@mercuryo-ai/agentbrowse-cli 0.1.6 → 0.1.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +76 -38
  2. package/package.json +12 -4
package/README.md CHANGED
@@ -1,48 +1,86 @@
1
1
  # @mercuryo-ai/agentbrowse-cli
2
2
 
3
- Browser-only CLI wrapper for `@mercuryo-ai/agentbrowse` on the shared
4
- `~/.magicpay` home.
3
+ Browser automation CLI for AI agents.
5
4
 
6
- `agentbrowse` is the browser operator surface for:
5
+ AgentBrowse CLI is the operator-facing way to work with a real web page.
7
6
 
8
- - bootstrapping shared MagicPay backend config for goal-based browser reasoning;
9
- - launching or attaching to a browser over CDP;
10
- - reading browser/page/runtime diagnostics;
11
- - navigating, observing, acting, extracting, and taking screenshots;
12
- - closing the shared browser session without owning payment/session/secrets
13
- flows.
7
+ Use it when you need to:
8
+
9
+ - launch a browser or attach to an existing CDP session;
10
+ - inspect the current page and act on visible controls;
11
+ - navigate directly to a known URL;
12
+ - extract structured data from the page;
13
+ - capture screenshots or recover a stuck browser session.
14
+
15
+ AgentBrowse works well as a standalone browser tool. It can also sit next to
16
+ MagicPay when a broader flow later reaches a protected login, identity, or
17
+ payment step.
18
+
19
+ Open source:
20
+
21
+ - library and docs: `https://github.com/MercuryoAI/agentbrowse`
14
22
 
15
23
  ## Install
16
24
 
17
25
  ```bash
18
- npm i -g @mercuryo-ai/agentbrowse-cli
19
- agentbrowse init <magicpay-api-key>
20
- agentbrowse --help
26
+ npm i -g @mercuryo-ai/agentbrowse-cli@latest
21
27
  ```
22
28
 
23
- `observe` and `extract` use the shared MagicPay assistive backend. Configure it
24
- once with `agentbrowse init <apiKey>` or provide `MAGICPAY_API_KEY` and
25
- `MAGICPAY_API_URL` at runtime.
26
-
27
- ## Current surface
28
-
29
- - `init`
30
- - `launch`
31
- - `attach`
32
- - `browser-status`
33
- - `navigate`
34
- - `observe`
35
- - `act`
36
- - `extract`
37
- - `screenshot`
38
- - `close`
39
-
40
- ## Architecture boundary
41
-
42
- - `agentbrowse` is the operator CLI for browser-only workflows.
43
- - `@mercuryo-ai/agentbrowse` owns browser primitives and the reusable runtime.
44
- - `@mercuryo-ai/magicpay-home` owns the shared `~/.magicpay` local-home contract.
45
- - `@mercuryo-ai/magicpay-sdk` provides the shared MagicPay gateway contract used by
46
- browser goal-observe/extract assistive flows.
47
- - `@mercuryo-ai/agentbrowse-cli` owns only the branded browser CLI UX and shared
48
- home wiring, including shared gateway bootstrap for assistive browser goals.
29
+ ## Core Loop
30
+
31
+ 1. `agentbrowse launch [url]` or `agentbrowse attach <cdp-url>`
32
+ 2. `agentbrowse observe`
33
+ 3. `agentbrowse act <targetRef> <action> [value]`
34
+ 4. repeat `observe` after meaningful page changes
35
+ 5. `agentbrowse navigate <url>` if the destination is already known
36
+ 6. `agentbrowse extract '<schema-json>' [scopeRef]` when you need structured
37
+ output
38
+ 7. `agentbrowse screenshot` or `agentbrowse browser-status` for evidence and
39
+ debugging
40
+ 8. `agentbrowse close` when you are done
41
+
42
+ ## When You Need API Setup
43
+
44
+ Simple browser tasks work without API setup.
45
+
46
+ Goal-based `observe` and `extract` use the shared agent config. Set it up once
47
+ with:
48
+
49
+ ```bash
50
+ agentbrowse init <api-key>
51
+ ```
52
+
53
+ You can also provide `MAGICPAY_API_KEY` in the environment. Use
54
+ `agentbrowse doctor` only if semantic commands still fail after `init` and you
55
+ want to inspect `~/.magicpay/config.json`.
56
+
57
+ ## First Task
58
+
59
+ Start with a plain browser task:
60
+
61
+ ```bash
62
+ agentbrowse launch "https://example.com"
63
+ agentbrowse observe
64
+ ```
65
+
66
+ If you want a focused or structured result:
67
+
68
+ ```bash
69
+ agentbrowse init <api-key>
70
+ agentbrowse observe "find the next visible action to continue"
71
+ agentbrowse extract '{"summary":"string"}'
72
+ ```
73
+
74
+ ## Command Groups
75
+
76
+ - Session setup: `launch`, `attach`, `navigate`
77
+ - Page work: `observe`, `act`, `extract`
78
+ - Diagnostics and cleanup: `screenshot`, `browser-status`, `close`
79
+ - Semantic runtime setup: `init`, `doctor`, `--version`
80
+
81
+ ## Companion Tools
82
+
83
+ - If the page is already at a protected login, identity, or payment form:
84
+ use `@mercuryo-ai/magicpay-cli`
85
+ - If one CLI should cover both browser work and protected fills:
86
+ use `@mercuryo-ai/magicpay-agent-cli`
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@mercuryo-ai/agentbrowse-cli",
3
- "version": "0.1.6",
4
- "description": "AgentBrowse CLI — browser-only operator shell on the shared MagicPay home",
3
+ "version": "0.1.8",
4
+ "description": "Browser automation CLI for AI agents",
5
5
  "type": "module",
6
6
  "license": "MIT",
7
7
  "bin": {
@@ -23,15 +23,23 @@
23
23
  "publishConfig": {
24
24
  "access": "public"
25
25
  },
26
+ "repository": {
27
+ "type": "git",
28
+ "url": "git+https://github.com/MercuryoAI/skills.git"
29
+ },
30
+ "homepage": "https://agents.mercuryo.io/docs/agents",
31
+ "bugs": {
32
+ "url": "https://github.com/MercuryoAI/skills/issues"
33
+ },
26
34
  "engines": {
27
35
  "node": ">=18.0.0"
28
36
  },
29
37
  "dependencies": {
30
38
  "@browserbasehq/stagehand": "^3.0.0",
31
39
  "dotenv": "^16.4.0",
32
- "@mercuryo-ai/agentbrowse": "0.2.52",
40
+ "@mercuryo-ai/agentbrowse": "0.2.53",
33
41
  "@mercuryo-ai/magicpay-home": "0.1.6",
34
- "@mercuryo-ai/magicpay-sdk": "0.1.0-test.5"
42
+ "@mercuryo-ai/magicpay-sdk": "0.1.0-test.6"
35
43
  },
36
44
  "devDependencies": {
37
45
  "@types/node": "^22.0.0",