PageForge 1.3: Überprüfen Sie jeden Durchlauf, bevor er schreibt, aktualisierte Seiten, SpinTax und wiederaufnehmende Batches. Sehen Sie, was sich geändert hat
Agentic Admin icon
aktiv gepflegt Getestet mit WP 7.1 #8 in abilities-api

Agentic Admin

Agentic Admin transforms your WordPress admin panel into an intelligent command center. Instead of navigating through multiple screens to diagnose issues, you simply describe your problem in plain English.

Aktive Installationen<10Neu
Downloads · 30d418▼ -44.3% vs prev. 30d
Wertung—0 Bewertungen
Gesundheits-Score60/100Messe
Downloads aller Zeiten967Seit Oktober 2026
Unterstützung gelöst—Keine aktuellen Threads
erfordertWP 6.9PHP 8.2+
Downloads · 7d71▼ -15.5% week over week
Unser Urteil

Mit Vorsicht verwenden

Agentic Admin works, but test it on a staging site before relying on it in 2026. Was last updated 2 months ago, and scores 60/100 on our health check.

  • Getestet mit dem neuesten WordPress (7.1)
  • Kleine Benutzerbasis (<10 aktive Installationen)
  • Bisher sehr wenige Bewertungen
  • Benötigt PHP 8.2 oder neuer

Wie stapelt es sich?

Side-by-side bei Installationen, Updates, Bewertungen und Support

Tägliche Downloads

3469104Oct 2Oct 26Nov 19
Gestern10
Täglicher Durchschnitt (1 Jahr)20
Spitzentag1396. Oktober 2026
Letzte 12 Monate971

Download-Spitzen folgen normalerweise einer neuen Version - jede Website, die automatisch aktualisiert wird, gilt als Download.

Ranglisten

Where Agentic Admin stands today

WordPress.org Ranglisten suchen

Live-Position in der Plugin-Suche, Top 100
StichwortPositionKonkurrierende PluginsKategorie
abilities-api >100 2,947 Best abilities-api plugins →
Ai >100 8,371 Best AI plugins →
site reliability >100 1,646 Best site reliability plugins →
sre #3 4 Best sre plugins →
webllm #1 2 Best webllm plugins →

About Agentic Admin

From the official readme · v0.11.0

Beschreibung

Agentic Admin transforms your WordPress admin panel into an intelligent command center. Instead of navigating through multiple screens to diagnose issues, you simply describe your problem in plain English.

Merkmale

  • 100% Local AI: Uses WebLLM to run Qwen 3 1.7B (default) or Qwen 2.5 7B directly in your browser via WebGPU
  • Privacy-First: AI inference runs in your browser – your prompts and content are never sent to an AI service. A few abilities look up public data (CVE databases, WordPress.org checksums, web search); all are listed under External services
  • Zero Server Costs: No GPU infrastructure needed – computation happens on the client
  • WordPress Abilities API: Natively integrates with WordPress’s official Abilities API
  • Natural Language Interface: Describe problems in plain English, get intelligent solutions

Bedarf

  • WordPress 6.9+ (includes the Abilities API)
  • PHP 8.2+
  • Modern browser with WebGPU support (Chrome 113+, Edge 113+)

Externe Dienste

This plugin runs AI locally in your browser by default, and your prompts and chat content are never sent to an AI service unless you explicitly enable the external LLM provider below.

Separately from AI inference, some abilities query public data sources to do their job: a security scan checks your plugin versions against CVE databases, a checksum verification compares your files against WordPress.org, and a web search sends your query to a search engine. Every external request the plugin makes is listed here:

Model source for the local engine (site-owner configured) — Only when an administrator sets a model source and loads a model.
The local engine runs a language model in the administrator’s browser. The model is not part of the plugin: model files are over 1 GB. The plugin contains no model download address. An administrator enters where models are downloaded from under Settings → Model source, and until then the local engine is off. Nothing is downloaded until an administrator then selects a model and clicks Load Model. The browser fetches the files directly from the configured source (the WordPress server makes no requests for them), and no prompts, admin data, or telemetry are sent. Files are cached in the browser after the first download.

To use the models published by the MLC-AI project, enter these addresses. No account or API key is needed:

  • Model weights URL: https://huggingface.co/mlc-ai/
  • Model library URL: https://raw.githubusercontent.com/mlc-ai/binary-mlc-llm-libs/main/web-llm-models/

You can also host the same files yourself and enter your own https addresses. Use the same layout: each model’s weights in <weights URL>/<model ID>/resolve/main/, and the compiled model libraries in <library URL>/<WebLLM version>/ (the plugin adds the version it needs, currently v0_2_80).
Hugging Face terms: https://huggingface.co/terms-of-service — Privacy: https://huggingface.co/privacy
GitHub terms: https://docs.github.com/en/site-policy/github-terms/github-terms-of-service — Privacy: https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement

External LLM provider (user-configured) — Only when you switch the engine from “Local” to “Remote” in settings.
When enabled, chat messages, tool descriptions, and tool results are sent through this plugin’s REST proxy (/wp-json/agentic-admin/v1/llm-proxy/) to the OpenAI-compatible endpoint URL you configure (e.g. Ollama, LM Studio, vLLM, OpenAI, Groq, Together). You choose the endpoint; the plugin does not preselect or default to any third-party provider. No data is sent until you save an endpoint and start a chat in Remote mode.

DuckDuckGo HTML search — Only when the optional web-search ability is invoked by the assistant.
The user’s search query is sent to https://html.duckduckgo.com/html/ over GET. No WordPress user data is sent.
DuckDuckGo terms: https://duckduckgo.com/terms — Privacy: https://duckduckgo.com/privacy

NVD CVE database (NIST) — Whenever the security-scan ability is invoked.
security-scan includes a plugin vulnerability check, so the names and versions of your active plugins are sent to https://services.nvd.nist.gov/rest/json/cves/2.0 to look up known CVEs. No user data, post content, or credentials are sent.
NVD terms: https://nvd.nist.gov/developers/terms-of-use — Privacy: https://www.nist.gov/privacy-policy

MITRE CVE API — Only when the security-scan vulnerability check finds a CVE identifier and follows up on it.
The CVE ID (e.g. CVE-2024-12345) is sent to https://cveawg.mitre.org/api/cve/ for details. No WordPress user data is sent.
MITRE terms: https://www.cve.org/Legal/TermsOfUse — Privacy: https://www.cve.org/Legal/PrivacyPolicy

WordPress.org plugin checksums — Only when the optional verify-plugin-checksums ability is invoked.
Installed plugin slugs and versions are sent to https://downloads.wordpress.org/plugin-checksums/ and https://plugins.svn.wordpress.org/ to verify file integrity against the official WordPress.org distribution.
WordPress.org policies: https://wordpress.org/about/privacy/

WordPress.org core source (SVN) — Only when the optional verify-core-checksums ability finds a modified core file and diffs are requested.
The original copy of that one file is fetched from https://core.svn.wordpress.org/tags/{version}/ so the plugin can show you a diff against your local version. Only the WordPress version number and the core file path are sent, both of which are public information; no site data is transmitted. The checksum list itself comes from WordPress core’s own get_core_checksums() function.
WordPress.org policies: https://wordpress.org/about/privacy/

Source code and build process

Agentic Admin is fully open source under GPL-2.0-or-later. The complete, human-readable source — including the JavaScript/React sources behind the compiled assets in build-extensions/ — is maintained in a public repository:

https://github.com/pluginslab/wp-agentic-admin

The files under build-extensions/ are generated from the sources in src/ with @wordpress/scripts (webpack). They contain only JavaScript and CSS: the bundles (index.js, sw.js, and code-split chunks) and the stylesheets. No WebAssembly, binaries, or other compiled artifacts are distributed with the plugin. To regenerate them from a checkout:

  1. npm install
  2. npm run build

There is no build step for the PHP. The WebLLM engine is bundled into the plugin from its npm package. The AI model weights and their compiled model libraries are loaded at runtime from the provider documented under External services above; these are large provider-hosted model files (over 1 GB), not part of the plugin code.

Installation

  1. Laden Sie den Ordner agentic-admin in das /wp-content/plugins/-Verzeichnis hoch
  2. Aktivieren Sie das Plugin über das „Plugins“-Menü in WordPress
  3. Navigate to “Agentic Admin” in your WordPress admin menu
  4. Wait for the AI model to download (one-time, ~1.2GB for Qwen 3 1.7B or ~4.5GB for Qwen 2.5 7B)
  5. Start chatting!

Änderungsprotokoll

The local engine now downloads models only from a source you set. If you used the local engine before, open Settings → Model source and enter the addresses listed under External services. Models already in your browser cache are reused.

0.11.0

  • Renamed: Plugin is now “Agentic Admin”. Text domain “agentic-admin”, function prefix agentic_admin_*. WordPress.org submission-ready.
  • Removed: feedback system, WebMCP bridge, voice input, file editing (write-file), and AI content generation (content-generate), plus three low-value abilities (backup-check, opcode-cache-status, disk-usage). Agentic Admin is a site health and maintenance assistant: it does not edit files or generate content. Removed code remains available in the project’s git history.
  • Security: blocked sensitive-column reads (user_email, user_pass) in query-database to prevent reconnaissance attacks (#166). Hardened query length cap and read-only verb gate.
  • Security: escaped output in functions-abilities.php (#121). Documented direct-DB-call rationale in db-optimize and database-check.
  • Docs: corrected the External services section. The CVE lookups were attributed to a plugin-vulnerability-scan ability that does not exist; they are made by security-scan. Added the previously undisclosed core.svn.wordpress.org fetch used by verify-core-checksums to build diffs. Replaced two absolute privacy claims that the section’s own list contradicted.
  • Compliance: removed deprecated load_plugin_textdomain() call, prefixed uninstall.php globals, fixed nonexistent Domain Path header, excluded CLOUDFEST_HACKATHON.md from distribution build.
  • New: ability manifest as single source of truth for which abilities register, with a agentic_admin_enabled_abilities filter for selective override. PHP authoritative for PHP-backed abilities; JS adds back the JS-only ones.
  • Fixed: thinking-disable setting now actually suppresses the streaming UI even when Qwen ignores /nothink (#181).
  • Fixed: Settings panel is now a real tab (not a stateful cog toggle). No more lingering Chat-tab underline or stale-state regressions (#197).
  • Fixed: Activate/Deactivate buttons on plugin-list rows now flip to the inverse action after a successful click (#179).
  • Fixed: AI model no longer preloads on every wp-admin page, deferred until the user opens the sidebar for the first time (#116).
  • Improved: post-tool summarization is brief (no re-listing items the user already sees in the tool result UI).
  • Improved: ChatInput keyboard handling simplified (Space inserts a space, no push-to-talk hijacking).
  • Removed: the local knowledge base (in-browser embeddings, vector store, and the codebase-index, code-search, schema-extract, wp-api-extract, docs-extract, and codebase-extract abilities). The plugin no longer loads Transformers.js from a CDN or ships any WebAssembly module.
  • Security: read-file now refuses files that can hold credentials, keys, or salts (wp-config.php, .env, private keys, database dumps, and any file defining the auth keys, salts, or DB password) instead of relying on redaction.
  • Security: wp-config-list now has its own PHP backend that reads constant names with the PHP tokenizer and never reads the values of credentials, keys, or salts.
  • Security: removed the security-scan salts check, which read the auth salt and could never fail.
  • Changed: AI Connectors are detected through the AI Client registry, as on the core Connectors screen, instead of reading API-key options.
  • Fixed: plugin, must-use plugin, and content paths are derived from the plugin’s own location and WordPress functions instead of WP_PLUGIN_DIR, WPMU_PLUGIN_DIR, and WP_CONTENT_DIR. Core checksum verification no longer miscounts files when the content directory is moved. The debug log path follows WordPress’s own error_log setting.
  • Fixed: read-file and uploads-scan resolve the site root with get_home_path(), so subdirectory installs work.
  • Security: the external LLM proxy no longer relays the provider’s response verbatim. Each streamed event is decoded and re-encoded as escaped JSON; anything else is dropped.
  • Changed: “Tested up to” is declared only in readme.txt.
  • Fixed: the model notice names where the model is downloaded from and its real size, instead of saying no data is sent to external servers.
  • Changed: the plugin no longer contains any model download address. The site owner sets the model source under Settings → Model source (the MLC-AI addresses are listed under External services), and the local engine stays off until it is set. WebLLM’s built-in model list is removed at build time.
  • Fixed: .well-known scanning resolves via get_home_path() instead of ABSPATH, so subdirectory installs scan the real site root.
  • Removed: 7 stale tab references and 6+ stale docs files (FEEDBACK-DEV.md).
  • Tests: 96 unit tests passing, plus the new manifest test suite (7 cases), index test suite (6 cases), and react-agent regression tests (3 cases for the per-call state cleanup fix).

0.10.0

  • CloudFest Hackathon 2026 release: 78 PRs merged, 42+ abilities shipped by 11 contributors
  • New: Plugin Abilities Platform, third-party plugins can auto-register abilities with the AI assistant
  • New: Voice input via local Whisper model, all audio stays on-device
  • New: In-browser RAG knowledge base with vector embeddings computed client-side
  • New: Settings UI with GPU detection, context window tuning, and knowledge base toggle
  • New: External AI provider support (Ollama, LM Studio, OpenAI, any compatible endpoint) via PHP REST proxy
  • New: WebMCP bridge for external AI agents via navigator.modelContext
  • New: “Check if Hacked” multi-step security workflow
  • New: Gutenberg editor sidebar and admin bar chat integrations
  • New: 28+ new abilities including web-search, security-scan, plugin vulnerability scanning, read-file, write-file, query-database, content-generate, and more
  • New: E2E test runner mirroring browser ReAct loop
  • New: CI/CD via GitHub Actions (PHP lint, JS lint, unit tests, build check)
  • New: Feedback system with thumbs up/down stored locally
  • New: Distribution zip for WordPress Playground compatibility
  • Improved: WCAG 2.2 AA accessibility compliance
  • Improved: GPU capability detection with f32 precision fallback
  • Improved: Fuzzy plugin name matching for activate/deactivate actions

0.9.5

  • New: Split Gutenberg Integration into three separate goals — Block Editor Chat Window (Goal 7), Update Post Content Ability (Goal 8), WASM Dev Docs Abilities (Goal 9)
  • New: Goal 9 aligned with existing feature/wasm-sqlite-devdocs branch work (4 abilities, 11 tests)
  • New: GitHub issues created for Goals 6-9 (#32-#35)
  • New: Voice + Context Recording separated as Goal 1.5 (stretch)
  • New: WebMCP Integration added as Goal 6 (stretch)
  • Improved: CLOUDFEST_HACKATHON.md — all goals now follow consistent format, code examples stripped from stretch goals

0.9.4

  • Updated: WebLLM upgraded from 0.2.80 to 0.2.82
  • New: /playground Claude Code skill for spinning up WordPress Playground with the plugin mounted and activated

0.9.3

  • New: ONBOARDING.md — step-by-step hackathon guide with project tour and role-specific instructions
  • New: /issue Claude Code skill for creating GitHub issues via interview with codebase inspection
  • Improved: CLOUDFEST_HACKATHON.md simplified — removed duplicated role descriptions and project summary, now links to ONBOARDING.md
  • Improved: README.md updated with /issue skill in Claude Code integration table

0.9.2

  • New: AI Fundamentals glossary with ~60 terms linked back to source chapters
  • New: Chapter 13 — “Designing Abilities” guide for Writers and UX contributors
  • New: End-to-end walkthrough in Chapter 8 tracing a message through the full system
  • New: Testing guidance section in Chapter 11 for LLM Testers writing tool selection tests
  • Improved: Trimmed overly theoretical content from Chapters 1, 2, and 5
  • Improved: Deduplicated hardware requirements — Chapter 3 is now single source of truth
  • Improved: INDEX.md updated with new “For Writers & Designers” section

Vollständiges Änderungsprotokoll auf WordPress.org →

Screenshots

The Agentic Admin chat tab in wp-admin, mid-conversation. The model has just answered a question about installed plugins by calling the plugin-list tool locally — full ReAct trace (user question, thought process, tool call, answer) visible.
The Agentic Admin chat tab in wp-admin, mid-conversation. The model has just answered a…
First-run model download in progress. The Qwen 3 1.7B weights (~1.2 GB) are fetched from the configured model source — once per browser, cancellable, cached for subsequent sessions.
First-run model download in progress. The Qwen 3 1.7B weights (~1.2 GB) are fetched from…
The Abilities browser, listing every tool the assistant can call against the WordPress Abilities API on this site.
The Abilities browser, listing every tool the assistant can call against the WordPress…
Settings panel. Set the model source, see detected GPU + VRAM, tune context-window size per model based on your hardware, toggle thinking mode, and switch between the local engine (WebLLM + WebGPU), a remote OpenAI-compatible endpoint, or the WordPress 7.0 Connector.
Settings panel. Set the model source, see detected GPU + VRAM, tune context-window size…
Multi-step workflow execution. "Do a performance check" is recognized as a 2-step workflow — the assistant runs site-health and error-log-read in sequence, then summarizes the environment (WP version, PHP, memory, debug mode, error log status) in one answer.
Multi-step workflow execution. "Do a performance check" is recognized as a 2-step…
WordPress 7.0 AI Connector integration. The Connector tab picks up any AI provider registered via WP 7.0's built-in Connector API — Anthropic, Google, OpenAI, or any third-party ai_provider plugin — and uses it as the model backend with zero extra setup.
WordPress 7.0 AI Connector integration. The Connector tab picks up any AI provider…

Für Entwickler

Ist das dein Plugin? Zeigen Sie die Zahlen.

Fügen Sie Ihrer Website, Docs oder GitHub Readme ein Live-Badge hinzu. Es wird von selbst aktualisiert - kein Konto erforderlich.

Aktiv installiert Badge Bewertungsabzeichen Gesundheits-Score-Abzeichen

Best Agentic Admin alternatives

All abilities-api plugins →
Alternativen
Rang Plugin Aktive Installationen Wertung Aktualisierten Gesundheit
1 MCP Adapter MCP Adapter Expose WordPress abilities as Model Context Protocol (MCP) tools, resources, and prompts… von WordPress.org 80K+ ★★★★★★★★★★ 5 (2) Vor 19 Stunden 82
2 Agent Abilities for MCP – Connect Claude and ChatGPT with Permission Controls and Audit Log Agent Abilities for MCP WordPress MCP server for Claude and ChatGPT with limited access, a pause switch, read-only… by Unaib Amir 1K+ ★★★★★★★★★★ 4.8 (5) Vor 5 Tagen 85
3 AgizoAI Agentic Browsing Optimizer AgizoAI Agentic Browsing Optimizer Prepare WordPress for AI agents with an agentic readiness dashboard, llms.txt, WebMCP-style… by AgizoAI.com 100+ ★★★★★★★★★★ Keine Bewertungen Vor 1 Monat 68
4 HLB Ability Registry for MCP HLB Ability Registry for MCP An admin-curated ability registry for the WordPress Abilities API, with a per-ability… by Jordan Hlebarov 20+ ★★★★★★★★★★ Keine Bewertungen Vor 1 Monat 63
5 SlyTranslate – AI Translation Abilities SlyTranslate – AI Translation Abilities AI translation for WordPress — admin UI, Gutenberg inline, and MCP workflows for external… by Timon 10+ ★★★★★★★★★★ 5 (1) Vor 1 Monat 69
6 Seeb Abilities – 100 New Abilities, Infinite Possibilities for AI Agents Seeb Abilities Adds new abilities to the WordPress Abilities API, so AI agents and MCP clients can manage… by Sanjeev Aryal <10 ★★★★★★★★★★ 5 (1) Vor 3 Wochen 71
7 Tessera for the Abilities API Tessera for the Abilities API Snapshot, audit, and rollback layer for plugins that register abilities via the WordPress… by Ibrahim <10 ★★★★★★★★★★ Keine Bewertungen Vor 6 Monaten 36
9 ModelGain Agent Readiness Audit ModelGain Agent Readiness Audit Audit whether a WordPress site is discoverable, understandable, and safely operable by AI… by ModelGain.com <10 ★★★★★★★★★★ Keine Bewertungen Vor 1 Monat 60
10 Npcink Abilities Toolkit Npcink Abilities Toolkit Expose and inspect WordPress Abilities API capabilities for AI hosts and clients, without… by Npcink <10 ★★★★★★★★★★ Keine Bewertungen Vor 3 Wochen 64
11 StoreCrafted Site Visibility Manager for WooCommerce StoreCrafted Site Visibility Manager for WooCommerce Granular public allowlist for WooCommerce Coming Soon — open homepage and blog while the… by StoreCrafted <10 ★★★★★★★★★★ Keine Bewertungen Vor 3 Wochen 64

Fragen und Antworten

Agentic Admin: quick answers

Gerade Antworten, gezogen von Live WordPress.org Daten.

Quelle: WordPress.org

Is Agentic Admin free?

Yes. Agentic Admin is free to download and use from the official WordPress.org plugin directory.

Is Agentic Admin safe to use in 2026?

Agentic Admin works, but test it on a staging site before relying on it in 2026. Was last updated 2 months ago, and scores 60/100 on our health check.

How many websites use Agentic Admin?

Agentic Admin is active on <10 WordPress websites and has been downloaded 967 times since it launched in October 2026. It was downloaded 418 times in the last 30 days.

Does Agentic Admin work with WordPress 7.1?

Yes. The developer has tested Agentic Admin up to WordPress 7.1.5, the latest release. It requires WordPress 6.9 or newer.

What PHP version does Agentic Admin need?

Agentic Admin requires PHP 8.2 or higher. Most hosts run PHP 8.x today, so it works on any modern WordPress hosting.

When was Agentic Admin last updated?

The latest version, 0.11.0, was released on October 3, 2026 (2 months ago).

Who makes Agentic Admin?

Agentic Admin is developed and maintained by Marcel Schmitz.

What are the best alternatives to Agentic Admin?

The most popular alternatives to Agentic Admin are MCP Adapter (80K+ installs), Agent Abilities for MCP (1K+ installs) and AgizoAI Agentic Browsing Op… (100+ installs).

Angetrieben von PageForge

Eine Vorlage und eine Tabelle. Eine echte Seite für jede Suche.

PageForge Verwandelt jede Zeile eines CSV in eine WordPress-Seite mit eigenem Titel, URL, SEO Felder und Schema entworfen. Kostenlos auf WordPress.org.

  • CSV und XLSX, plus Google Sheets auf Beruf und Unternehmen
  • seinen eigenen Titel, URL, SEO Felder und Schema für jede Seite
  • Arbeitet mit dem Blockeditor, Elementor, Divi und Avada
  • Kostenlos auf WordPress.org, keine Kreditkarte

↑↓ bewegen↵ öffnen