Nanobrowser
Open-source Chrome extension for multi-agent AI web automation
- Category
- Coding & Development
- Pricing
- Free and open source (Apache 2.0); no subscription. You pay only for the LLM API usage you connect (OpenAI, Anthropic, Gemini, Groq, Cerebras, etc.), or $0 if you run local models via Ollama.
- Best for
- Nanobrowser suits developers, power users, and privacy-conscious teams who are comfortable managing their own LLM API keys and want a transparent, inspectable alternative to paying $200/month for OpenAI Operator or similar hosted browser agents.
- Official site
- nanobrowser.ai
- Last updated
- August 2026
Nanobrowser is an open-source browser extension that turns Chrome or Edge into an AI-driven automation agent. Rather than running as a hosted SaaS product, it installs directly into the browser and executes tasks locally, coordinating a small team of specialized LLM-powered agents to plan and carry out multi-step actions on real websites — clicking, navigating, extracting data, and reasoning about obstacles as they arise. The project is maintained on GitHub under the nanobrowser organization, licensed under Apache 2.0, and has attracted a sizeable open-source following (roughly 13,800+ GitHub stars and 1,400+ forks at time of research), with active Discord and GitHub Discussions communities driving its roadmap.
The tool's core differentiator is its explicit framing as a free, transparent alternative to OpenAI's Operator agent, which carries a $200/month price tag as part of ChatGPT Pro. Nanobrowser instead uses a bring-your-own-API-key model: users connect providers like OpenAI, Anthropic, Gemini, Groq, Cerebras, or local models via Ollama, and can assign different models to different agents (for example, a stronger model like Claude Sonnet for planning and a cheaper, faster model for navigation). Because everything runs in the user's own browser session with their own credentials, there's no cloud backend handling browsing data, which the project markets heavily as a privacy advantage. This combination of open-source transparency, LLM flexibility, and local-first execution is what distinguishes it from closed, subscription-based browser-agent products.
Nanobrowser suits developers, power users, and privacy-conscious teams who are comfortable managing their own LLM API keys and want a transparent, inspectable alternative to paying $200/month for OpenAI Operator or similar hosted browser agents. It's a strong fit for people who already use Chrome or Edge, want to experiment with different model combinations (including running fully local models via Ollama for zero API cost), and value having the automation logic open source and auditable. It's a weaker fit for non-technical users who want a zero-configuration, fully managed agent service, for anyone standardized on Firefox or Safari, or for teams that need enterprise support contracts and guaranteed uptime rather than a community-maintained open-source tool.
Key features
Multi-agent architecture
A Planner agent handles high-level reasoning and task breakdown while a Navigator agent executes concrete browser actions (clicking, typing, scrolling); the Planner can dynamically re-instruct the Navigator when it hits obstacles mid-task.
Per-agent model assignment
Users can assign a different LLM to the Planner versus the Navigator, letting them balance cost and capability (e.g., a stronger reasoning model for planning, a cheaper model for routine navigation steps).
Broad LLM provider support
Works with OpenAI, Anthropic, Gemini, Groq, Cerebras, Llama, Ollama for local models, and any custom OpenAI-compatible API endpoint.
Interactive side panel
A chat-style sidebar inside the browser shows real-time status updates as agents work, and lets users watch progress rather than treating automation as a black box.
Follow-up questions
After a task completes, users can ask contextual follow-up questions about the results without starting a new session from scratch.
Conversation history
Past agent interactions and task runs are saved and accessible, making it easier to revisit or reuse previous automations.
Local-first, privacy-focused execution
The extension runs entirely client-side in the browser; no browsing data or credentials are sent to a Nanobrowser-operated cloud service.
Manual and store installation paths
Available via the Chrome Web Store for stable releases, or as a manually loaded unpacked extension from GitHub release zips for access to the newest features ahead of store review.
Pricing breakdown
Free & Open Source
- Full multi-agent automation feature set with no paywalled tiers
- Bring your own LLM API key — actual cost is whatever the connected provider (OpenAI, Anthropic, Gemini, Groq, Cerebras, etc.) charges for usage
- Zero ongoing cost when paired with local models via Ollama
- Source code, issue tracker, and Discussions fully open on GitHub
- Optional voluntary support via GitHub Sponsors — not required to use the extension
Pros and cons
Pros
- No subscription cost at all: the software itself is free, so the only ongoing expense is whatever LLM API usage the user chooses to connect, which can be minimized or eliminated by running local models through Ollama.
- Splitting the Planner and Navigator roles across different models gives users fine-grained control over the cost/performance tradeoff, something closed agent products don't expose.
- Because everything executes inside the user's own Chrome or Edge session, there's no separate cloud agent seeing or storing browsing activity, which is a meaningful privacy improvement over hosted browser-agent services.
- The Apache 2.0 license and public GitHub repository mean the automation logic is fully auditable rather than a black box, which matters for users automating sensitive or authenticated web sessions.
- An active Discord and GitHub Discussions community shares prompt patterns, local-model benchmarks, and configuration tips, which shortens the learning curve for tuning agent behavior.
- Manual installation from GitHub releases gives early access to new capabilities ahead of the (sometimes delayed) Chrome Web Store review process.
Cons
- Browser support is narrow: Chrome and Edge are officially supported, while Firefox, Safari, and other Chromium-based browsers like Opera or Arc are explicitly unsupported, which rules it out for non-Chromium users.
- There's no managed backend or default model included, so a new user has to obtain and configure their own API keys before the extension does anything useful — it isn't a plug-and-play experience.
- Using cost-effective model configurations (e.g., cheaper Planner/Navigator pairings) is documented by the project itself as producing less stable output and requiring more iterations on complex tasks.
- Local models require noticeably more careful, explicit prompt engineering than cloud models, according to the project's own guidance, which adds friction for non-technical users trying to run it fully offline.
- As a community open-source project without a company behind it, support depends on volunteer maintainers and Discord/GitHub responsiveness rather than an SLA-backed help desk.
- Real-world reliability of any browser-automation agent depends heavily on how frequently target websites change their DOM/layout, and Nanobrowser's task success is bounded by the underlying LLM's web-navigation reasoning quality.
Alternatives to Nanobrowser
Frequently asked questions
Is Nanobrowser free to use?
Yes. Nanobrowser itself is free and open source under the Apache 2.0 license. The only cost is whatever usage fees the LLM provider you connect (OpenAI, Anthropic, Gemini, etc.) charges, or $0 if you run local models via Ollama.
How is Nanobrowser different from OpenAI Operator?
OpenAI Operator is a proprietary, hosted browser agent bundled with ChatGPT Pro at roughly $200/month. Nanobrowser is a free, open-source Chrome/Edge extension that runs locally and lets you plug in your own choice of LLM provider instead of relying on one vendor's model and paying a flat subscription.
Which LLM providers does Nanobrowser support?
It supports OpenAI, Anthropic, Google Gemini, Groq, Cerebras, Llama-based models, Ollama for local models, and any custom OpenAI-compatible API endpoint, with more providers planned according to the project.
Does Nanobrowser work on Firefox or Safari?
No. Nanobrowser officially supports only Chrome and Edge. Firefox, Safari, and other Chromium-based browsers such as Opera or Arc are not officially supported, though some functionality may work unofficially on other Chromium variants.
What is the multi-agent system in Nanobrowser?
Nanobrowser uses two specialized agents that collaborate: a Planner agent that handles high-level reasoning and task strategy, and a Navigator agent that carries out concrete browser actions like clicking and typing. Users can assign different LLMs to each agent to balance cost and performance.
Ready to try Nanobrowser?
Head to the official site to explore pricing and start a free trial where available.
Visit Nanobrowser →