Run agents on your own machine

llama.cpp

Deployment

ggml-org

LLM inference in C/C++ across CPU and GPU backends, using the GGUF format with quantization, a REST server, and a WebUI

ggufquantizationguilocal-first

Platform

n8n

Coding

n8n-io

Workflow automation platform combining a visual canvas with custom code, self-hosted or cloud, with 1500+ integrations and AI agents

orchestrationagent-builderlocal-first

whisper.cpp

Voice

ggml-org

C/C++ port of OpenAI's Whisper speech-recognition model, dependency-free and optimized for on-device inference

stton-devicemetalquantization

Platform

OpenHands

CodingDeployment

OpenHands

Self-hosted control center running OpenHands, Claude Code, Codex, or any ACP agent across local, Docker, VM, and cloud backends

acpdockerclilocal-first

QwenPaw

ConnectorsMemory

agentscope-ai

Your Personal AI Assistant: easy to install, deploy on your own machine or on the cloud.

productivitymulti-agentlocal-firstchatbotskill

Goose

CodingInterface

aaif-goose

Rust-built local agent with desktop, CLI, and API surfaces, 15+ model providers, and 70+ MCP extensions

acpclimulti-providerlocal-first

JiuwenSwarm

ConnectorsInterface

openJiuwen-ai

JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your f

productivityfeishuxiaoyicronmobile

MNN

Coding

alibaba

Lightweight deep learning engine for on-device inference and training, with runtimes for local LLMs and diffusion models

on-devicemobileembeddedquantization

Supermemory

CodingMemory

supermemoryai

Supermemory is broader than mem0, Engram, Graphiti, or CocoIndex. Those solve storage, coding-agent notes, temporal fact

ragknowledge-graphcontext-enginelocal-first

Hermes WebUI

Interface

nesquena

Browser interface for the Hermes Agent with chat, sessions, a workspace file browser, and profile and task controls

chatbotlocal-firstpwassh-tunnel

InvokeAI

Generative MediaInterface

invoke-ai

Locally hosted creative engine for diffusion image generation with a unified canvas, node workflows, and gallery management

stable-diffusiondiffusionfluxlocal-first

Langfuse

MonitoringQA

langfuse

Open-source platform for tracing, evaluating, and debugging LLM applications, self-hosted or cloud

observabilityevaluationpromptlocal-first

Nanobot

MemoryConnectorsInterface

HKUDS

nanobot: The Ultra-Lightweight Personal AI Agent

productivitylocal-firsttelegramdiscordchatops

OpenDesign

CodingInterface

nexu-io

The open-source Claude Design alternative

ui-designdesign-systemdesktoplocal-first

LocalAI

InferenceGenerative Media

mudler

Self-hosted engine that runs LLM, vision, voice, image, and video models on any hardware behind OpenAI-compatible APIs

local-firstopenai-compatiblellama-cppmultimodal

Maka

Coding

apache

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and terminatio

local-firstdesktopsandboxevent-sourcing

Open WebUI

Interface

open-webui

Self-hosted, offline-capable AI platform for Ollama and OpenAI-compatible models with RAG, tools, and multi-user access control

ollamaraglocal-firstopenai-compatible

OpenConnector

Coding

oomol-lab

Open-source connector gateway giving agents authenticated access to 1,000+ SaaS providers via SDK, CLI, MCP and HTTP/OpenAPI

oauthlocal-firstclisdk

FreeLLMAPI

DeploymentCoding

tashfeenahmed

OpenAI-compatible proxy that stacks the free tiers of 16 LLM providers (~1.7B tokens/month) behind one /v1 endpoint — plus any custom OpenAI

gatewayopenai-compatiblefailoversmart-routing

LiteRT

Coding

google-ai-edge

On-device runtime (formerly TensorFlow Lite) for running models at the edge.

on-devicegpunpuquantization

Platform

Multica

Coding

multica-ai

Assigns issues to coding agents like human teammates, with squads, autopilots, reusable skills, and unified local and cloud runtimes

productivitymulti-agenttask-managementlocal-firstworkspace

OpenJarvis

InferenceTraining

open-jarvis

Personal AI, On Personal Devices

productivitylocal-firstollamaclicron

PicoClaw

Connectors

sipeed

Single-binary Go assistant for $10-class hardware, running in under 10MB RAM with 16+ chat channels

productivitylightweightrisc-vlocal-firstembedded