Run agents on your own machine

Tool

Kindalive

Coding

smithandrewjohn

Robot emotions through simulated neurochemistry — shown on an LED dot-matrix face.

roboticsled-displayemotionalollama

Tool

Minions

Coding

HazyResearch

A communication protocol that enables small on-device models to collaborate with frontier models in the cloud

local-firsttoken-optimizationollamaon-device

Harness

HermesClaw

SecurityDeployment

TheAiSingularity

Community stack running the Hermes Agent inside NVIDIA's OpenShell sandbox with kernel-enforced network and filesystem limits

sandboxdockeropenshellllama-cpp

App

Atomic Hermes

InterfaceConnectorsInference

AtomicBot-ai

Native macOS AI assistant bundling chat, terminal, file browser, computer-use, and local models in one app

productivitymacoslocal-firstdesktopcomputer-use

BaseRT

Inference

6.4x faster than llama.cpp, 3.9x faster than MLX

apple-siliconlocal-firstmacosllm-runtime

App

Cherry Studio

Interface

CherryHQ

Cross-platform desktop client for interacting with multiple LLM providers

productivitymulti-providerdesktopollamaknowledge-base

Ollama

Inference

Runs open large language models locally without an API key

local-firstopen-weightscli

App

OpenWorker

SecurityConnectors

andrewyng

OpenWorker is a local desktop agent built to return finished work, a document or a Slack reply.

desktopvulnerability-scannerslackollama

App

Text Generation Webui

InferenceTrainingGenerative Media

oobabooga

A desktop app for local LLMs. Open source, no telemetry. Text, vision, tool-calling, web search. UI + API.

productivitydesktoplocal-firstggufmultimodal

VeritasGraph

MemoryDeploymentResearch

Governed on-prem GraphRAG & AI agents with verifiable proof

graphraglocal-firstollamaknowledge-graph