unbrowse
Unbrowse for Claude Code: the node's tools and the agent skills
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/unbrowse-ai-unbrowse)HTML
<a href="/listings/unbrowse-ai-unbrowse"><img src="/api/listings/unbrowse-ai-unbrowse/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
You need Node 20.3 or newer, on macOS, Linux or Windows.
npm i -g unbrowse unbrowse connect
`unbrowse connect` starts Unbrowse on your machine and adds it to Claude Code. Restart Claude Code and ask it to get something from a website. `unbrowse app` opens the window; `unbrowse start` runs the node without it.
Version 13 is on npm under the tag `next` for now: a plain `npm i -g unbrowse` still installs 12.5.0, the hosted client that has closed. For Codex, Cursor, VS Code, Gemini, Zed and other agents, see [Install the Unbrowse MCP](docs/install-mcp.md).
Prefer not to use npm?
- **macOS:** download the disk image from [Releases](https://github.com/unbrowse-ai/unbrowse/releases), open it and drag Unbrowse onto Applications. It is signed ad hoc, not notarized, so open it the first time by hand: right-click it and choose Open, or on macOS 15 and later, after the warning, System Settings > Privacy & Security > Open Anyway. - **Linux or Windows:** download `unbrowse-<version>-linux-<arch>.tar.gz` or `unbrowse-<version>-windows-x64.zip`. It holds the node, `unb`, the browser and the window in one folder, with a README that says how to start them. Check the download against the release's `SHA256SUMS`.
A release keeps itself up to date and runs on Arc testnet. npm fetches the programs for the machine it installs on: macOS (Apple silicon and Intel), Linux (x64 and arm64, glibc 2.35 or later) and Windows (x64). That brings the app, the node, `unb`, the agent skill and the client, and no browser: the node fetches its browser the first time a goal needs one (or `unbrowse browser install` fetches it now; [docs/guides/the-browser.md](docs/guides/the-browser.md)). Foundry's Anvil (`foundryup`) is needed only for test mode, the local devnet: the default of a build from source, or a node whose `chain` setting is `devnet`.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 16 lines
- {
- "name": "unbrowse",
- "description": "Unbrowse for Claude Code: the node's tools and the agent skills",
- "owner": {
- "name": "Unbrowse",
- "url": "https://unbrowse.ai"
- },
- "plugins": [
- {
- "name": "unbrowse",
- "source": "./integrations/claude-code",
- "description": "Use websites through the Unbrowse node on this machine: say what you want and get the site's own JSON back",
- "category": "development"
- }
- ]
- }
README.md · README · 335 lines
- # Unbrowse
- **Your agent uses websites without a browser.**
- Unbrowse runs on your own computer. The first time your agent needs something from a site, Unbrowse opens the page
- once, finds the request the site's own app makes, and keeps it. After that, your agent makes that request directly:
- plain HTTP, no browser, no page to read.
- On a site it has learned, Unbrowse is up to 100× faster than driving a browser. Across 94 sites, an uncached answer took
- 950 ms on average, against 3,404 ms for a browser agent ([research paper](https://arxiv.org/abs/2604.00694)). A cached
- answer comes back in about 67 ms.
- [Releases](https://github.com/unbrowse-ai/unbrowse/releases) ·
- [Install the MCP](docs/install-mcp.md) ·
- [Moving from the hosted version](docs/upgrade.md) ·
- [Architecture (AGENTS.md)](AGENTS.md) ·
- [Contributing](CONTRIBUTING.md) ·
- [Security](SECURITY.md)
- ## Install
- You need Node 20.3 or newer, on macOS, Linux or Windows.
- ```bash
- npm i -g unbrowse
- unbrowse connect
- ```
- `unbrowse connect` starts Unbrowse on your machine and adds it to Claude Code. Restart Claude Code and ask it to get
- something from a website. `unbrowse app` opens the window; `unbrowse start` runs the node without it.
- Version 13 is on npm under the tag `next` for now: a plain `npm i -g unbrowse` still installs 12.5.0, the hosted client
- that has closed. For Codex, Cursor, VS Code, Gemini, Zed and other agents, see [Install the Unbrowse MCP](docs/install-mcp.md).
- Prefer not to use npm?
- - **macOS:** download the disk image from [Releases](https://github.com/unbrowse-ai/unbrowse/releases), open it and drag
- Unbrowse onto Applications. It is signed ad hoc, not notarized, so open it the first time by hand: right-click it and
- choose Open, or on macOS 15 and later, after the warning, System Settings > Privacy & Security > Open Anyway.
- - **Linux or Windows:** download `unbrowse-<version>-linux-<arch>.tar.gz` or `unbrowse-<version>-windows-x64.zip`. It holds
- the node, `unb`, the browser and the window in one folder, with a README that says how to start them. Check the
- download against the release's `SHA256SUMS`.
- A release keeps itself up to date and runs on Arc testnet. npm fetches the programs for the machine it installs on:
- macOS (Apple silicon and Intel), Linux (x64 and arm64, glibc 2.35 or later) and Windows (x64). That brings the app, the
- node, `unb`, the agent skill and the client, and no browser: the node fetches its browser the first time a goal needs
- one (or `unbrowse browser install` fetches it now; [docs/guides/the-browser.md](docs/guides/the-browser.md)).
- Foundry's Anvil (`foundryup`) is needed only for test mode, the local devnet: the default of a build from source, or a
- node whose `chain` setting is `devnet`.
- ## Used the hosted version?
- Unbrowse used to run on our servers. That service closed in November 2026. An old agent setup that still points at it hears the two
- commands above in reply. If you set Unbrowse up with version 12 or earlier, run them. `unbrowse connect` finds your old
- setup, asks before changing it, keeps a copy, and can undo the move. Logins you saved on the hosted service did not move
- to your machine; [Moving to the new Unbrowse](docs/upgrade.md) says how to add the ones you need.
- ## How it works
- A **route** is one learned call: the request, every value it needs traced to where it comes from, and the caller's
- values as inputs. An agent says what it wants; the node calls the route that does it, or learns one and calls that.
- ```
- agent ── HTTP / MCP ──▶ unbrowse-node ──▶ the site's own API (a route, plain HTTP)
- │
- └── links unbrowse-browser/core ──▶ Chrome (once, to learn the route)
- ```
- Your sign-ins stay on your computer, in your system's own keystore.
- ## Choose a starting point
- | Goal | Start here |
- |---|---|
- | Use it | [Install](#install) |
- | Connect an agent (Claude Code, Cursor, …) | [Install the Unbrowse MCP](docs/install-mcp.md), or [Connect an agent](#connect-an-agent) |
- | Move from the hosted version | [docs/upgrade.md](docs/upgrade.md) |
- | Build from this repo | [Run from source](#run-from-source) |
- | Change the code | The [repository map](#whats-here), then the `README.md` in the directory you are touching |
- | Understand the idea | [docs/concepts/](docs/concepts/why-unbrowse.md): the concepts in plain words, from the papers, each ending with what the code does today and where it differs |
- | Read the design | [papers/](papers/README.md): the whitepaper, the economy, selection and the protocol specification, which is normative for the design |
- | Understand how it works | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md): the whole system with diagrams — pipeline, keys, peer network, payments; [AGENTS.md](AGENTS.md) for the pattern and rules |
- | Know what it costs, and where fees go | [docs/MONEY.md](docs/MONEY.md): what each action costs, measured; the fee split; paying your own way |
- | Start as a new owner, from install to first earnings | [docs/ONBOARDING.md](docs/ONBOARDING.md); every command in [docs/CLI.md](docs/CLI.md); all the docs, and the order to read them, in [docs/README.md](docs/README.md) |
- | Fix something that broke | [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md): symptom, cause, fix |
- | Contribute | [CONTRIBUTING.md](CONTRIBUTING.md); report vulnerabilities privately per [SECURITY.md](SECURITY.md) |
- ## Run from source
- The node runs on macOS, Linux and Windows. Its root key lives in the system's keystore (the Keychain, Windows'
- Credential Manager, or the Secret Service on Linux; on a Linux machine with no desktop session,
- `~/.unbrowse/root.key`, readable by its user alone). The node browses in Chrome or any other Chromium browser on the
- machine, and downloads Chrome for Testing the first time a goal needs a browser and there's none.
- Toolchain, the versions CI pins ([.github/workflows/ci.yml](.github/workflows/ci.yml)):
- | Tool | Version | For |
- |---|---|---|
- | Rust | stable | the node, `unb`, the browser |
- | [Foundry](https://getfoundry.sh) (`anvil`) | latest (`foundryup`) | test mode, the node's local payment chain |
- | Zig | 0.17.0 | the window |
- | Bun | 1.4.3 | the browser dashboard's tests |
- | Node | 22 | the TypeScript SDK and skill |
- ```bash
- # The browser the node drives (its own build and tests: unbrowse-browser/)
- cargo build --release --manifest-path unbrowse-browser/cli/Cargo.toml
- # The node. Its TLS stack is BoringSSL patched to match Chrome's handshake, vendored once by a script
- cd unbrowse-node
- sh scripts/apply-tls-patch.sh
- cargo run --bin unbrowse-node
- # The window, in another terminal (it starts the node itself if nothing answers)
- cd unbrowse-node/window && zig build run
- ```
- The node listens on `127.0.0.1:7788` and keeps everything under `~/.unbrowse` (`UNBROWSE_HOME` moves it).
- A release install puts **one command, `unbrowse`**, on `PATH`: it runs the node and forwards the node's own commands to
- it (`unbrowse vault …`, `unbrowse agent …`, `unbrowse passkey …`, `unbrowse session …`, `unbrowse telemetry …`), and an
- agent's `do`/`browse`/`search`/`connect` to `unb`.
- ```bash
- unbrowse agent new my-agent # an agent key; prints its setup once
- unbrowse vault import export.csv # a browser's or password manager's login export
- unbrowse session import github.com # a site's signed-in session (add --from cookies.txt for an exported file)
- unbrowse passkey import keys.json # passkeys a password manager exported
- ```
- From this source build there is no `unbrowse` wrapper (it ships in the `unbrowse` npm package): run the binaries the build
- left at `target/release/` — `unbrowse-node <command>` and `unb <command>`. Each directory has its own build and tests;
- [unbrowse-node/README.md](unbrowse-node/README.md) is the one to read next, and lists every node command.
- ## Connect an agent
- On a fresh machine, `npm i -g unbrowse && unbrowse connect` is enough for Claude Code: `connect` starts the node if
- it isn't running and registers the agent the node made on its first run. For another agent, make a key (in the
- window: Money, Add agent; or `unbrowse agent new <name>`), then point an MCP client at the node with the key's
- token:
- ```bash
- # Claude Code
- claude mcp add --scope user unbrowse --env UNBROWSE_NODE=http://127.0.0.1:7788 -- unb mcp --agent first # unb mcp signs each request with the token, which never goes over the wire
- # Any other MCP client, or the CLI
- export UNBROWSE_NODE=http://127.0.0.1:7788
- export UNBROWSE_AGENT_TOKEN="$(unbrowse agent token)"
- unbrowse connect # starts the node if needed, registers your first agent with Claude Code
- ```
- Claude Code, Codex, OpenClaw, Hermes Agent and ElizaOS also take the node as a plugin, with the skill:
- [integrations/](integrations/README.md).
- The node serves MCP at `POST /mcp` and the same actions over HTTP on `127.0.0.1:7788`
- ([unbrowse-node/README.md](unbrowse-node/README.md#the-agent-api)). A global `npm install` also puts the agent skill in
- `~/.claude/skills/unbrowse`.
- Some routes belong to other people's nodes and carry a fee, paid from the node's balance in dollars; what each action costs, and where the money goes, is in [docs/MONEY.md](docs/MONEY.md). `unbrowse money` prints the balance, each agent's daily limit and earnings.
- ## What's here
- A polyglot repository, not a single-language monorepo. Each directory is its own build with its own `README.md` —
- **read the nearest one before changing the code there.**
- | Directory | What it is | Language | Guide |
- |---|---|---|---|
- | [`unbrowse-node/`](unbrowse-node) | The node: the agent API (HTTP and MCP on 127.0.0.1), the route learner, the vault, payments, and the window | Rust, Zig, TypeScript | [README](unbrowse-node/README.md) |
- | [`unbrowse-browser/`](unbrowse-browser) | The browser the node learns from: a fork of agent-browser that records every request and typed value | Rust | [AGENTS](unbrowse-browser/AGENTS.md) |
- | [`unbrowse-sdk/`](unbrowse-sdk) | `unbrowse` for npm and PyPI: the node, its browser, the agent skill and the client in one package | TypeScript, Python | [README](unbrowse-sdk/README.md) |
- | `unbrowse-settlement/` (private repository) | The settlement contracts that pay contributors, sites and the network for each call | Solidity | private |
- | [`unbrowse-telemetry/`](unbrowse-telemetry) | The worker that takes nodes' anonymous usage events ([what is sent](#usage-telemetry)) | JavaScript | [README](unbrowse-telemetry/README.md) |
- | [`skills/`](skills) | Agent skills that teach an agent to use the node | Markdown | [README](skills/README.md) |
- | [`integrations/`](integrations) | The node as a plugin for Claude Code, Codex, OpenClaw, Hermes Agent and ElizaOS | TypeScript, Python | [README](integrations/README.md) |
- | [`papers/`](papers) | The design: the whitepaper, the economy, selection and the protocol specification, as Markdown and PDF | Markdown, PDF | [README](papers/README.md) |
- | [`docs/`](docs) | The docs: concepts, getting started, guides, reference, and the system docs | Markdown | [README](docs/README.md) |
- The architecture, with diagrams of the pipeline, keys, peer network and payments, is in
- [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md); what each action costs and where the money goes is in
- [docs/MONEY.md](docs/MONEY.md). The two repository-wide guides sit at the root: [AGENTS.md](AGENTS.md) explains the pipeline and the rules learned
- building it; [CLAUDE.md](CLAUDE.md) adds the one rule every change follows — fixes are general, never written for one
- site. CI runs every directory's tests ([.github/workflows/ci.yml](.github/workflows/ci.yml)); work lands on `staging`,
- is cut into `release/X.Y` branches and ships to `main` as tagged semantic versions
- ([CONTRIBUTING.md](CONTRIBUTING.md#branches-and-releases)).
- ## Usage telemetry
- The node tells Unbrowse how it is used, so we can show the network is used and fix what breaks. It is on by default
- in a release while the node is on the network (a node you keep off the network sends nothing; a build from source sends nothing
- unless `UNBROWSE_TELEMETRY=1`), it says so when it starts, and one command turns it off:
- ```bash
- unbrowse-node telemetry off # kept in ~/.unbrowse/telemetry.json; `unbrowse-node telemetry` shows the state
- UNBROWSE_TELEMETRY=0 # in the environment: off, whatever the file says
- ```
- **What is sent**, in batches to `telemetry.unbrowse.ai` ([`unbrowse-telemetry/`](unbrowse-telemetry)), and nothing else:
- | Field | What it is |
- |---|---|
- | `event` | `node_start` (the node started), `tool_call` (an agent called a tool), `route_failed` (a route the node keeps ran and failed) or `fetch_failed` (a paid fetch of another node's route failed) |
- | `version`, `os` | the node's version, and `macos`, `linux` or `windows` |
- | `install_id` | a random id drawn once for this install, tied to nothing else: not your identity, account, machine or name |
- | `tool` | which agent tool or API route: `unbrowse_do`, `unbrowse_call`, `/v1/routes/{id}/call`, … (never which route) |
- | `outcome`, `error_class` | `ok`, `failed` (the site's call failed) or `error` (the node refused it), and a coarse class: `not_found`, `forbidden`, `site`, …; for a failed route or fetch, the kind of failure from a fixed list (`http`, `door`, `shape_mismatch`, `no_body`, …) |
- | `duration_ms` | how long the call took |
- **Never sent:** URLs, sites or host names, page content, requests or answers, route ids, goals or inputs, cookies,
- passwords, passkeys, vault entries, keys, wallet addresses, user or machine names, or your IP address. Every field and
- value is checked against a fixed list before it is queued, and again by the worker, which refuses a batch with any
- other field or anything that looks like an address. The worker keeps each event and the hour it arrived; it never
- reads or keeps the caller's IP address.
- **Your linked wallet.** Unbrowse uses no API keys, and needs no account: the node has its own wallet. If you link a
- wallet of yours to the node (with email or Google, or your own), the node also sends the site three events while telemetry is on: `node_started`, `owner_linked` and
- `owner_unlinked`. Each is signed by the node's key and names the node's address and your account's address, so a
- count belongs to a node that really sent it and the account that owns it (`unbrowse-node/app/src/link.rs`,
- `link::tell`). They never name a site, route or input. A node you haven't linked sends none, and `telemetry off`
- stops them too. The usage counts above stay as they are: no account, only the random install id.
- Telemetry never slows the node: an event is queued without waiting, a full queue drops it, and a batch the worker
- doesn't take within a few seconds is dropped, never retried. With the worker down, everything works the same.
- ## Bug reports
- Agents notice what the node can't: a result for another repository than the one asked for, a block page answered as
- `ok: true`, a call that only worked with a workaround. So an agent reports it, with `unbrowse_report` (MCP),
- `POST /v1/report`, `unb report` or `report()` in the SDKs, and carries on. The node scrubs the report, adds what it
- knows, and sends it to the relay at `telemetry.unbrowse.ai` ([`unbrowse-telemetry/`](unbrowse-telemetry)), which files
- it as a **public issue** on [unbrowse-ai/unbrowse](https://github.com/unbrowse-ai/unbrowse/issues) labelled
- `agent-report`. Reports of the same problem share one issue, which counts them: the same kind, tool, route shape,
- page host and last failed call, as the node says them (an agent's own words never split or join problems). A problem
- whose issue was closed opens a new one. The node also reports a few problems it notices itself: a crash, an internal error, a route that still failed
- after its page was walked again.
- Reports are off until you turn them on (`unbrowse-node reports on`), since each becomes a public issue. Once on, they
- follow telemetry: off in a build from source unless `UNBROWSE_REPORTS=1`, and off whenever telemetry is.
- **An agent's report waits for you.** An agent writes its own words into a report, and a page it read can steer what it
- writes, so nothing an agent reports leaves until you have read it, scrubbed, in your window and sent it
- (`reports_waiting`, then `report_send`, which the node asks you about in its own dialog with the report's text shown,
- or `report_discard`). The agent is told its report waits (`waiting_for_owner`). Reports the node makes itself carry no
- words from a site, and are sent as before.
- ```bash
- unbrowse-node reports on # opt in; `reports off` turns them off again
- unbrowse-node reports off # kept in ~/.unbrowse/reports.json, and a running node stops at once; `unbrowse-node reports` shows the state
- UNBROWSE_REPORTS=0 # in the environment: off, whatever the file says
- ```
- **What a report holds**, and nothing else (the relay refuses any other field):
- | Field | What it is |
- |---|---|
- | `kind` | `wrong_data`, `false_success`, `failed`, `slow`, `confusing` or `other` |
- | `summary`, `expected`, `got`, `goal`, `error` | the agent's words, scrubbed and cut to 140 to 1,500 characters |
- | `url` | the page's scheme, site and path template (below); never its query or fragment |
- | `tool` | which agent tool gave the wrong answer |
- | `route` | the route's shape: method, site, path template, input names, whether it writes, its step count |
- | `last_error` | the agent's last failed call in the past ten minutes: its tool, class, and the status or kind of error the node saw (`Failed: step 2 of 2 answered 403`); never what the site said |
- | `version`, `os`, `source` | the node's version and OS, and whether an agent or the node filed it |
- | `install_id` | for the relay's limit of 20 reports an install a day; never published, kept only hashed with the day |
- **Scrubbed before it leaves**, then again by the relay, after decoding what is encoded (`%40`, `\/`, `@`) and
- dropping hidden characters (zero-width, bidi): query strings and fragments, logins in URLs, emails, IP addresses,
- numbers of nine digits or more however they are spaced (cards, phone numbers, national ids; four or more in a path),
- hex, tokens and keys, the value of any field whose name says it's a secret (`password=`, `"api_key": …`, `code:`),
- vault references, your home folder, user name, machine name and vault account names. A host keeps only the site's
- own name: the names in front of it are `*` (`*.atlassian.net`), a machine on your network is `[internal]`, an
- address `[ip]`. A route's or page's path keeps only plain lowercase words, templates and versions; anything else (a
- handle, an id, a file name) is `{id}`. A route's input values and defaults, cookies, headers and bodies are never
- read into a report, and nor is anything a site said: the node's own reports and `last_error` carry only the error's
- kind and status. A report says which site the agent was using, never whose account.
- The reply tells the agent what happened (`sent` with the issue's URL, `queued` while the relay can't be reached,
- `already_sent` for a problem this node reported today, or `off`), what was scrubbed, and the report exactly as filed.
- A queued report is sent within the next quarter hour, for up to a week.
- ## When a page needs you
- The node gets past a site's defenses itself wherever it can, and says so plainly: a challenge, a bot check or a
- clearance cookie is a step to satisfy, not a stop sign. A check an agent can see — an image grid, a slider, a queued
- page — is met with `unbrowse_challenge`: the node shows the agent a picture of the page and takes its clicks one step
- at a time, so the agent's own model reads the check and the page's own answer says whether it passed. Some pages only a
- person can get past: a sign-in your vault has no login for, a two-step code, a check that renders only for a human.
- An agent asks with `unbrowse_browse ["ask_owner", "sign in to LinkedIn"]`, and the app's **Browser** screen shows you
- that page live: click and type on the picture as if it were the page, then press **Done, give it back**. You can open Browser any time without
- being asked. Agents never see what you type, and the session stays in the site's profile, so the agent carries on signed
- in ([unbrowse-node/README.md](unbrowse-node/README.md#the-owners-hands-on-a-page)).
- A wall the node cannot clear is reported as `blocked`, never as data. Bypassing anti-bot is part of the product, done
- openly; faking a success the site did not give is not.
- ## Website passkeys (on by default)
- A headless browser has no authenticator, so a site that asks for a passkey ("verify it's you") stops an agent until a
- person acts. The node keeps a site's passkey in its vault and answers that prompt itself. **This is on by default.**
- When **you** sign in on a page by hand (you take it over when the agent asks, and give it back done) and the site then
- offers to make a passkey (its "add a passkey?" prompt after sign-in, or one it makes on its own), the node accepts it
- and keeps it, with no further step from you. A vault login an *agent* fills arms nothing: a passkey signs in as you
- with no password and no second factor, so one an agent could make would be a credential stronger than its own key —
- and every key on the node as strong as the weakest of them. A site
- that never offers one gets none: the node doesn't go into a site's settings to make one. The passkey is sealed in the
- vault under a key derived from the root key, and it never goes to the network, a peer or a log. The node says so the
- first time it starts, and `unbrowse-node passkey list` shows every passkey it holds and whether it was enrolled
- automatically (`auto`) or by you (`manual`). A passkey a password manager exported (Bitwarden, CXF, KeePassXC) can
- be imported too (`unbrowse passkey import <file>`); iCloud Keychain, Google Password Manager, Windows Hello and security
- keys don't let one out.
- **The risk, plainly: any site the node signs in to may get a passkey registered on your account, and whoever
- controls your node can then sign in as you there.** That includes any agent holding one of its keys, since agents
- drive the node's browser and the node answers the passkey prompt for them, with no prompt to you and no second
- factor: the passkey is the second factor. A Google (Gmail) account is the highest-value target there is: it resets
- the passwords of most of your other accounts, so a node holding its passkey can reach them too. Keep the node on a
- machine you alone control, and check the activity log (every enrolment and every sign-in with a stored passkey is a
- line there).
- **To opt out:** `unbrowse-node passkey off` (or `UNBROWSE_PASSKEYS=0`) for every site, or `unbrowse-node passkey never
- <site>` for one (`passkey allow <site>` undoes it); `passkey never google.com` is the one to consider first. To delete
- a passkey: `unbrowse-node passkey remove <id>`, then on the site's account page (security, passkeys) delete it there
- too, or the site keeps accepting it; on Google that is `https://myaccount.google.com/signinoptions/passkeys`. More:
- [unbrowse-node/README.md](unbrowse-node/README.md#website-passkeys-on-by-default).
- ## Contributing and security
- See [CONTRIBUTING.md](CONTRIBUTING.md). Report vulnerabilities privately, as [SECURITY.md](SECURITY.md) describes,
- never in a public issue.
- ## Licence
- [Apache-2.0](LICENSE). Copies and forks keep the [NOTICE](NOTICE) file. The licence covers the code, not the name:
- a fork ships under its own name ([TRADEMARKS.md](TRADEMARKS.md)).
- Third-party code keeps its own licence: agent-browser (Apache-2.0) in `unbrowse-browser/`; forge-std (MIT or
- Apache-2.0) and OpenZeppelin (MIT) in `unbrowse-settlement/lib/`.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.