Bring the providers you choose.

Models, search, speech, channels, tools, agent runtimes and complete interfaces are apps you install, and replace when your needs change.

The apps for a local model runtime and for MCP tool servers ship inside PersonalClaw itself, so this directory does not list them.

It lists the 69 first-party apps in 14 categories.

Open the app repository

Every app below is from PersonalClaw/PersonalClawApps v0.3.9, the apps release this site pins.

69 apps

A2A Agent Call

Automation

Hand one task to an external A2A agent when a trigger fires, on hosts you allow-list.

A2A Triggers

Alibaba Model Studio

Models

Qwen chat, vision, and embedding models, plus image generation, through DashScope.

Qwen Embedding Image

Amazon Bedrock

Models

Chat, embedding, image, video, and speech models using your AWS credential chain.

Chat Embedding Media Speech

Anthropic

Models

Claude chat models through the Anthropic Messages API.

Claude Chat

Anthropic-Compatible

Models

Connect any endpoint that implements the Anthropic Messages API.

Chat Compatible

Brave Search

Search

Broad web search with ranked links, snippets, and a recency filter.

Web Recency

Browser Connector

Companions

Let a browse task act in your own signed-in browser, only in a tab it opens for itself.

Extension Browse

Claude (Subscription)

Models

Claude models over your existing Claude Code sign-in, with no API key.

Claude Chat Subscription

Claude Code

Agents

Run Claude Code over ACP in a config of its own; every tool beyond its own reads asks the host approval gate.

ACP Coding Approvals

Code Review

Tools

Review a GitHub pull request file by file, riskiest changes first; nothing is posted back.

GitHub Review

Companion

Tools

Opt-in reminders, a folder watchlist, and a day plan, each off until you turn it on.

Reminders Watchlist

DeepSeek

Models

DeepSeek chat and reasoner models through its OpenAI-compatible API.

Chat Reasoning

Design Critique

Tools

Accessibility and craft findings for a URL or screenshot, each with the change that clears it.

Accessibility Review

Diarization (ONNX)

Speech

Install-and-go local speaker diarization using sherpa-onnx.

Local Keyless Diarization

Diarization (pyannote)

Speech

High-accuracy speaker diarization using the pyannote.audio pretrained pipeline.

Local Diarization

Discord Channel

Channels

Pair a DM, converse in servers, and answer approvals with buttons through a Discord bot.

Messaging Threads Reactions

Docs & Slides

Tools

Turn a markdown brief into a PowerPoint deck or a Word or PDF document on your machine.

PPTX DOCX PDF

DuckDuckGo

Search

Keyless, zero-config web search with links and snippets.

Keyless Web

Email Channel

Channels

Converse with your agent by email over IMAP and SMTP, with replies threaded back.

Email Threads

Exa

Search

Semantic web search with relevant highlights and extracted content.

Semantic Extract

FAL

Models

Hosted image and video generation across FAL's model catalog.

Image Video

Faster Whisper

Speech

Local speech-to-text with CTranslate2-optimized Whisper models.

Local Keyless STT

Folder Notification Drop

Channels

Deliver teammate-addressed notifications into a shared folder, for a roster you declare.

Team Folder

Folder Sync

Sync

Sync state between your machines through a shared or synced folder, with no server.

Folder NFS USB

Gemini CLI

Agents

Run Google's Gemini CLI over ACP with its own sign-in; PersonalClaw stores no key.

ACP Coding

Git Repository

Knowledge

Index a git repository's code and docs into your knowledge library, re-reading only changed files.

Git Code Docs

Git Sync

Sync

Sync state between your machines through a git remote you own, as a readable history.

Git Audit

GitHub Repo Watcher

Automation

Fire automations when a watched GitHub repo ships a release or opens an issue.

GitHub Releases

Google Gemini

Models

Gemini chat, embedding, image, video, and text-to-speech models.

Chat Embedding Media

Groq

Models

Low-latency chat inference using Groq's OpenAI-compatible API.

Chat Fast

Growth Tracker

Products

Turn real work into evidenced growth artifacts and a shareable accomplishment document.

Career Projects Tasks

HTTP Webhook Hooks

Automation

Send templated agent lifecycle events to an HTTP endpoint.

Webhook Automation

Issue Radar

Tools

Triage a repository's open issues through gh or glab without changing the tracker.

GitHub GitLab Triage

Kiro CLI

Agents

Run the Kiro CLI agent over ACP when the local binary is available.

Local ACP Coding

Lima Sandbox

Sandboxes

Run agent-influenced commands inside a Lima virtual machine instead of on the host.

VM Isolation

Local Image Generation

Models

Generate images with a ComfyUI server you run on your own machine.

Local Keyless Image ComfyUI

Mail Inbox

Inboxes

IMAP mail from a sender allowlist as inbox items, with threaded reply drafts.

Email Attachments

Menu Bar Companion

Companions

Running loops and waiting approvals in your Mac's menu bar.

macOS Approvals

Meta Muse Spark

Models

Meta Muse Spark chat models through the Meta AI API.

Chat Compatible

Minutes

Products

Combine recordings, notes, transcripts, decisions, and action items on one meeting timeline.

Meetings Transcription Tasks

Mistral AI

Models

Mistral models through its OpenAI-compatible endpoint.

Chat Compatible

Notes

Tools

A git-backed markdown notebook whose notes stay plain files on your machine.

Markdown Git

OpenAI

Models

OpenAI chat, vision, code-tool, and embedding models.

Chat Vision Embedding

OpenAI Codex

Agents

Run the Codex CLI over ACP while PersonalClaw enforces host tool approvals.

ACP Coding Approvals

OpenAI Tool Servers

Tools

Connect OpenAI-compatible tool servers that expose tools over REST.

Tools REST

OpenAI-Compatible

Models

Connect a self-hosted, proxied, or unlisted Chat Completions endpoint.

Chat Compatible

OpenRouter

Models

One key for hundreds of models across providers — chat with image input, embedding, image, and video.

Chat Vision Embedding Image Video

Ops

Tools

An on-call responder that files alarms as incidents and works them against your runbook.

On-call Incidents

Perplexity Sonar

Search

Answer-first live web search with synthesized responses and cited sources.

Answers Citations

Piper TTS

Speech

Local neural text-to-speech with downloadable Piper voices.

Local Keyless TTS

Qdrant Vector Store

Knowledge

Use your own Qdrant for the vector half of knowledge retrieval.

Qdrant Retrieval

RapidOCR (Offline)

Knowledge

Read text from scans and screenshots offline, so a scanned page becomes searchable knowledge.

Local Keyless OCR Offline

Research Lab

Tools

Unattended research campaigns that end in one sourced markdown report.

Research Unattended

Rsync Sync

Sync

Sync state between your machines with rsync over ssh, encrypted end to end by default.

rsync SSH

S3 Sync

Sync

Sync state between your machines through an S3-compatible store you own, encrypted end to end.

S3 MinIO

SearXNG

Search

Private, keyless meta-search through your own SearXNG instance.

Local Keyless Self-hosted

Sentence Transformers

Models

Run text embedding models in-process on your own machine.

Local Keyless Embedding

Shared Automations

Automation

Serve automations from a shared file; each machine fires only its own owner's rows.

Team Triggers

Skills.sh Marketplace

Skills

Search, preview, install, and manage community skills from skills.sh.

Skills Marketplace

Slack Channel

Channels

Monitor Slack channels, respond to mentions, and participate in threads.

Messaging Threads

Spec Builder

Tools

Write a spec and compile it into a workflow definition the engine runs.

Specs Workflows

Tavily

Search

Agent-oriented search with synthesized answers, scored results, and page extraction.

Answers Extract

Telegram Channel

Channels

Pair a chat and converse through a Telegram bot, with inline approvals.

Messaging Threads

Together AI

Models

Serverless model inference through Together AI's compatible API.

Chat Compatible

vLLM

Models

Connect a local vLLM server through its OpenAI-compatible endpoint.

Local Keyless Chat

Voice Clone TTS

Speech

Clone a voice from a short clip and speak with it on your own machine.

Local TTS Voice cloning

Web Tools

Tools

Give agents guarded web search, fetch, and structured extraction primitives.

Search Fetch Extract

Wikipedia Search

Search

Keyless encyclopedic search with ranked articles and introductory extracts.

Keyless Reference

Installation is a security decision.

Apps do not become active the moment code arrives. PersonalClaw separates acquisition, inspection, consent, and enablement.

  1. 01

    Quarantine

    The package lands outside the active runtime while its manifest and contents are inspected.

  2. 02

    Scan

    Supply-chain checks assign a verdict. Dangerous findings cannot be overridden.

  3. 03

    Consent

    The owner sees requested capabilities before deciding whether to continue.

  4. 04

    Enable

    The app receives a scoped gateway token. Its own code still runs as you, which the install review says before you consent.

See declared permissions and scan verdicts before you install

The ecosystem is an open surface.

Provider apps can be small Python adapters. Full apps can ship a backend, mounted React interface, storage, cron work, and event access. The manifest declares what the app may ask the gateway for; its network permission is a declaration, not a fence.

web-tools/app.json at v0.3.9{ "name": "web-tools", "version": "0.1.6", "displayName": "Web Tools", "description": "General web primitives the agent can call: web_search, web_fetch, and web_extract. web_search runs over the search provider you bind in Settings \u2192 Search, web_fetch is an SSRF-guarded page fetch + extraction, and web_extract does structured extraction. No key of its own \u2014 it uses the bound search provider's.", "icon": "Globe", "author": "PersonalClaw", "license": "MIT", "minPersonalClawVersion": "0.2.3", "tags": [ "tool", "web" ], "prompts": [ "prompts/web-extract.yaml" ], "permissions": { "network": true }, "provider": { "id": "tools", "label": "Search, fetch and extract web pages", "type": "tool", "implementation": "provider:create_provider", "capabilities": [ "web" ] } }
Read the app creation guide