Local & Self-Hosted AI Tools
Browse local and self-hosted AI software, from chat apps and model servers to coding, image, video and voice tools.
9.2KUpdated 23 hours agoApache-2.0
#Distributed execution
CatBoost is an open-source machine learning library for developers and data scientists building prediction models with numerical and categorical data. Its built-in handling of categories reduces the work needed to turn non-numeric inputs into usable features. It runs computations on your own CPU or GPU and uses the Apache 2.0 license.
180Updated 2 months agoMIT
macOS · Windows · Linux · Web#Human approval#LLM tracing#Multi-agent workflows
Oh My Subagents coordinates Codex and Claude agent teams for developers and researchers handling coding, investigations or independent code review. It saves delegated work and progress so teams can resume interrupted tasks.
1.1KUpdated 7 months agoMIT
Web · Browser Extension#Ollama integration
ollama-ui is a simple browser interface for people who use Ollama and want a graphical front end for it. It provides an HTML UI for an existing Ollama setup.
7Updated 4 months agoApache-2.0
macOS · Web#Git integration#Human approval#MCP
Workstream is a local developer dashboard for people who track code reviews and project work across several services. It runs on your machine and opens in a browser, with local SQLite storage. The project is open source under Apache License 2.0.
7.8KUpdated 2 years agoApache-2.0
Docker#Hugging Face integration#llama.cpp backend#Multilingual
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.
21.8KUpdated 23 hours agoMIT
macOS · Windows · Linux#Git integration#LM Studio integration#MCP
jcode is a terminal AI coding assistant for developers who want to choose their model provider and carry useful context between conversations. It supports local and self-hosted model endpoints alongside cloud services.
65.5KUpdated 1 day ago
Docker · Web#Human approval#Multi-user access#Multilingual
NocoDB is a self-hosted database workspace for teams that want to manage records through a spreadsheet interface. It runs on your own server with Docker and can connect to existing PostgreSQL or MySQL databases. A hosted service is also available.
1.2KUpdated 6 days agoApache-2.0
#Guardrails#Ollama integration
UQLM is a Python library for developers and researchers assessing the reliability of LLM answers. Its confidence scores estimate the likelihood of errors or hallucinations; they don't verify that an answer is factually correct.
6.9KUpdated 2 days agoApache-2.0
#Agent Client Protocol#Human approval#MCP
codecompanion.nvim is an AI coding assistant for developers who want model chat, code edits, and coding agents inside Neovim. It lets you bring editor context into AI conversations and review agent changes in the editor.
3.3KUpdated 1 week agoAGPL-3.0
macOS · Windows · Linux#Inpainting#LoRA
OneTrainer trains diffusion models on your own machine for people adapting image or video models to their own datasets. Its graphical interface brings dataset preparation, training and output previews into one application.
746Updated 6 months agoMIT
macOS#Hugging Face integration#MLX#OpenAI-compatible API
MLX Omni Server lets developers use local models through both OpenAI-compatible and Anthropic-compatible APIs on an Apple Silicon Mac. It's for applications built around those SDKs that need inference on hardware the developer controls. Apple's MLX framework provides hardware acceleration, and all AI processing stays on the Mac.
519Updated 3 weeks agoMPL-2.0
macOS · Windows · Linux#RAG#Reranking#Semantic search
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.
106Updated 1 month agoApache-2.0
macOS#Batch processing
SAMJ-IJ brings local AI segmentation into ImageJ and Fiji for researchers annotating microscopy images. It turns point or rectangle prompts into object regions, so users can work with Segment Anything models without writing code or leaving their image analysis environment.
1.3KUpdated 4 weeks agoMIT
VS Code#Context compression#LLM tracing#MCP
Prompty is a prompt format and developer toolkit for building AI applications. It keeps prompt text, model settings, inputs and tool definitions in a portable Markdown file that developers can share across editors and language runtimes.
2.5KUpdated 1 day agoGPL-3.0
iOS · Android#Human approval#LM Studio integration#Multimodal input
Conduit is a native mobile AI client for people who want access to their self-hosted models and agents from an iPhone or Android phone. It can connect through Open WebUI or directly to a model endpoint.
252Updated 2 months agoAGPL-3.0
macOS · Windows · Linux · Docker#Hybrid search#MCP#Multimodal input
Marginalia is a research agent for people whose papers, notes and working files are spread across a mixed document library. It reads relevant parts of the original files before writing answers with citations.
accentize.comVoice, Speech and Music
macOS · Windows
Accentize DeRoom is a proprietary desktop audio plugin for podcast editors, content creators and dialogue editors working with speech recorded in echoing rooms. It runs inside audio and video applications on macOS and Windows, using a neural network to separate direct sound from room reflections.
1.1KUpdated 2 days agoApache-2.0
Docker#Code execution#Distributed execution#Git integration
SWE AF is an AI coding agent system built on AgentField for developers delegating changes across a repository or several related codebases. It divides work among agents and adjusts the remaining plan when tasks run into problems.
Marketing Studio
1 video255Updated 2 months agoMIT
Windows · Web#Agent Skills#Browser automation#Code execution
Marketing Studio is a local rendering engine with a Claude Code plugin for developers and product teams creating launch materials from an app repository. It keeps generated media and review records alongside the product's code.
10.2KUpdated 2 weeks agoApache-2.0
Docker#Distributed execution#Hugging Face integration#LoRA
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.
41Updated 2 years agoBSD-2-Clause
macOS · Windows · Linux#Distributed execution
Labkit is a local image segmentation plugin for Fiji, aimed at researchers working with microscopy datasets that can be too large for conventional desktop workflows. It supports manual labeling and automated pixel classification, with a design that lets consumer laptops work with images spanning multiple terabytes.
8KUpdated 3 months agoMIT
#Batch processing#Multilingual#Multimodal input
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.
366Updated 4 months ago
Windows · Linux · Docker#Browser automation
Damru is a self-hosted Python framework for developers doing mobile web scraping, automation testing, or browser fingerprinting research. It controls Chrome inside a containerized Android environment; physical Android phones aren't supported.
32.8KUpdated 1 month agoMIT
#MCP#Ollama integration
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.
495Updated 1 year agoMIT
#Batch processing#Hugging Face integration#Multilingual
IndicTrans2 is a family of translation models for developers building multilingual applications and researchers working on Indian languages. It covers all 22 scheduled languages of India, including languages with limited training data.
11KUpdated 3 days agoApache-2.0
Docker · Web#llama.cpp backend#MCP#Multi-user access
HuggingChat UI is a browser-based ChatGPT alternative for people and teams who want to host their own chat service. It's the application behind Hugging Face's hosted HuggingChat, and it connects to a separate model backend.
3.6KUpdated 23 hours agoMIT
macOS · Windows · Linux#Agent Skills#Git integration#Resumable workflows
tuicr is a local terminal code review tool for developers reviewing changes from teammates or coding agents. It works with Git, jj and Mercurial, covering uncommitted work, commit ranges and remote pull requests or changes.
10.2KUpdated 1 year agoMIT
#Hugging Face integration#Multimodal input
InternVL is a family of vision-language models for developers and researchers building AI applications that interpret images and answer questions about them. Downloadable models let teams host inference themselves.
4.2KUpdated 1 day agoAGPL-3.0
Docker · Web#Multi-user access#Multilingual#Prompt caching
Speakr is a self-hosted transcription and note-taking app for people who need to revisit meetings, interviews or lectures. It pairs recordings with searchable transcripts and AI summaries.
547Updated 2 days agoMIT
macOS · Windows#Agent Skills#Code execution#Human approval
CoWork OS is an AI agent desktop for developers and people working with documents, research and email. It brings tasks and their outputs into one workspace, where you can review agent actions and control approvals.
1.2KUpdated 1 day agoAGPL-3.0
macOS · Windows · Linux · Docker#Git integration#Human approval#Multi-user access
Oleafly is a desktop editor for researchers writing papers, theses and other long documents in LaTeX, Typst or Markdown. It brings the manuscript, PDF preview and research tools into one workspace, with projects stored as ordinary files you own.
goodsnooze.gumroad.comDictation and Voice Typing
macOS · iOS#Batch processing#Multilingual#Ollama integration
MacWhisper turns recordings into editable transcripts for people working with interviews, lectures, podcasts and meetings. Local transcription works offline and keeps the audio on your Mac.
10Updated 3 days agoEUPL-1.2
iOS · Android#llama.cpp backend#Multimodal input#Streaming inference
NobodyWho Chat is an on-device AI assistant for people who want help with writing, brainstorming, coding and questions without sending their conversations to a hosted model. Language-model inference runs on the phone, and chat works offline without an account.
4.3KUpdated 23 hours agoMIT
macOS · Windows · Linux · Web#Code execution#Git integration#Multi-agent workflows
Agent of Empires is a self-hosted session manager for developers working with several AI coding agents in parallel. It lets you follow work across projects and branches without keeping every agent's terminal open.
4.7KUpdated 2 days agoMIT
Web#Agent Skills#Guardrails#MCP
HyperResearch is a research agent for Claude Code and OpenAI Codex that produces cited reports and keeps sources for later questions. It's for researchers who want to review the evidence behind a report and reuse their collected material.
13.7KUpdated 2 days agoApache-2.0
Docker · Web#Code execution#Distributed execution#MCP
QuantDinger is a self-hosted AI trading platform for independent traders, Python strategy authors, and small teams. It brings research, strategy development, testing, and trade execution into one workspace while keeping strategy code and broker credentials under the operator's control.
11.6KUpdated 2 months agoMIT
Docker#Ollama integration#OpenAI-compatible API
WeChat Bot is a self-hosted AI agent for people who want automated replies across messaging apps and tools to examine their WeChat conversations. It builds on Wechaty and can use local models through Ollama or external AI services.
1KUpdated 2 months agoApache-2.0
macOS · Windows · Linux#Knowledge graphs#MCP#Persistent memory
GrapeRoot is a local MCP context tool for developers using AI coding assistants on projects that require repeated file exploration. It selects relevant code before each prompt reaches the assistant and remembers earlier work.
4.4KUpdated 3 weeks agoMIT
Web#Batch processing#Hugging Face integration#ONNX
BiRefNet is an AI image segmentation model for developers and image workflow builders who need to separate subjects from backgrounds. It produces foreground masks for cutouts and has dedicated models for matting, where edges can include partial transparency.
31.2KUpdated 6 days agoMIT
Docker#Batch processing#Hugging Face integration#Multimodal input
Unlimited-OCR is an OCR model for developers building document extraction workflows on their own hardware or servers. It handles individual document images and multi-page inputs, including PDFs converted to page images.
221Updated 6 months ago
Web#Hugging Face integration#Multilingual#Multimodal input
MOSS-Music is a local AI model for people who need to describe, transcribe, or analyze recorded music. It works with full tracks and combines sung lyrics with musical details in its responses.
745Updated 3 weeks agoMIT
macOS · Windows · Linux#Batch processing
Segment Anything for Microscopy adapts Meta AI's Segment Anything to biomedical images, with models fine-tuned on microscopy data. It's for researchers who need to label cells or structures such as mitochondria in electron microscopy volumes. The software runs locally on Windows, macOS and Linux and is open source under the MIT license.
19Updated 7 months agoMIT
Docker · Web#Git integration#Hybrid search#MCP
RepoRelay makes Git repositories searchable by AI coding assistants across projects and versions. It's for developers who want a shared code index on their own infrastructure, accessible from different editors.
15KUpdated 1 day agoMIT
macOS · Windows · Linux#Batch processing#LM Studio integration#Multilingual
Subtitle Edit is an offline desktop application for people creating captions or revising subtitle files alongside video. Editing, format conversion and playback run on your computer. Optional translation and speech services send requests to external providers.
7.3KUpdated 1 year agoApache-2.0
#Hugging Face integration#Tool calling#Web search
InternLM is a family of downloadable language models for developers and researchers building AI assistants or adapting models to their own applications. It includes base models for further training and chat models tuned to follow instructions.
92.3KUpdated 1 day agoApache-2.0
Linux · iOS · Android · Web#Home Assistant integration#Multilingual#Wake word detection
Home Assistant Assist lets you control your smart home through natural language. It's built into Home Assistant and can process voice entirely on your own hardware, keeping those voice commands local.