Collection
Run agents on your own machine
Runtimes, models and tooling that work on hardware you control.
212 tools · showing 1–24
Deployment llama.cpp
LLM inference in C/C++ across CPU and GPU backends, using the GGUF format with quantization, a REST server, and a WebUI
Coding n8n
Workflow automation platform combining a visual canvas with custom code, self-hosted or cloud, with 1500+ integrations and AI agents
Voice whisper.cpp
C/C++ port of OpenAI's Whisper speech-recognition model, dependency-free and optimized for on-device inference
Training Mlx
MLX: An array framework for Apple silicon
Coding +1Goose
Rust-built local agent with desktop, CLI, and API surfaces, 15+ model providers, and 70+ MCP extensions
Monitoring +1Langfuse
Open-source platform for tracing, evaluating, and debugging LLM applications, self-hosted or cloud
Coding LiteRT
On-device runtime (formerly TensorFlow Lite) for running models at the edge.
Coding Maka
Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and terminatio
Coding +1OpenHands
Self-hosted control center running OpenHands, Claude Code, Codex, or any ACP agent across local, Docker, VM, and cloud backends
Connectors +1JiuwenSwarm
JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your f
Inference Manifest
Open-source LLM router exposing one OpenAI-compatible endpoint across API keys, subscriptions, and local models, with cost tracking
Coding Multica
Assigns issues to coding agents like human teammates, with squads, autopilots, reusable skills, and unified local and cloud runtimes
Deployment oMLX
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Inference +1LocalAI
Self-hosted engine that runs LLM, vision, voice, image, and video models on any hardware behind OpenAI-compatible APIs
Inference Ollama
Runs open large language models locally without an API key
Coding +1OpenDesign
The open-source Claude Design alternative
Deployment No Mistakes
A local git proxy in front of your real remote. Clean up PRs before they land in origin.
Memory +1Xerj
XERJ is the new way for AI to search data.
Deployment +2Foundry Local
Foundry Local is an end-to-end local AI solution for building applications that run entirely on the user's device.
Interface +1Jan
Desktop app for running open-weight LLMs locally or connecting to cloud providers, exposing an OpenAI-compatible local API
Memory LEANN
Stop storing embeddings, and still keep your recall. LEANN is a low‑storage vector index that recomputes embeddings on t
Deployment Mesh LLM
Distributed LLM inference that pools GPUs across machines and serves one OpenAI-compatible API, splitting large models across nodes
Inference +2MLX-Serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mo
Interface +2Octop
A smarter, self-hosted AI assistant — multi-user, multi-agent.
More ways in
Start with another goal.
Code with an agent
Agents and libraries that read, write and review code in your repo.
Browse tools
Build a personal assistant
Runtimes and skills for an agent that handles your inbox, calendar and daily errands.
Browse tools
Research and write from your own sources
Deep-research pipelines, drafting tools and retrieval over your own documents.
Browse tools
Automate your marketing
Agents that draft content, schedule posts, research leads and keep campaigns running.
Browse tools
Answer your customers
Support agents, help-desk integrations and the chat channels they answer on.
Browse tools
Create images, video and music
Generation and editing for imagery, animation, video and audio.
Browse tools
Give agents a voice
Speech recognition, synthesis and the parts of a spoken conversation.
Browse tools