magenta-canon 0.1.7 → 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 +18 -13
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -49,35 +49,40 @@ but "verify the receipt yourself."
49
49
 
50
50
  ## See it run (30-second demo)
51
51
 
52
- <!-- Pre-wired embed: commit the recording at docs/assets/magenta-canon-demo.gif
53
- and it renders here automatically. Capture recipe: docs/DEMO_RECORDING.md. -->
54
- ![Terminal demo showing Magenta Canon allowing one AI-agent tool call, blocking another, verifying the evidence bundle, and detecting tampering.](docs/assets/magenta-canon-demo.gif)
52
+ The fastest way to see it is to run the one-command proof loop yourself:
55
53
 
56
- > **Demo asset placeholder — recording in progress.** Until
57
- > `docs/assets/magenta-canon-demo.gif` is committed, the image above will not
58
- > render. Caption once live: *One command. One allowed call. One blocked call.
59
- > Independent verification. Tamper detection.*
54
+ ```bash
55
+ npx magenta-canon@next demo
56
+ ```
57
+
58
+ It runs the whole loop — an allowed call, a blocked call, a verified receipt,
59
+ and a tamper case that fails. A narrated walkthrough is in the
60
+ [explainer video](https://themagentacanon.com/magenta-canon.html#visual), and the
61
+ [**Understand it visually**](#understand-it-visually) section below shows each
62
+ step. *(A terminal-recording GIF is coming; see [`docs/DEMO_RECORDING.md`](docs/DEMO_RECORDING.md).)*
60
63
 
61
64
  ## Understand it visually
62
65
 
63
66
  The whole idea in three pictures — full set (get started, architecture, the
64
67
  downstream non-bypass proof, one-command demo) in the
65
- **[Visual Guide](docs/VISUAL_GUIDE.md)**.
68
+ **[Visual Guide](docs/VISUAL_GUIDE.md)** and on the
69
+ [live site](https://themagentacanon.com/magenta-canon.html#visual).
66
70
 
67
71
  **What it does** — authorize what's allowed, block what isn't, record proof of both:
68
72
 
69
- ![Magenta Canon sits between an AI agent and a tool server, authorizing, blocking, and recording every tool call.](docs/assets/onboarding/magenta-what-it-does.png)
73
+ ![Magenta Canon sits between an AI agent and a tool server, authorizing, blocking, and recording every tool call.](https://themagentacanon.com/assets/onboarding/magenta-what-it-does.png)
70
74
 
71
75
  **Allowed vs blocked** — an $89 refund is forwarded; a $250 refund stops at the gate:
72
76
 
73
- ![An $89 refund is authorized and forwarded; a $250 refund is blocked and never reaches the tool server.](docs/assets/onboarding/magenta-allowed-vs-blocked.png)
77
+ ![An $89 refund is authorized and forwarded; a $250 refund is blocked and never reaches the tool server.](https://themagentacanon.com/assets/onboarding/magenta-allowed-vs-blocked.png)
74
78
 
75
79
  **Verify the receipt** — check the proof yourself; one flipped byte fails verification:
76
80
 
77
- ![The magenta-verify checker returns VERIFIED for a valid receipt and VERIFICATION FAILED when a single byte is tampered.](docs/assets/onboarding/magenta-verify-the-receipt.png)
81
+ ![The magenta-verify checker returns VERIFIED for a valid receipt and VERIFICATION FAILED when a single byte is tampered.](https://themagentacanon.com/assets/onboarding/magenta-verify-the-receipt.png)
78
82
 
79
- A narrated walkthrough is in the [explainer video](docs/assets/onboarding/magenta-canon-explainer.mp4)
80
- (also embedded on the [landing page](public/magenta-canon.html)).
83
+ A narrated walkthrough is in the
84
+ [explainer video](https://themagentacanon.com/magenta-canon.html#visual) on the
85
+ live site.
81
86
 
82
87
  ## The proof (we don't rely on claims)
83
88
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "magenta-canon",
3
- "version": "0.1.7",
3
+ "version": "0.1.8",
4
4
  "type": "module",
5
5
  "license": "Apache-2.0",
6
6
  "description": "A verifiable MCP accountability gateway for AI-agent tool calls: allows authorized calls, blocks unauthorized calls, records both, and produces cryptographic evidence anyone can verify.",