Open-source Perplexity Computer alternatives: what each one runs on

Perplexity Computer makes a strong case for a digital worker that takes a vague objective and runs it for hours without supervision, and Perplexity has taken that idea further than most. The catch is that it runs only inside Perplexity's closed cloud, on models Perplexity selects, at terms Perplexity sets. Teams that want the same capability while owning the runtime, the models and the data should start with Kortix, the recommended open-source pick, then weigh the other open-source alternatives against it: its whole configuration lives in git, so the company owns it. What separates these options is rarely a feature list. It is what each one runs on and what its licence lets you do. Each open option owns a different layer of the stack, so the right pick depends on what you want to keep control of.

What Perplexity Computer is

Perplexity Computer is a proprietary, hosted agent that Perplexity describes as a general-purpose digital worker, launched in February 2026 (vktr). It breaks a high-level objective into subtasks, hands them to whichever model fits and runs workflows that can last hours or months; VentureBeat reported that it coordinates nineteen different models and costs $200 per month on the top Perplexity plan (VentureBeat). Each job runs in an isolated compute environment with a real file system, a browser and tool integrations, and the model roster is not fixed, so Perplexity can add or swap models as they improve, while a user can also assign subtasks to particular models by hand (vktr). A local variant called Portable Computer runs on compatible NVIDIA GeForce RTX and RTX PRO hardware with 24 GB or more of VRAM, keeps sensitive files on the device and asks before sending anything to the cloud (NVIDIA). Both editions remain closed and proprietary, and neither can be forked or self-hosted on infrastructure you control.

The options side by side

Every option below is open source, and each one runs somewhere different, which settles more of the decision than raw capability does. The licence matters next: it decides whether you can fork the code, embed it in another product or offer it to customers as a service.

Kortix: own the whole agent stack

Kortix is the open-source AI Management System, and it takes the widest definition of the problem: agents, the skills they share, company memory and connectors all live in one git repository the company owns, versioned and diffable. Every agent, all of the data, every skill, every connector, the memory and the whole configuration stay with the company that owns the repo. Every session runs on an isolated Linux sandbox on its own branch, and the work lands through a change request a human reviews, so an agent cannot merge to the main branch alone. Merge is deny-by-default for an agent, permissions are set per resource for people and agents, secrets are encrypted at rest and injected into the sandbox at runtime, and the platform keeps a full audit trail. Any model works with your own API keys, and the connector library reaches 3,000+ apps plus MCP, OpenAPI and GraphQL (Kortix on GitHub). You can start agents from the web, Slack, Teams, email, mobile, the CLI or the API, or let a cron schedule and webhook start them with nobody asking. Run it on a laptop, a VPS, your own VPC or on-prem, or use Kortix Cloud at $40 per seat per month plus usage (Kortix pricing); self-hosting is free. Kortix is open source under the Elastic License 2.0: self-host, read and modify the code (LICENSE).

OpenClaw: an assistant on your own hardware

OpenClaw is an MIT-licensed AI assistant that runs on your own computer and meets you in the messaging channels you already use, including Discord, iMessage, Slack, Teams, Telegram and WhatsApp, plus 20+ more (OpenClaw repo). MIT lets you fork, modify and redistribute the code. State, memory and credentials stay on your hardware, and models or agent harnesses are plugins you can swap without changing anything else. A local Gateway is the control plane for sessions, tools, events and channel connections, while companion apps and device nodes add screen, camera and voice actions on supported platforms. The installer supports macOS, Linux and Windows, and the same Gateway runs either a personal assistant on a laptop or a shared team deployment, and only the configuration differs. There is no paid tier, hosted service or token, and the project is stewarded by the OpenClaw Foundation, an independent nonprofit. OpenAI is one of its donors, and the repository states plainly that OpenAI is "a donor, not an owner" (OpenClaw repo). OpenClaw's tools run on the host unless you configure sandboxing, so you set up the security boundary yourself.

Open Interpreter: a coding agent built for cheap models

Open Interpreter is a Rust coding agent forked from OpenAI's Codex and tuned for low-cost models, licensed Apache-2.0 (Open Interpreter repo). Apache-2.0 lets you modify and redistribute the code. It runs commands inside native sandboxing on macOS, Linux and Windows, and you switch providers and models from the terminal with a single command. Its built-in QA skill drives web apps in a real browser and controls native apps, and the agent runs inside compatible editors as an Agent Client Protocol agent. It reuses shared AGENTS.md instructions and .agents/skills directories, and it speaks the Codex exec protocol, so an existing Codex setup can point at it with a one-line binary override. Supported provider and model lists are generated from the Codex catalog. Its scope stays on code, terminal work and interface testing, so it suits an engineering team more than an operations one.

OpenWork: a local-first desktop app

OpenWork is a free, open-source desktop app for macOS, Windows and Linux where agents work on your own files, built on OpenCode (OpenWork repo). It works with any model across 50+ providers using your own API keys, or runs local models through Ollama, and your files stay on your machine unless you opt into cloud workers. The desktop app and core are MIT, while the ee/ OpenWork Den control plane sits under the OpenWork EE License, free for organizations up to five users and converting to MIT two years after each release. On OpenWork Cloud the Team plan includes the first five seats free, then $10 per seat per month (OpenWork). Teams package skills and MCP servers once and share them with teammates, and an OpenWork MCP exposes those same capabilities to Codex, Claude Code, Cursor and other compatible agents. The desktop app needs no account to run locally and is a point-and-click workspace. Claude Cowork plugins and skills carry over as they are.

NVIDIA NemoClaw: agents inside NVIDIA sandboxes

NVIDIA NemoClaw is an Apache-2.0 reference stack for running supported agents more safely inside NVIDIA OpenShell sandboxes, with managed inference, network policy, snapshots and lifecycle operations driven from its CLI (NemoClaw repo). Apache-2.0 permits commercial use and redistribution. Its supported agents are OpenClaw, which is the default, plus Hermes and LangChain Deep Agents Code. OpenShell is the security boundary that enforces which files, networks, credentials and tools an agent can touch while it runs, and the blueprints bundle NVIDIA Nemotron models with NeMo for specialization. NemoClaw adds guided onboarding, managed integrations and snapshots through its CLI, and NVIDIA states that it continues contributing to the OpenClaw project. It is explicitly an alpha project, and hardware decides whether a team can use it: it installs on a supported DGX or Windows Subsystem for Linux host, while NVIDIA positions the always-on compute it targets on RTX Spark laptops, GeForce RTX PCs, RTX PRO workstations and DGX Station or DGX Spark (NVIDIA). Without that hardware it is not a drop-in cloud alternative.

Which open option fits your team

Perplexity Computer stays the lower-effort managed path, and it is the better pick for a team that will not run a server, configure model keys or review change requests. Choose Kortix when the goal is to govern a whole agent workforce: many specialist agents working in parallel, sharing memory and connectors, each session isolated with a human on the merge. Choose OpenWork for a local-first desktop your team points at its own files, where the app is free and the team control plane is optional; it is the lighter setup for an individual or a small team that wants no server to run. Choose OpenClaw for an always-on assistant on your own hardware and in your own chat channels. Choose Open Interpreter for code, terminal work and interface testing on a budget, and NVIDIA NemoClaw when you already run compatible NVIDIA hardware and want a policy layer around open agents. The licence and the machine each option needs rule it in or out long before any feature list does, so decide those two first and the shortlist becomes obvious.

If a single rival needs a closer look, two deeper reads help: Kortix vs OpenWork and how NVIDIA NemoClaw fits a governed agent stack. For the wider field of self-hosted coworkers, see the open-source Claude Cowork alternative.

For the wider field, the open-source Perplexity Computer alternatives round-up collects the leading open-source options with their licences and runtimes. Teams weighing Kortix directly against Perplexity Computer can read the Kortix vs Perplexity Computer head-to-head, and the Kortix self-hosting guide covers running the stack on your own hardware.

Ready to own the stack? Try Kortix and run your first agent from a repository your company controls.