All apps

First-party app · Amazon Bedrock

bedrock-models

Amazon Bedrock models, authenticated with your own AWS credential chain. No key is stored by PersonalClaw. Chat (Converse API), embedding (Titan/Cohere/Nova), image generation (Nova Canvas, Stability AI) and video generation (Nova Reel) where your region serves them, and speech-to-text. One instance per AWS profile/region.

Before you install

A first-party app of PersonalClaw v0.3.9

No scan on record before install

PersonalClaw publishes no scan of its own apps before you install one.

PersonalClaw runs its own scan of the actual code of every app it installs: this one is rescanned when you install, and that scan is what can stop an install.

Its row on Compare: install rescan

Compatibility
Works with PersonalClaw v0.3.9

What it gets

Permissions
  • network: true
Its own network permission
On. Its own network permission is a declaration, not a fence.

What it reaches

Hosts it names
Not declared in this release's manifest

Its own code has no host list at this release: any hosts it names are for the programs, servers and sources it starts or fetches, not everything it can reach. Its own network permission is a declaration, not a fence.

Secrets you would enter

Settings marked secret
Not declared in this release's manifest

What installing it gives and runs

The manifest's own declarations, under the names install consent shows them by and in its order. The Store adds, at install, which of them run as you.

Permissions it is granted
{
  "network": true
}
Python packages installed for it
[
  "boto3>=1.34"
]
Provider modules the gateway loads
[
  {
    "type": "model",
    "implementation": "provider:create_provider"
  }
]

Not declared in this release's manifest:

  • Scheduled jobs
  • Engine packages it can install
  • What it needs that PersonalClaw does not install
  • Programs on this machine it starts
  • npm packages installed for it
  • Places outside its folder it writes
  • Pages it adds to the dashboard
  • Components it adds to the dashboard
  • A server process of its own
  • The sandbox tier its server runs in
  • Command run after install
  • Command run after an update
  • Command run when it is switched on
  • Command run when it is switched off
  • Command run before it is removed
  • What it runs for personalclaw setup
  • What it runs for personalclaw doctor
  • Connector sources it parses
  • MCP servers it adds
  • Skills it installs

Where it comes from

Publisher
PersonalClaw
License
MIT
Pinned commit
169cbc4f8fc59cd42a65a6a3546235bc49ab3b22
Signer
Not declared in this release's manifest

From review to enable

  1. Held and scanned. An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.Its row on Compare: install rescan
  2. A dangerous verdict ends it. A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.Its row on Compare: dangerous verdict
  3. You review and consent. The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.Its row on Compare: consent
  4. Its setup runs, then you switch it on. Nothing it declares runs before your consent; an app already installed is offered as an update instead.

To install it and switch it on

  1. In PersonalClaw, open the Store.
  2. Find bedrock-models.
  3. Review what it gets and runs, and consent.
  4. Install it, then switch it on.

Evidence

bedrock-models/app.json at the pinned commit, as written, with the blob hash git lists for it: eae60e7a1f549199ff1752a7cae659af8e84af4f

Open it at the commit

{
  "name": "bedrock-models",
  "version": "0.1.23",
  "displayName": "Amazon Bedrock",
  "description": "Amazon Bedrock models, authenticated with your own AWS credential chain. No key is stored by PersonalClaw. Chat (Converse API), embedding (Titan/Cohere/Nova), image generation (Nova Canvas, Stability AI) and video generation (Nova Reel) where your region serves them, and speech-to-text. One instance per AWS profile/region.",
  "icon": "Cloud",
  "author": "PersonalClaw",
  "license": "MIT",
  "requiresCoreFeatures": [
    "adaptive-thinking",
    "closing-streams",
    "cut-off-answers",
    "guarded-clients",
    "model-efforts"
  ],
  "tags": [
    "model",
    "llm",
    "embedding",
    "image_gen",
    "video_gen",
    "stt",
    "bundled"
  ],
  "dependencies": {
    "pythonDependencies": [
      "boto3>=1.34"
    ]
  },
  "permissions": {
    "network": true
  },
  "provider": {
    "id": "models",
    "label": "Bedrock chat, embedding, image, video and speech models",
    "renamedFrom": ["model"],
    "type": "model",
    "providerType": "bedrock",
    "implementation": "provider:create_provider",
    "multiInstance": true,
    "capabilities": [
      "chat",
      "code_tools",
      "streaming",
      "vision",
      "embedding",
      "image_gen",
      "video_gen",
      "stt"
    ],
    "settingsSchema": {
      "type": "object",
      "properties": {
        "region": {
          "type": "string",
          "default": "us-east-1",
          "x-meta": {
            "label": "AWS Region",
            "help": "The AWS region every call this instance makes goes to: chat, embeddings, images, video, speech-to-text and the model list. Empty uses us-east-1, whatever your AWS profile or environment names. Credentials come from your AWS environment / profile \u2014 no key is stored here."
          }
        },
        "profile": {
          "type": "string",
          "default": "",
          "x-meta": {
            "label": "AWS Profile",
            "help": "Optional named profile from ~/.aws. Empty uses the default credential chain (env / SSO / instance role). Add a second instance with a different profile to use another AWS account.",
            "tags": [
              "advanced"
            ]
          }
        },
        "default_model": {
          "type": "string",
          "default": "",
          "x-meta": {
            "label": "Default Chat Model",
            "help": "A Bedrock chat model id (full versioned id). The model this instance answers with when nothing in Settings → Models names one. Leave it empty to choose its models in Settings → Models."
          }
        },
        "system_prompt": {
          "type": "string",
          "default": "",
          "x-meta": {
            "label": "System Prompt",
            "help": "Optional system prompt prepended to every chat turn.",
            "tags": [
              "advanced"
            ]
          }
        },
        "max_tokens": {
          "type": "integer",
          "default": 0,
          "minimum": 0,
          "x-meta": {
            "label": "Max Output Tokens",
            "help": "The most tokens Bedrock may generate in one turn, never more than the model allows. 0 sends the budget PersonalClaw sets for that call, else up to 64000 to a Claude model that thinks (its thinking counts against the cap) and 8192 to any other. With 0, a tool call cut at that limit is tried once more with twice the room; a set cap is never raised. A cap is always sent, because Bedrock's own default can be low enough to cut long answers and tool calls short.",
            "tags": [
              "advanced"
            ]
          }
        },
        "video_s3_bucket": {
          "type": "string",
          "default": "",
          "x-meta": {
            "label": "S3 Bucket",
            "help": "S3 bucket Bedrock's media features stage files in: Nova Reel writes each generated video there, and speech-to-text uploads each recording there for Amazon Transcribe, deleting it afterwards. Required for video generation and speech-to-text; nothing else uses it. Falls back to the BEDROCK_VIDEO_S3_BUCKET env var.",
            "tags": [
              "advanced"
            ]
          }
        }
      },
      "required": [
        "region"
      ]
    }
  }
}
Scan verdict
No scan on record before install
Scan time
No scan is published before install
Blocking findings
No scan is published before install
Scanner version
No scan is published before install

PersonalClaw publishes no scan of its own apps before you install one.

  • Every app is scanned again when you install it, whatever its listing says.

    An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.

    apps/app_manager.py at v0.3.9
  • A dangerous scan verdict stops the install, and nothing overrides it.

    A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.

    apps/app_manager.py at v0.3.9
  • Consent covers exactly what you reviewed, and an app that changed asks again.

    The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.

    apps/app_manager.py at v0.3.9
  • A setting an app marks secret is kept in the credential store and never shown back.

    The app's settings file holds only a reference, the value lives in the credential store, and every route that shows settings masks it. The app's own code receives the value when it runs.

    apps/secret_fields.py at v0.3.9

PersonalClaw/PersonalClawApps @ 169cbc4f8fc5 · bedrock-models/app.json