Best Artificial Intelligence Software for Linux - Page 23
View:
Compare the Top Artificial Intelligence Software for Linux as of September 2026 - Page 23
Sort By:
-
1
AG2
AG2
AG2 is the open source AgentOS for building production-ready AI agents and multi-agent systems in minutes, not months. Formerly AutoGen, it provides an open source Python framework for building, orchestrating, and scaling AI agents that can collaborate through shared context, use tools, execute workflows, and support both autonomous and human-in-the-loop patterns. AG2 is designed for developers who want to build systems, not prompts, with simple and intuitive syntax, built-in conversation patterns, and a flexible platform for multi-agent automation. Agents in AG2 can extend their capabilities with tools, allowing them to interact with external systems, fetch real-time data, execute code, search the web, process documents, and complete complex tasks beyond a model’s internal knowledge. It supports many LLM providers and local models, including OpenAI-compatible endpoints, Anthropic Claude, Gemini through Vertex AI, DeepSeek, and LM Studio.Starting Price: Free -
2
Multica
Multica
Multica is an open source project management platform for human and agent teams, built to turn coding agents into real teammates rather than separate tools. It gives humans and AI agents the same workspace, where agents can be assigned issues, report progress, reply in comments, raise blockers, ship code, and appear in the member list with profiles, avatars, and open-issue queues. Users can assign work to an agent the same way they would hand a task to a teammate, or open a chat window to ask it to draft an issue, answer a question, or handle a one-off request. Multica’s shared context layer keeps issue comments, attachments, reports, task history, and workspace knowledge accessible to both people and agents, while skills act as workspace-wide playbooks that let every agent reuse the same definitions and operating instructions.Starting Price: Free -
3
AionUi
AionUi
AionUi is a desktop workspace where AI agents live on the user’s computer and actually collaborate across everyday tasks such as writing code, making slides, sorting files, crunching numbers, editing photos, creating reports, writing papers, and running automations 24/7. Users can work with one agent, run multiple agents in parallel, assign tasks to the right assistant, or team them up inside one unified workspace. AionUi auto-detects Claude Code, Codex, Gemini CLI, Aion CLI, OpenCode, OpenClaw, Goose, and 20+ more tools already installed on the machine, so users can reuse their existing setup without reinstalling or duplicating tools. It includes 20+ built-in assistants for presentations, Excel, financial models, documents, academic papers, diagrams, UI/UX design, games, creative writing, project planning, recruiting, setup, and autonomous end-to-end work. Users can also create custom assistants tailored to their workflow.Starting Price: Free -
4
Kimchi
Kimchi
Kimchi is a centralized gateway for managing SaaS and self-hosted AI models, built to help teams deploy, route, optimize, and scale LLM infrastructure without changing the developer workflow. It gives organizations one control layer for AI coding agents, open-source models, commercial models, and internal inference, allowing teams to combine lower-cost OSS models with higher-tier providers such as Claude, OpenAI, Gemini, and others when the task requires it. Kimchi focuses on reducing LLM cost while making development more autonomous, with fast model routing, coding-oriented inference, MCP integration, multi-agent workflows, interchangeable OSS and commercial models, and low-friction local setup. It supports running the Kimchi coding agent across teams, giving engineering organizations broader access to AI coding while preserving team-wide usage attribution, cost visibility, and operational control.Starting Price: Free -
5
oh-my-codex (OMX)
oh-my-codex (OMX)
oh-my-codex, also known as OMX, is a workflow layer for OpenAI Codex CLI that helps users start stronger coding sessions and manage complex development work with more structure. The tool keeps Codex as the execution engine while adding prompts, skills, hooks, runtime support, HUDs, agent teams, and durable project state. OMX supports a recommended workflow built around deep interviews, planning, goal creation, execution, verification, and long-running task management. It stores project guidance, plans, logs, memory, and runtime state in a dedicated .omx folder so work can stay organized across sessions. The platform is primarily designed for macOS and Linux users working with Codex CLI, with additional support for team workflows through tmux. oh-my-codex helps developers use Codex more effectively by adding repeatable processes, stronger task routing, and better runtime coordination.Starting Price: Free -
6
oh-my-claudecode
oh-my-claudecode
oh-my-claudecode is a multi-AI orchestration plugin for Claude Code that helps developers coordinate Claude, Gemini, and Codex in one structured workflow. The platform is designed to turn Claude Code into a more powerful development environment with specialized agents, skills, execution modes, and MCP-powered tools. It includes 19 specialized agents for planning, architecture, debugging, execution, review, security, testing, design, documentation, and other software development tasks. oh-my-claudecode supports powerful modes such as Autopilot, Ralph, Ultrawork, Deep Interview, Team, and Planning to match different coding and project needs. The plugin also includes tools for language server integration, structural code analysis, persistent Python work, project memory, and session state. oh-my-claudecode helps developers automate complex engineering work, coordinate multiple AI systems, and complete coding tasks with more speed and structure.Starting Price: Free -
7
Docling
Docling
Docling is an easy-to-use, self-contained, MIT-licensed open source toolkit for converting messy documents into structured data and simplifying downstream document and AI processing. It can parse many popular document formats into a unified and richly structured Docling Document, including PDF, DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and scanned pages through an OCR engine of the user’s choice. Docling detects tables, formulas, reading order, chunks, bounding boxes, page headers and footers, pictures, captions, code, list items, paragraphs, cells, and document structure, making extracted content easier to process, search, and ingest into AI, RAG, and agentic systems. It can export parsed documents to JSON, text, Markdown, HTML, and Doctags, giving developers flexible outputs for pipelines and applications. Docling stores and traverses components according to reading order, partitions documents into bite-sized contiguous text chunks.Starting Price: Free -
8
PaddleOCR
PaddlePaddle
PaddleOCR is a leading open source OCR toolkit and document AI engine that turns PDFs and images into structured, LLM-ready data with high accuracy. It is designed to bridge the gap between documents and large language models by extracting, recognizing, parsing, and organizing information from scanned pages, photos, forms, tables, formulas, charts, and complex layouts. PaddleOCR supports more than 100 languages and provides a practical toolkit for building intelligent RAG and agentic applications that need reliable document understanding. Its core capabilities include PaddleOCR-VL, PP-OCRv5, PP-StructureV3, and PP-ChatOCRv4. PaddleOCR-VL is an ultra-compact vision-language model for multilingual document parsing, supporting 109 languages and performing well on complex elements such as text, tables, formulas, and charts. PP-OCRv5 is built for universal-scene text recognition.Starting Price: Free -
9
Laguna XS.2
Poolside
Laguna XS.2 is Poolside’s open-weight agentic coding model, built as the lightest and fastest model in the Laguna family. It is a 33B total-parameter Mixture of Experts model with 3B activated parameters, trained completely in-house on 30T tokens. As Poolside’s newest generation model open to the community, Laguna XS.2 is a second-generation architecture and the company’s first open-weight model, built on the lessons learned from training Laguna M.1 across synthetic data and reinforcement learning. The model is designed for agentic coding workflows, where it can code, act, iterate quickly, and perform best inside Poolside’s coding agent. Laguna XS.2 is positioned as a strong model for rapid agentic iteration, especially for developers and teams that need a compact, efficient coding model rather than a heavier frontier system. It is released under an Apache 2.0 license, allowing the community to evaluate, fine-tune, quantize, serve, and build on the weights.Starting Price: Free -
10
Laguna M.1
Poolside
Laguna M.1 is Poolside’s most capable model for agentic coding, built and trained in-house for software development workflows. It is a 225B total-parameter Mixture of Experts model with 23B activated parameters, trained completely in-house on 30T tokens using 6,144 interconnected NVIDIA H200 GPUs. Poolside trained Laguna M.1 from scratch with its own data work, training codebase, and async on-policy reinforcement learning in its agent harness, all with agentic coding in mind. The model is designed to perform at its best inside Poolside’s coding agent, where it can reason through software tasks, interact with tools, edit code, run tests, and support longer autonomous development sessions. Laguna M.1 is built for developers and teams working on complex coding tasks that require stronger reasoning, architectural understanding, terminal use, and multi-step execution than lightweight models can provide.Starting Price: Free -
11
DiffusionGemma
Google
DiffusionGemma is an experimental open model that explores text diffusion, an exceptionally fast approach to text generation. Released under an Apache 2.0 license, this 26B Mixture of Experts (MoE) model moves beyond the sequential token-by-token processing of typical autoregressive Large Language Models (LLMs). Instead, it generates entire blocks of text simultaneously, delivering up to 4x faster text generation on GPUs. Built on the intelligence-per-parameter of the Gemma 4 family and Gemini Diffusion research, DiffusionGemma integrates a novel diffusion head designed to maximize generation speed. It is designed for researchers and developers exploring speed-critical, interactive local workflows such as in-line editing, rapid iteration, and non-linear text structures. By shifting the decode bottleneck from memory bandwidth to compute, it can generate more than 1,000 tokens per second on a single NVIDIA H100 and more than 700 tokens per second on an NVIDIA GeForce RTX 5090.Starting Price: Free -
12
AutoClaw
Z.ai
AutoClaw by AutoGLM brings Agent execution power into an IM entry point, letting users activate an AI agent avatar with one click, call professional tools autonomously, and complete complex tasks automatically inside a Feishu conversation box. It looks like chat, but it is actually an Agent execution channel: the user starts a goal in a single dialog box, AutoClaw breaks it down, executes the steps, and sends the result and context back into Feishu. The task entrance is just one conversation, not a configuration page, and not another separate task system. Once the task is launched, the agent avatar continues pushing the work forward, while local tools perform real actions and the steps and status unfold along the same track. Feishu then receives not only the final conclusion, but also the context, progress, and the next handoff point. AutoClaw supports one-click OpenClaw setup, Windows and macOS downloads, IM integration, hot-swappable models, and more than 50 skills.Starting Price: Free -
13
RagLeap
RagLeap
RagLeap is a self-hosted AI business platform providing 9 AI roles — AI Manager, Customer Support, Voice Agent, Email Manager, Personal Secretary, DB Analyst and AI COO in one system. Runs on your own server with complete data privacy. Connects to MySQL, PostgreSQL, MongoDB. Handles WhatsApp, Telegram, Voice calls, Email and web chat in 222+ languages. Free self-hosted tier available. Cloud plans from $29/month.Starting Price: $0 -
14
AgentOne
AgentOne
Free alternative to Claude Cowork - AgentOne is an AI agent that helps you get work done, not just talk about it. Give it a goal in plain English, and it can break the task into steps, use the right tools, gather information from connected apps, and work toward a finished result. AgentOne lets non-technical and technical users alike easily automate boring work. With support for over 12,700 apps, services, and websites, AgentOne fits into the tools you already use. It can run multiple agents in parallel to tackle complex tasks faster, sync seamlessly across your devices, and work with hundreds of AI models using your own API keys. Privacy remains a core focus, with your data staying under your control and stored locally whenever possible. Start for free with no credit card required, and experience a more capable, connected, and private approach to AI-powered automation.Starting Price: $8.99/month -
15
Hy3
Tencent
Hy3 preview is Tencent Hy’s most intelligent model in the Hy series to date, built as a 295B-parameter Mixture-of-Experts model with 21B activated parameters, 3.8B MTP layer parameters, and support for up to a 256K token context window. As the first model trained on Tencent Hy’s rebuilt infrastructure, Hy3 preview is designed to improve real-world usability across complex reasoning, instruction following, context learning, coding, agent capabilities, and overall inference performance. It integrates both fast and slow thinking capabilities, allowing direct responses for simpler tasks and deeper reasoning for complex math, coding, and reasoning work. The model is built around well-rounded capabilities across long-context understanding, instruction following, tool use, and agent workflows, with evaluation focused not only on standard benchmarks but also on authentic business and development scenarios.Starting Price: Free -
16
Open Voice OS
Open Voice OS
Open Voice OS is a community-driven, open source voice AI platform for creating custom voice-controlled interfaces across devices with NLP, a customizable UI, and a focus on privacy and security. Built by developers from Linux and FOSS communities around the globe, it is an open platform for making cutting-edge voice assistance technology available to everyone. Open Voice OS is multi-platform, designed for embedded headless devices, single-board computers with screens, DIY smart speakers, Raspberry Pi devices, Mark I and Mark II devices, Linux desktops, laptops, and Docker containers. As a voice operating system, OVOS goes beyond a traditional “Hey Mycroft…” assistant and provides the foundational tools and frameworks for integrating voice interaction into robots, automation systems, smart furniture, mirrors, cloud-based voice services, embedded devices, and smart TVs.Starting Price: Free -
17
LM Studio Bionic
LM Studio
LM Studio Bionic is an AI agent built for getting real work done with open models across coding, research, documents, files, and general knowledge work. It gives users flexible control over where models run: locally on their device, through LM Link, or with frontier open-source models in LM Studio Secure Cloud for heavier tasks. Local models are powered by the LM Studio runtime and can be downloaded directly inside the app, while cloud requests use Zero Data Retention and are processed without being stored after completion. For coding, users can connect a local folder as a Code project and ask Bionic to inspect a codebase, explain unfamiliar logic, search for relevant files, trace behavior, edit code, or debug issues. Inline diffs make changes easy to review as the agent works. Work projects support documents, PDFs, presentations, spreadsheets, and local directories, allowing Bionic to generate new files, organize materials, summarize content, edit existing work, and more.Starting Price: Free -
18
Buzz
Block
Buzz is a self-hostable workspace where humans and AI agents build together in the same rooms, on a relay the team owns. One community brings conversations, agents, workflows, repositories, artifacts, documents, search, and automation into a single workspace with one identity model and one event log. Every message, reaction, workflow step, review approval, canvas update, huddle event, and Git action is recorded as a cryptographically signed Nostr event, giving people and processes the same audit trail. Agents are members, not bots: teams add them to channels like colleagues, give them their own keys and scoped memberships, and let them open repositories, send patches, review code, run workflows, edit canvases, orchestrate other agents, create channels, join voice huddles, and bring the right people into the work. Buzz can search project history and return answers with supporting threads, patches, runs, and approvals.Starting Price: Free -
19
Spokenly
Spokenly
Spokenly is an AI-powered dictation app for Mac, iPhone, Windows, and Linux that turns speech into clean, punctuated text wherever you work. Hold a shortcut, speak naturally, and release to place the transcription directly at the cursor in browsers, email, chat, word processors, IDEs, terminals, and other apps. It supports more than 100 languages, including mixed-language dictation, and offers both local and cloud speech-to-text models. Whisper, Parakeet, and other on-device models can run completely offline, while cloud engines from providers such as OpenAI, Deepgram, Groq, Soniox, and ElevenLabs can be used for higher-accuracy or real-time transcription. Local Only Mode blocks network requests so voice data stays on the device. Modes let users save different transcription models, AI providers, prompts, and output styles for specific tasks, while AI Instructions can remove filler words, fix grammar and punctuation, summarize, rewrite, translate, or reformat dictated text.Starting Price: $8.33 per month -
20
Handy
Handy.computer
Handy is a free, open source, cross-platform speech-to-text app that runs completely offline and puts whatever you say directly into any text field. Press and hold a configurable keyboard shortcut, speak, and release; Handy records your voice, transcribes it locally, and pastes the result into the app you are using. Push-to-talk is enabled by default, but users can switch to a toggle mode that starts and stops recording with separate key presses. Handy supports macOS, Windows, and Linux and keeps voice data on the computer instead of sending audio to cloud services. Users can choose between Whisper models and Parakeet V3, Whisper provides broad multilingual support across more than 99 languages, while Parakeet V3 is optimized for fast CPU performance and automatic language detection. Silence is filtered with voice activity detection, and GPU acceleration is available for Whisper where supported.Starting Price: Free -
21
Vizaye
Vizaye
Vizaye is an AI platform for surface material businesses that combines a website builder, live catalog hosting, room visualizer, and WhatsApp AI assistant. The platform helps manufacturers, retailers, showrooms, dealers, distributors, builders, and contractors turn product catalogs into digital sales experiences. Users can upload products through Excel, photos, or WhatsApp, and Vizaye builds a product website, configures the visualizer, and trains the assistant. Vizaye supports surface materials such as ceramic tiles, marble, granite, wooden flooring, stone, quartz, wallpaper, wall panels, vinyl, SPC, epoxy, laminate, WPC flooring, grout, and ceiling tiles. Its tools include QR engagement, showroom kiosk mode, lead dashboards, inventory management, walk-in sales support, PDF catalog creation, digital marketing, SEO, calculators, and sales playbooks.Starting Price: $79 -
22
ExecuTorch
ExecuTorch
ExecuTorch is PyTorch’s open source framework for deploying AI/ML models directly to edge devices, enabling text, vision, speech, recommendation, and multimodal inference without requiring the cloud. It exports models from PyTorch without intermediate conversion formats, preserves ATen operators, and uses ahead-of-time compilation to optimize performance for target hardware before deployment. Its modular design lets developers choose compile-time and runtime optimizations while staying inside the familiar PyTorch ecosystem, including torchao for quantization. A portable C++ runtime with a base footprint of about 50 KB can run on smartphones, desktops, embedded systems, microcontrollers, DSPs, and Cortex-M processors. ExecuTorch supports Android, iOS, Linux, Windows, macOS, and WebAssembly, with native APIs for C++, Swift, Kotlin, and Objective-C.Starting Price: Free -
23
Atomic Agent
Atomic Agent
Atomic Agent is an open-source, local-first AI agent that runs on your own machine from the terminal. It drives your real tools — shell, files, and browser — and keeps every session on your own disk. Point it at a local model through llama.cpp, or connect a hosted model when you want more power. You choose the model, you own the data, you stay in control. No cloud lock-in. Install with a single command on macOS, Linux, or Windows. Built for developers and power users who want a capable autonomous agent without shipping their work to someone else's cloud.Starting Price: $0 -
24
bb
bb
bb is a local-first, fully customizable IDE for working with AI coding agents, designed to control, automate, and even modify itself. Almost anything in the environment can be changed with a single prompt: users can add panels, CLI commands, skills, plugins, and workflows that immediately become available to their agents. Many of bb’s own capabilities, including GitHub integration, agent memory, scheduled jobs, and remote access, are built as plugins using the same tools available to users. Its CLI is open to external programs such as shell scripts, cron jobs, or bots in Telegram, Signal, and Slack, allowing them to spawn work threads that remain available in the sidebar. bb supports multiple coding agents, including Claude Code, Codex, Cursor, Pi, OpenCode, Grok, omp, and Hermes, letting users assign tasks to the best-suited agent or have one agent spawn and manage another in separate threads. Work runs on the user’s own machine and can continue independently until they return.Starting Price: Free -
25
Reasonix
Reasonix
Reasonix is an open source coding agent designed for long autonomous sessions that remain readable, auditable, and reversible. One local engine powers four interfaces: terminal, desktop app, browser, and ACP-compatible editors, with sessions, permissions, skills, and MCP servers shared across them. Plan mode holds every write until the proposed steps are reviewed and approved, while reads, writes, and shell commands are separately gated and constrained by a workspace sandbox. Each turn creates a checkpoint outside Git, allowing users to rewind a long run without affecting commit history. MCP support over stdio, SSE, and streamable HTTP merges external tools into one registry, while Markdown skills and isolated subagents extend the agent without requiring a fork. Reasonix maps a codebase once and keeps that map throughout the session, letting users queue tasks, review diffs, and resume work without losing context.Starting Price: Free -
26
Zoo Code
Roo Code
Zoo Code is an open source AI coding assistant for your IDE, built to help developers stay on task and ship great code with specialized modes and full model flexibility. Built-in Architect, Code, and Debug modes shape how the agent approaches different tasks, while custom modes let users create workflows for security reviews, documentation, or anything else they need. Architect mode can plan complex changes without editing files, producing strategy documents and file maps for review before code is written. The assistant supports multi-file editing, context management, customizable settings, and full bring-your-own-key support for any provider, making it fully model-agnostic. Every proposed change lands as a diff so developers can see exactly what will change before it touches the codebase, with no silent rewrites. External tools, databases, APIs, and custom resources can be connected through Model Context Protocol.Starting Price: Free -
27
Berd
Block Open Source
Berd is a weird, playful open source desktop app for building and getting real work done with AI agents. Instead of acting like another generic chatbot wrapper, it provides a consistent workspace around capable agents, bringing projects, sessions, files, skills, tools, models, providers, and custom agents into one application. Users can start chats, attach files or folders, choose agents and models, work inside projects, manage skills and extensions, review session history, configure providers, and build automations without losing the thread of the workspace. The experience is designed to make agent work feel grounded, inspectable, and continuous, with clear visibility into which project, files, agent, model, provider, and session state are shaping each interaction. Berd gives agents roles, instructions, skills, tools, and distinctive visual identities so they feel recognizable and easier to understand without hiding what they can actually do.Starting Price: Free -
28
Cumora
Cumora
Cumora is a collaborative workspace where humans and AI agents operate as teammates rather than treating AI as a chatbot that waits for prompts. Each agent has a persona, memory, status, role, voice, editable system prompt, and private workspace for files, notes, and observations. Agents retain context from earlier conversations, build an ongoing understanding of the people they work with, and can take initiative on a user-defined cadence by messaging teammates, posting observations, or assembling small groups around something they noticed. Workspaces support human invitations, projects, attached files, grouped agents, and synchronized live state across desktop, browser, and mobile experiences. Agents can communicate directly with one another, while Whisper rooms let users observe those conversations without participating.Starting Price: Free -
29
Portable Computer by Perplexity
Perplexity
Portable Computer is a local-first version of Perplexity Computer that runs entirely on your own machine, keeping private data on-device while still supporting complex agentic workflows. Built with NVIDIA, it runs the orchestrator, planner, tool router, scheduler, durable task queue, local search index, and AI models locally, so it can analyze data, synthesize files, search documents and code, take actions on the device, and keep long-running jobs active without relying on the cloud. It runs on NVIDIA DGX Spark with Qwen 3.8 27B or PPLX 27B, with NVIDIA Nemotron 3.5 Lightning coming to the model picker. It is trained to complete as much of each task locally as possible and can escalate only the steps that need current information, browser access, connected apps, or frontier reasoning. When a task needs to send content from the device to a cloud service, Portable Computer asks for permission before proceeding.Starting Price: $20 per month -
30
HOL Guard
HOL
HOL Guard is a local-first runtime security layer for AI agents that watches what an AI assistant is about to do and stops risky actions before they happen. It sits between the agent and the computer, evaluating supported tool calls and local artifacts for threats such as secret and credential exposure, destructive commands, prompt-injection-driven actions, malicious or changed packages, risky MCP configuration, and unsafe plugins, skills, hooks, and settings. Known threats can be blocked automatically, while ambiguous actions are paused for user approval so people remain in control. Guard runs entirely on the developer’s machine, works offline, and does not upload files, prompts, or passwords. Local checks typically complete in under 50 milliseconds and require no changes to existing code or routines. It supports coding agents including Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw, with tailored integrations that inspect actions before execution.Starting Price: $4.99 per month