, including Ollama, LM Studio, OpenAI, Claude and Gemini.

GPT4All is a local AI chatbot for people who want language models and document conversations on their own computer. Model inference and LocalDocs processing run on the device without a cloud connection.

Sonar serves language and multimodal models for developers and teams running AI applications on their own hardware. It builds on vLLM and works with Hugging Face-compatible models.

python-audio-separator splits recordings into separate vocal and instrumental tracks on your own hardware. It's a Python package for karaoke creators and developers who want to process audio in scripts or applications.

Distil-Whisper is a family of speech recognition models for developers who want to transcribe English audio on their own hardware. The models build on Whisper, reducing model size and processing time with some differences in accuracy.

Dify is a visual builder for teams creating AI agents and applications that use their own data and tools. Its canvas makes application logic visible so teams can inspect and test how a task proceeds.

Agent Zero is a self-hosted AI agent framework for people who want an assistant to carry out research, coding, and document work on a computer. You can watch its actions and intervene in the same desktop with your mouse and keyboard.

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.

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.

Waves Curves AQ is an automatic equalizer plugin for people mixing audio who want a starting point based on their recording. It analyzes the audio and generates five distinct EQ profiles, giving you several tonal alternatives to consider.

Onyx is an AI search and chat platform for teams with information scattered across workplace apps. It gives employees and AI agents answers grounded in company documents.

FATE is a self-hosted federated learning framework for enterprises and institutions that want to train models together while protecting data privacy. It supports collaboration across participating organizations and uses homomorphic encryption and multi-party computation (MPC) for secure computation.

Applio converts recordings and microphone input into another voice for musicians making AI covers, streamers and speech creators. You can choose community voice models or train a model from your own recordings.

FastLLM is an open-source inference engine for people running large language models on their own machines or self-hosted servers. Its main draw is hardware flexibility: large mixture-of-experts (MoE) models can spread their weights across GPU memory, system RAM and disk when they don't fit entirely on a graphics card.

MindWalk helps developers review coding-agent sessions by showing where an agent explored and changed a repository. It turns Claude Code, Codex and pi logs into a visual replay for comparing the agent's work with the task you assigned.

Graphiti is a Python framework for developers building AI agents that need to remember information as it changes. It turns conversations, structured records and unstructured text into a queryable graph with a history of facts.

Torch-TensorRT compiles PyTorch models with TensorRT to reduce inference latency on NVIDIA hardware. It's for developers running models on their own machines or servers who want faster execution while keeping their PyTorch workflow. The project is open source under the BSD 3-Clause license.

ZeroClaw is a personal AI agent for people who want an assistant running on their own computer or server. It can use a shell and browser, respond through messaging apps and perform scheduled tasks.

TTS WebUI is a self-hosted browser interface for people creating speech and music or processing audio with AI models. It brings these tasks into one place, with model choices for different kinds of audio work.

LocalWriter adds AI writing assistance inside LibreOffice Writer for people who want to draft and revise text within their documents. It works with selected passages and requires a separate language model runner.