AI tools for Linux

A2A Protocol

Agents

Open standard for letting AI agents from different frameworks talk to each other.

Amazon Q Developer

Coding · Multi-model (Amazon proprietary + partners)

AWS's in-IDE coding assistant and agent, formerly CodeWhisperer, tuned for cloud-heavy workflows.

Atua

Agents · Multi-model (BYO key)

Keyboard-summoned macOS AI assistant that reads your screen and drives system apps with your own API keys.

BrainSoup

Agents · Multi-model (ChatGPT, Mistral, local LLMs)

Windows desktop app for building teams of specialized AI agents that collaborate through chat.

ChatBar

Writing · Multi-model (ChatGPT, Claude, Gemini, Copilot, Perplexity, Pi, Poe)

Menu-bar launcher that puts ChatGPT, Claude, Gemini, Copilot, Perplexity, Pi and Poe one keystroke away.

Cherry Studio

Agents · Multi-model

Open-source desktop AI client that wires 300+ LLMs into one chat, knowledge-base, and agent workspace.

Claude Code

Coding · Claude (Opus / Sonnet / Haiku)

Anthropic's agentic coding tool that reads, edits, and ships code from the terminal, IDE, or web.

DaVinci Resolve

Video · DaVinci Neural Engine (proprietary)

Hollywood-grade post-production suite with a Neural Engine that quietly automates the tedious parts of editing, color, and audio.

Daytona

Agents

Secure, isolated sandboxes for running AI-generated code with sub-90ms cold starts.

EKHOS AI

Audio · Proprietary local models

Offline Windows transcription app with speaker diarization, GPU acceleration, and 98-language support.

EasyChat AI

Writing · ChatGPT (OpenAI)

Windows desktop ChatGPT client with a polished native UI and a bring-your-own-key lifetime option.

Elephas

Writing · Multi-model (GPT-5, Claude, Gemini, BYO API)

Privacy-first Mac AI writing assistant that redacts PII before any cloud call and indexes your files locally.

GitHub Spec Kit

Coding · Multi-model

Open-source toolkit that forces AI coding agents through a Spec to Plan to Tasks to Implement workflow.

Hermes Agent

Agents · Multi-model (300+ via Nous Portal)

Open-source multi-channel AI agent with persistent memory, scheduling, and subagent delegation from Nous Research.

InfiBench

Evaluation

Stack Overflow-derived benchmark for evaluating code LLMs on real-world programming questions.

IntelliBar

Writing · Multi-model (GPT-4o, Claude 3.5, Gemini, o1, Llama, DeepSeek, Ollama)

Native macOS menu-bar client that talks to every major LLM with your own API keys.

Keploy

Coding

Open-source AI testing platform that records real API traffic and replays it as regression tests in CI.

Kiln AI

Evaluation · Multi-model

Open-source workbench for building, evaluating, and fine-tuning AI agents across 190+ models.

Kong AI Gateway

Agents · Multi-model

Enterprise API gateway extended to route, govern, and observe LLM and agent traffic across providers.

Kotaemon

RAG · Multi-model (OpenAI, LlamaCPP, any OpenAI-compatible endpoint)

Open-source RAG UI for chatting with your own documents, locally or self-hosted.

LM Studio

Agents · Multi-model (gpt-oss, Qwen3, Gemma, DeepSeek-R1, Llama, others)

Desktop app for discovering, downloading, and running open-weight LLMs locally with an OpenAI-compatible server.

Ludwig

Fine-tuning · Multi-model (PyTorch + HuggingFace Transformers)

Declarative, YAML-driven deep learning framework for fine-tuning LLMs and multi-modal models without writing training loops.

MockingBird

Audio · GE2E + Tacotron + HiFi-GAN/WaveRNN/Fre-GAN

Open-source Mandarin-first voice cloning that mimics a speaker from a 5-second sample.

Msty

Writing · Multi-model (Ollama, Claude, GPT, Gemini, others)

Privacy-first desktop AI workspace that runs local and cloud models side by side.

ONNX

Fine-tuning

Open standard for representing and exchanging machine learning models across frameworks and runtimes.

Ollama

Coding · Multi-model (Llama, Qwen, Gemma, DeepSeek, Mistral, Phi, etc.)

The de facto runtime for running open-weights LLMs locally, now with a paid cloud tier for bigger models.

OpenClaw

Agents · Bring-your-own (Claude, GPT, others)

Open-source local AI agent that controls your computer and talks back through your messaging apps.

PaletteBrain

Writing · OpenAI (BYO key); Azure OpenAI supported

macOS keyboard launcher that pipes selected text in any app to ChatGPT via your own OpenAI key.

Pieces

Coding · Multi-model (BYO OpenAI, Anthropic, Gemini, Ollama)

On-device long-term memory layer that feeds your last nine months of work context into any LLM or IDE assistant.

PyGPT

Writing · Multi-model (GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Ollama)

Open-source desktop AI assistant that wires every major LLM provider into one local app with agents, vision, and a code interpreter.

Reasonix

Coding · DeepSeek (e.g. deepseek-v4-flash)

DeepSeek-native terminal coding agent built around byte-stable prefix caching for cheap long sessions.

Recommenders

Coding · Multi-algorithm (ALS, xDeepFM, others)

Open-source Python library with classical and deep-learning algorithms for building recommendation systems.

Riffo

Agents · OpenAI GPT (undisclosed)

AI desktop file organizer that bulk-renames messy filenames and auto-sorts files into folders.

ScreenSnapAI

Writing · OpenAI / Anthropic (BYO key)

Native macOS screenshot tool that auto-names captures and lets you chat with an LLM about what's on screen.

TurboVec

RAG

Rust-powered vector index with 2-4 bit TurboQuant compression for SIMD-accelerated RAG search.

Vibe

Audio · OpenAI Whisper (via whisper.cpp)

Offline desktop transcription app powered by Whisper, with diarization, batch processing, and an HTTP API.

Voicebox

Audio · Multi-model (Chatterbox, Qwen TTS, Whisper, etc.)

Open-source desktop voice studio for local cloning, dictation, and giving MCP agents a voice.

World Monitor

Agents · Multi-model (Claude, GPT via MCP)

Real-time global intelligence dashboard fusing 56 map layers, 500+ news feeds, and an AI analyst into one situational-awareness console.

WriteMage

Writing · OpenAI ChatGPT (BYO key or managed)

Native macOS and iOS overlay that drops ChatGPT into any app, Spotlight-style.

oMLX

Coding · Multi-model (Qwen, Llama, Mistral, Gemma, DeepSeek, MiniMax, GLM)

Native macOS LLM inference server built on MLX, with paged SSD KV caching for Apple Silicon agents.

omp (Oh My Pi)

Coding · Multi-model (Claude, OpenAI, others)

Open-source terminal coding agent with LSP, DAP, subagents, and a native Rust execution engine.

pgMagic

Coding · OpenAI (user-supplied API key)

Mac desktop client that lets you chat with your Postgres database in natural language using your own OpenAI key.