There’s no place like 127.0.0.1
Find AI apps, model servers, coding assistants and creative tools you can run locally or self-host on your own hardware.
- +AionUiAI Bots for Chat Appstoday
- +whichllmLocal Model Runnerstoday
- +React Native RAGLLM Libraries and SDKsyesterday
- +zvec-grepAI Search and Deep Researchyesterday
- +AgentSocietyAgent Frameworksyesterday
- ▲mattpocock/skillsNew stars per day, last 7 days: 1230, 1222, 1097, 983, 778, 508, 0+5.8K ★
- ▲h4ckf0r0day/obscuraNew stars per day, last 7 days: 995, 515, 765, 1326, 729, 296, 0+4.6K ★
- ▲vercel-labs/agent-desktopNew stars per day, last 7 days: 762, 960, 798, 713, 588, 375, 0+4.2K ★
- ▲obra/superpowersNew stars per day, last 7 days: 511, 614, 635, 571, 544, 360, 0+3.2K ★
- ▲Alishahryar1/free-claude-codeNew stars per day, last 7 days: 615, 448, 829, 413, 389, 237, 0+2.9K ★
Recommended tools
All 2,000+ tools14.4KUpdated 1 day agoAGPL-3.0
macOS · Windows · Linux#Browser automation#LLM tracing#MCP
BrowserOS neo is a secondary Chromium browser for AI agents handling web tasks that require signed-in accounts. Agents work in their own tabs while you continue browsing, with a live view of their actions.
61.6KUpdated 7 hours agoMIT
macOS · Windows · Linux · iOS · Android · Web#Git integration
T3 Code is a locally hosted interface for developers who want to control coding agents on their computer, including from another device. Its server and web app run on your machine, but model processing depends on the connected provider. With the standard Claude Code cloud connection, prompts and model responses travel over the network to its model service.
119.3KUpdated 3 days agoAGPL-3.0
iOS · Android · Web#Multi-user access#Semantic search
Immich is a self-hosted photo and video manager for people who want to keep their collection on their own server. Its mobile apps and web interface provide access to the same library.
9.5KUpdated 3 weeks agoApache-2.0
macOS · Windows · Linux · Docker#Structured output
Cog packages machine learning models for researchers and developers serving them on their own infrastructure. It handles the container environment and inference API around a Python model.
Skills (mattpocock)
13 videos325.2KUpdated 4 days agoMIT
#Agent Skills#Context compression#Git integration
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.
1.3KUpdated 14 hours agoMIT
macOS · Windows · Linux · Docker · Web#Guardrails#Multi-user access#Ollama integration
LibreDB Studio is a self-hosted database IDE for developers and database teams who want browser access to data inside their own network. It can run beside the database, with an interface that also works on phones and tablets.
4.7KUpdated 1 day agoApache-2.0
#Code execution#Hybrid search#MCP
Docker Agent runs individual AI agents or teams from configuration files. Developers can use it for coding assistants, research tasks and automation workflows.
125.9KUpdated 5 hours agoMIT
macOS · Windows · Linux · iOS · Android#Browser automation#Code execution#Git integration
Orca is a desktop workspace for developers managing several AI coding agents on the same project. It keeps each task in a separate Git worktree so agents can edit independently while you compare their results.
45.7KUpdated 2 days ago
macOS · Windows · Linux#Hugging Face integration#MCP#OpenAI-compatible API
Jan is a desktop AI chat app for people who want to run models on their own computer while retaining the option to use cloud providers. Local model use works offline; choosing a hosted model sends requests to that provider.
39KUpdated 4 days agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#LM Studio integration#MLX
llmfit helps people choosing models for their own computers compare what will fit in memory and how fast it might run. It checks your hardware before recommending models, so you can assess candidates before downloading them.
111.4KUpdated 5 hours agoAGPL-3.0
macOS · Windows · Linux · Docker#Batch processing#MCP#Multilingual
VoiceStudio is a local AI voice studio for creators who need speech generation and audio production without uploading their recordings. It combines voice creation, video dubbing and longer spoken projects in one application.
13.1KUpdated 10 hours agoGPL-3.0
macOS#Multilingual#Streaming inference#Works offline
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.
7.5KUpdated 3 days agoMIT
macOS#LM Studio integration#Ollama integration#Works offline
Dayflow is an automatic time tracker and work journal for developers, freelancers, and other people who work on a Mac. It uses screen activity to reconstruct what you worked on without manual timers or tags.
35.7KUpdated 2 days agoApache-2.0
Linux · Docker#Browser automation#Code execution#MCP
Obscura is a headless browser engine for developers building AI agents and web scraping systems with many independent sessions. Each session starts with fresh state, keeping cookies, logins and cached data separate between tasks.
1.8KUpdated 3 days agoApache-2.0
macOS · Linux#Multimodal input#OpenAI-compatible API
GuideLLM benchmarks LLM deployments so engineering and ML teams can assess capacity and response times under expected traffic. It can test self-hosted servers through OpenAI-compatible or vLLM-native interfaces.
983Updated 1 week agoMIT
Docker · Web#Git integration#MCP#Ollama integration
OpenFlowKit is a diagram editor for developers who need to explain software architecture or understand an existing codebase. You can draw directly, work in text, or let an AI agent edit the same canvas.
24.2KUpdated 1 day agoApache-2.0
macOS#Agent Skills#Browser automation#LLM tracing
agent-desktop lets developers give AI agents control of macOS apps such as Finder, Safari and Xcode. It identifies controls through the app's accessibility tree, so agents can act on buttons and text fields by their UI structure.
11.9KUpdated 3 days ago
macOS · Windows · Linux · Docker · Web#Batch processing#ControlNet#GGUF
Wan2GP generates media on your own computer for creators who want to work with several AI models in one browser interface. It builds on Wan-Video/Wan2.1 and focuses on making generation accessible on GPUs with limited memory.
303.9KUpdated 1 week agoMIT
Windows#Guardrails#MCP#Multi-agent workflows
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.
35.6KUpdated 11 hours agoApache-2.0
Docker · Web#Agent Skills#Hybrid search#RAG
Qdrant is a vector database for developers building semantic search, retrieval-augmented generation (RAG), recommendations and AI agent memory. It stores embeddings with metadata so applications can find similar items within a relevant subset of their data.
51.6KUpdated 24 hours agoApache-2.0
macOS · Windows · Linux#Browser automation#Guardrails#Tool calling
agent-browser lets AI agents interact with websites through compact text snapshots and references to specific page elements. It's for developers connecting coding assistants or other agents to a browser without sending them the full page HTML.
42KUpdated 2 days agoMIT
Docker · Web#LM Studio integration#Ollama integration#OpenAI-compatible API
Open Notebook is an alternative to Google's NotebookLM for researchers, students and professionals working with their own materials. It brings research and notes together while letting you choose what context an AI model can access.
84.8KUpdated 6 hours agoApache-2.0
macOS · Windows · Linux · Docker · Web#Agent Skills#Git integration
HyperFrames turns web layouts and animations into videos for developers and teams building automated video workflows. It uses plain HTML and CSS, so you can create compositions yourself or work with an AI coding assistant without adopting React.
156.7KUpdated 3 days agoMIT
macOS · Windows · Docker · Web#LLM tracing#MCP#Multi-agent workflows
Langflow is a visual builder for developers creating AI agents and applications that answer questions using connected data. It lets you assemble workflows visually and customize their components in Python.
52.9KUpdated 16 hours agoMIT
macOS · Windows · Linux · Android · Docker · Web#Context compression#llama.cpp backend#LM Studio integration
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.
5KUpdated 2 weeks agoMIT
macOS · Windows · Linux#Agent Skills#Multimodal input#Tool calling
Phone Harness connects an AI agent to a real iPhone or Android to carry out tasks through app screens. It's for developers who want phone automation without relying on an app API.
Superpowers
13 videos318.1KUpdated 2 weeks agoMIT
Windows#Agent Skills#Code execution#Git integration
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.
187.1KUpdated 13 hours agoMIT
macOS · Windows · Linux · Docker#GGUF#llama.cpp backend#Multimodal input
Ollama runs open models for people who want local AI applications, model chat or a backend for coding assistants. It provides a command-line interface and an API, with a choice between inference on your hardware and its cloud service.
103.3KUpdated 5 days agoBSD-3-Clause
Docker#Guardrails#MCP#Resumable workflows
Scrapling is a Python web scraping framework for developers collecting data from individual pages or crawling whole sites. Its adaptive parser can relocate selected elements when a website's layout changes.
8.8KUpdated 3 days agoApache-2.0
Docker#Distributed execution
MONAI is a framework for researchers and developers building AI models for medical images. Its Core library provides medical-specific tools for training and evaluating models within existing PyTorch workflows.
70.6KUpdated 10 hours ago
macOS · Windows · Linux · Web · VS Code · JetBrains#Agent Client Protocol#Code execution#llama.cpp backend
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.
noemaai.comChat With Your Documents
macOS · iOS#GGUF#MCP#MLX
Noema is a local AI assistant for people who want to chat with models and get answers from their files on Apple devices. It brings models, documents and tools into a native workspace on iPhone, iPad, Mac and Vision Pro.
MoneyPrinterTurbo
7 videos143.8KUpdated 3 days agoMIT
macOS · Windows · Linux · Docker · Web#Agent Skills#Batch processing#Hugging Face integration
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.
2.7KUpdated 1 week agoApache-2.0
macOS#Hugging Face integration#MLX#Multimodal input
MTPLX is a native Mac app, command-line tool and local LLM server for people running chat or coding models on Apple Silicon. It uses a model's own multi-token prediction heads to accelerate generation without a separate draft model.
59.5KUpdated 14 hours agoApache-2.0
macOS · Windows · Docker · Web#Agent Skills#llama.cpp backend#LM Studio integration
DeepTutor is a self-hosted AI tutor for learners who want to study their own materials through a browser or CLI. It supports Docker deployment and uses configured model providers for its AI capabilities. Hosting the app locally is separate from model inference; requests to a remote provider leave the host.
30.7KUpdated 7 days agoApache-2.0
Docker · Web#MCP#Multi-agent workflows#Ollama integration
GPT Researcher is an AI research agent for people who need detailed reports based on web evidence, their own documents, or both. It investigates a question and writes a report with inline citations readers can check.
117.4KUpdated 6 hours agoApache-2.0
macOS · Windows · Web#Agent Skills#Hybrid search#MCP
Claude Mem gives coding assistants persistent project memory, so developers can carry earlier decisions and failed approaches into later sessions without explaining them again.
4.3KUpdated 4 days agoApache-2.0
#Distributed execution
NeuralForecast is an open-source Python library for data scientists and developers who want to train and compare neural time series forecasting models in their own Python environment. It brings recurrent networks and forecasting-specific architectures under one interface, so comparing models doesn't require working with separate research implementations. The license is Apache 2.0.
52.1KUpdated 1 day agoApache-2.0
Windows · Web · JetBrains#Agent Skills#Batch processing#Git integration
OpenCodeReview is a locally installed AI code review CLI for developers who want findings tied to specific code lines. It sends code to a configured LLM endpoint through OpenAI- or Anthropic-compatible APIs. The local CLI handles the review process; model inference depends on that endpoint.
394.5KUpdated 7 hours agoMIT
macOS · Windows · Linux · iOS · Android · Docker#Multi-user access#Persistent memory#Tool calling
OpenClaw is an AI assistant you run on your own computer for personal tasks or shared team use. It connects to existing messaging services, so you can reach the assistant through the apps you already use.
13.6KUpdated 2 days agoApache-2.0
Docker · Web#Batch processing#Git integration#Resumable workflows
Codex Security is a locally run vulnerability scanner for developers and security teams, available as a CLI and TypeScript SDK. It can run on your machine, in CI or in containers, but sends AI analysis requests to a cloud model provider. Scans require provider credentials and an internet connection.
22.4KUpdated 14 hours ago
macOS · Windows · Linux#MCP#Multimodal input#Ollama integration
Screenpipe records computer activity so people can revisit past work and give AI agents context from screens and conversations. Capture history stays on your device by default.
77.2KUpdated 1 day agoMIT
macOS · Windows · Linux#Agent Skills#Code execution#Multimodal input
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.
39.1KUpdated 9 hours agoMIT
macOS · Windows · Linux#Code execution#Multi-agent workflows#OpenAI-compatible API
Oh My Pi is a terminal coding assistant for developers who want an AI agent working directly in their codebase with IDE tools. It's a fork of Pi that supports both local model servers and cloud providers.
202.1KUpdated 8 hours agoAGPL-3.0
Docker#Batch processing#MCP#Structured output
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.
1.6KUpdated 1 day agoMIT
macOS#Hugging Face integration#Image-to-image#MLX
Nativ is a macOS app for people who want AI chat and coding tools to use models running on their own Mac. It combines a chat workspace, model library, and local inference server.