Personal assistants · AI agent
Open Duet: review, pricing, security and alternatives
Open Duet is an open-source AI agent published by Anil Matcha, in the personal assistants family. Open Duet provides AI coworkers with memory, routines and isolated computers, requiring your approval before acting. Its repository has 6,140 stars and its last commit is from October 24, 2026.
What Open Duet does
Open Duet belongs to the personal assistants family: general-purpose agents, often self-hosted and driven from a messaging app, that act for you on your files, accounts and services. On our grid it ranks #31 of the 46 projects of this family listed in the directory.
Who is Open Duet for?
It targets individuals and freelancers who want an assistant able to act for them day to day, often from a messaging app. Typical tasks people give it:
- sort e-mail and draft replies
- manage a calendar and reminders
- look up information and summarise it
- run small recurring tasks
It is a good candidate if your data must stay on your machines.
Access and human control
According to its documentation, Open Duet can:
- control the screen, keyboard and mouse
By default it asks for your confirmation before sensitive actions (command, send, delete). Keep that setting, at least at first: full-auto mode saves time but removes the last safeguard.
Open Duet pricing
The code is free, under the Apache-2.0 licence.
Getting started with Open Duet
- Install it: the project ships as a Python package (install with
piporuv). The exact command is in the repository README. - Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
- Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
- Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.
Security: risk level
A personal assistant often combines access to private data, reading outside content and sending messages: the combination that enables data leaks through prompt injection.
Points found for Open Duet:
- Supervised sensitive access: it can act on the system, but asks for confirmation by default.
Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.
Project activity and releases
Created on May 25, 2023, the Anil-matcha/open-duet repository has 6,140 stars, 762 forks and 1 open issues, with 291 commits in total. It received changes this month.
Over the last 52 weeks: 277 commits, an average of 5.3 per week.
The project publishes no numbered releases on GitHub: you install it from the main branch or a package manager.
Open Duet vs other personal assistants
GitHub stars of the best-rated open-source projects in the personal assistants family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.
Open Duet and other personal assistants at a glance
The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.
| Agent | Model | Score | Stars or entry price | Self-hostable | Human approval |
|---|---|---|---|---|---|
| Open Duet | open source | 59 | 6.1K ★ | yes | yes |
| OpenClaw | open source | 95 | 392.9K ★ | yes | – |
| Hermes Agent | open source | 90 | 256.7K ★ | yes | – |
| nanobot | open source | 87 | 49.3K ★ | yes | – |
| CowAgent | open source | 87 | 47.6K ★ | yes | – |
| QwenPaw | open source | 86 | 36K ★ | yes | – |
| ZeroClaw | open source | 85 | 33K ★ | yes | – |
| OpenHuman | open source | 82 | 42.3K ★ | yes | – |
How we rated it
Score: 59/100, computed only from public, verifiable data, with no subjective testing or partnership:
- Adoption 21/40: 6,140 stars on a log scale (40 points from about 200,000).
- Activity 18/30: last commit less than a month ago, 0 releases in six months, 277 commits in a year.
- Framework 20/30: licence, default human approval, self-hosting, model choice and documentation site.
The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.
Verdict
Open Duet is a project to watch: compare it with the alternatives before adopting it.
Strengths
- Very active development
- Can run on your side: data under control
- Asks before sensitive actions
- Permissive licence (Apache-2.0)
Avoid if…
- You cannot isolate it (container, virtual machine)
Alternatives
Learn more
Frequently asked questions
Is Open Duet free?
The software is free (Apache-2.0 licence). You still pay for the model calls, unless you use a local model.
Is Open Duet safe?
Our risk level: mid. Points found: supervised sensitive access. Give it minimum rights and approve irreversible actions.
Which models does Open Duet use?
Its documentation does not specify the supported models.
Can Open Duet be installed on your own server?
Yes, from the Anil-matcha/open-duet repository. Data then stays with you, but security and updates are your job.
What are the alternatives to Open Duet?
In the same family: OpenClaw, Hermes Agent, nanobot, and CowAgent.
Open Duet or OpenClaw: what is the difference?
Both belong to the personal assistants family. Open Duet has 6.1K stars against 392.9K for OpenClaw. The right choice mostly depends on the access you are willing to give it.
Related articles
- Open source or proprietary AI agent: how to decideOctober 25, 2026
- AI agent vs. chatbot: what's the difference?October 24, 2026
- Autonomous AI agents: how much should you let them do?October 12, 2026
- AI agent memory: how agents remember (and forget)October 11, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score