惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
WordPress大学
WordPress大学
N
Netflix TechBlog - Medium
T
Troy Hunt's Blog
Help Net Security
Help Net Security
L
LINUX DO - 最新话题
aimingoo的专栏
aimingoo的专栏
Microsoft Azure Blog
Microsoft Azure Blog
Y
Y Combinator Blog
Attack and Defense Labs
Attack and Defense Labs
M
MIT News - Artificial intelligence
Security Archives - TechRepublic
Security Archives - TechRepublic
SecWiki News
SecWiki News
博客园 - 三生石上(FineUI控件)
P
Privacy International News Feed
AI
AI
PCI Perspectives
PCI Perspectives
L
Lohrmann on Cybersecurity
G
Google Developers Blog
N
News | PayPal Newsroom
Hugging Face - Blog
Hugging Face - Blog
B
Blog RSS Feed
The Hacker News
The Hacker News
Apple Machine Learning Research
Apple Machine Learning Research
B
Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
I
InfoQ
Webroot Blog
Webroot Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
V
Visual Studio Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
U
Unit 42
A
About on SuperTechFans
Cyberwarzone
Cyberwarzone
Schneier on Security
Schneier on Security
Cisco Talos Blog
Cisco Talos Blog
D
Docker
博客园_首页
The Cloudflare Blog
S
Secure Thoughts
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
The Last Watchdog
The Last Watchdog
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
Last Week in AI
Last Week in AI
F
Fortinet All Blogs
I
Intezer
Google DeepMind News
Google DeepMind News
Know Your Adversary
Know Your Adversary
Simon Willison's Weblog
Simon Willison's Weblog

Hacker News - Newest: "OpenClaw"

OpenClaw just launched an official app for iPhone, details here - 9to5Mac OpenClaw Launch — Deploy AI Chatbots in Seconds Self-Host OpenClaw AI Agent on VPS: Full Setup Guide GitHub - xltvy/openclaw-memgpt: OpenClaw plugin that gives agents MemGPT-style memory: tiered core/archival/recall storage, self-directed memory operations via tool calls, memory-pressure warnings, and recursive summarisation. Integrates the reference MemGPT implementation via a local sidecar service, preserving the original architecture without reimplementation. Malicious AI 23 ClawHub Plugins Squat Official Org Scopes - Manifold Security what shipping OpenClaw in production taught us — AutoClaw AgentLine — AI Phone API | Phone Numbers, Voice & SMS for AI Agents Make Your OpenClaw Agent Cheaper, and Measure It Yourself GitHub - sammysltd/OpenEmployee: Make your OpenClaw agent employable: deny-by-default governance, budgets, allowlists, approval gates, and a signed audit trail via MakerChecker. Migrate from OpenClaw | Hermes Agent StackOverflow closed my OpenClaw and paperclipAI integration q. as "irrelevant" GitHub - sausin/outpost: Removing AI agents' quiet security problem Potassium — ClawHub Plugins Pi Building Pi, Openclaw's Minimalist Coding Agent | Mario Zechner, Creator of Pi I Spent 4 Hours So You Don’t Have To: Hetzner Metal + NixOS in ~15 Minutes − Irakli's blog GitHub - snuri00/osint-mcp: Self-hosted OSINT toolkit — MCP server, AI REPL, CLI, web app & chat apps (WhatsApp/Telegram/Discord via OpenClaw). Entity, event/news & social/community intelligence. Keyless-first. What a Regex Can't Do GitHub - ai-sns/openclaw-hermes-agent-network: OpenClaw Hermes AI Agent Social Network🦞💬🦞Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment. Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets GitHub - CODEANDTRUST/clawcall: Give your OpenClaw / self-hosted AI agent inbound phone calls - a Twilio-to-gateway voice bridge with working agent tools mid-call (MIT). Build a ZeroCost Web Automation Pipeline with OpenRouter, OpenClaw, and MediaUse Let OpenClaw Run Wild in Simulation, Not on Your Customers | Veris AI GitHub - gpdir16/tabyAgent: A lighter, easier alternative to OpenClaw/Hermes. Runs autonomously inside Docker and chats with you through Telegram. Ask HN: What are the biggest problems you find in OpenClaw/Hermes? Microsoft launches Scout, an OpenClaw-inspired personal assistant GitHub - openclaw/openclaw-windows-node: Windows companion suite for OpenClaw - System Tray app, Shared library, Node, and PowerToys Command Palette extension Microsoft unveils Scout, an autonomous AI agent built on OpenClaw Gavriel Cohen found his own code inside OpenClaw, so he walked away GitHub - hunvreus/heypi: Chat agents for your team, with approvals and sandboxed tools. Slack, Discord, Telegram, webhooks. HolaClaw: run OpenClaw securely in Mac Multi-Agent Orchestration System: Hermes (Windows) ↔ OpenClaw (WSL) We were building infra for OpenClaw, and today I just tried Hermes and holy shit GitHub - openclaw/openclaw: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 OpenClaw as the Universal Operating System for Agents ARC Prize - Community Leaderboard Setup OpenClaw with Slack: from install to first message twitter.com I Gave My OpenClaw Agent a Physical Body Use Grok in OpenClaw The creator of OpenClaw used $1,300,000+ of OpenAI tokens in 30 days, which is a hell of a perk GitHub - oswarld/openshears: 🔪 THE OPENCLAW TERMINATOR 🦞 Are we human? Show HN: OpenClaw is just not dangerous enough. I needed something else OpenClaw creator burned through $1.3 million in OpenAI API tokens in a single month — bill covered 603 billion tokens across 7.6 million requests and 100 coding agents Reducing OpenClaw token usage OpenClaw/Hermes Hosting Comparison GitHub - ExTV/rikkahub-agent: RikkaHub Agent -- is RikkaHub fork that have Full agent mode . For $1.3 million a month, OpenClaw founder Peter Steinberger runs 100 AI agents that code, review PRs, and find bugs Where OpenClaw Security Is Heading OpenAI Models in OpenClaw, Done Right GitHub - thesysdev/openclaw-os: The default workspace for OpenClaw Token, Harness, OpenClaw, RAG, MCP, Agent – What's the Difference? We need a safe alternative to Telegram for agents like OpenClaw or Hermes Two OpenClaw agents negotiate a YC SAFE with Agentic Power of Attorney OpenClaw Had a Rough Week GitHub - LobsterTrap/tank-os GitHub - haishmg/Clawback How OpenClaw Got Safer in Public openclaw ggsql — ClawHub Show HN: iClaw is part OpenClaw, part Siri, powered by Apple Intelligence GitHub - lotsoftick/openclaw_client: OpenClaw web client Show HN: OpenClaw but Efficient and with an SDK GitHub - TheGuyWithoutH/mac-computer-use GitHub - microsoft/openclaw: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 The OpenClaw turkey problem OpenClaw: opioids for Chinese AI companies GitHub - supersuit-tech/permission-slip [AINews] The Two Sides of OpenClaw OpenClaw stats don't add up GitHub - brexhq/CrabTrap: An LLM-as-a-judge HTTP proxy to secure agents in production Anthropic - OpenClaw Hustlers are cashing in on China’s OpenClaw AI craze Engineering Managers are going to hate OpenClaw GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw Ask HN: Who is using OpenClaw? Why Meta’s AI Alignment Director Couldn't Stop Her Own Agent—and How to Fix It GitHub - epsilla-cloud/clawtrace: Make your OpenClaw agents better, cheaper, and faster. Ask HN: What are you using OpenClaw or agents for? GitHub - epsilla-cloud/clawtrace: Make your OpenClaw agents better, cheaper, and faster. GitHub - theprint/nfh-self-improvement-loop: Minimal adversarial framework for AI agent self-modification. Inspired by karpathy/autoresearch. GitHub - ibrahimmukherjee-boop/ClearFrame: OpenClaw Alternative with better governance, security Show HN: Agent-Notifications – Real-Time Alerts for OpenClaw and Hermes Agents OpenClaw + Claude are better than therapy GitHub - zeulewan/glueclaw: Use Claude Max subscription with OpenClaw again Anthropic temporarily banned OpenClaw’s creator from accessing Claude OpenClaw’s memory is unreliable, and you don’t know when it will break Give Your OpenClaw Agent a Real Memory You need a Windows Remote Desktop, not an OpenClaw GitHub - cruxdigital-llc/CongaLine: Deploy and manage a fleet of OpenClaw AI assistants anywhere. Supporting hobbyist, team, and enterprise use cases. GitHub - cezarpena/vsm-cell: VSM-Cell is an OpenClaw agent P2P mesh orchestration standalone app. GitHub - joshchoi4881/dropspace-agents GitHub - askalf/dario: Universal LLM router. One local endpoint, every provider — OpenAI, Groq, OpenRouter, Ollama, Claude Max/Pro subscriptions, the Claude Agent SDK, any OpenAI-compat URL. Your tools stop caring which vendor is upstream. Tutorial: Secure OpenClaw with CloudConnexa OpenClaw and the Dream of Free Labour GitHub - RageDotNet/openclaw-webdav GitHub - aelaguiz/doctrine: Code-like DSL and compiler for agent workflows that compile to portable AGENTS.md instructions. Unlocking cloud inference compute for OpenClaw OpenClaw for Sales: How AI Agents are Revolutionizing Revenue Teams | Kickscale OpenClaw Architecture - Part 1: Control Plane, Sessions, and the Event Loop
GitHub - kevinslin/openai-apps: Support openai apps in openclaw
2026-04-08 · via Hacker News - Newest: "OpenClaw"
OpenAI Apps logo

Use ChatGPT apps inside OpenClaw.

Prerequisites

Quickstart

  1. Clone this repo:
git clone https://github.com/kevinslin/openai-apps.git
cd openai-apps
  1. Install dependencies and the local bundle into OpenClaw:
pnpm install
openclaw plugins install .
  1. Enable the bundle in your OpenClaw config:
  • set allow_destructive_actions to always in order to support write actions (eg. updating google calendar). default is never

Warning

Enabling write actions (allow_destructive_actions: "always") increases risk. Agent mistakes or prompt-injection attacks can trigger unintended destructive operations (for example, deleting or modifying data in connected apps like email, calendar, or task systems). Keep this set to "never" unless you explicitly accept that risk.

{
  "plugins": {
    "entries": {
      ...
      "openai-apps": {
        "enabled": true,
        "config": {
          "allow_destructive_actions": "never",
          "connectors": {
            "*": {
              "enabled": true
            }
          }
        }
      }
    }
  }
}
  1. Restart the OpenClaw gateway so plugin config changes are loaded.
  2. Open your normal OpenClaw chat/TUI session and issue an app-backed request (examples in Usage below).

Usage

summarize my recent emails
CleanShot 2026-03-30 at 18 38 20@2x
add a calendar event reminding me to walk my gerbil tomorrow at 7am for 30 minutes
CleanShot 2026-03-30 at 18 39 50@2x

Configuration

All bundle config lives under plugins.entries["openai-apps"].config.

  • allow_destructive_actions: Controls destructive app-action elicitations. Use "always" to auto-accept, "on-request" to prompt through the MCP client when supported, or "never" to auto-decline. Defaults to "never".
  • connectors: Per-app enablement map. Use explicit connector ids like gmail, linear, or google_calendar.
  • connectors["*"]: Enables all accessible ChatGPT apps, with explicit connector entries able to disable individual apps.
  • appServer.command / appServer.args: Override how the bundle launches codex app-server.

Example with one explicitly enabled connector:

{
  "plugins": {
    "entries": {
      "openai": {
        "enabled": true
      },
      "openai-apps": {
        "enabled": true,
        "config": {
          "allow_destructive_actions": "never",
          "connectors": {
            "gmail": {
              "enabled": true
            }
          }
        }
      }
    }
  }
}

Wildcard Configuration

To enable all accessible ChatGPT apps, use *:

{
  "plugins": {
    "entries": {
      "openai": {
        "enabled": true
      },
      "openai-apps": {
        "enabled": true,
        "config": {
          "allow_destructive_actions": "never",
          "connectors": {
            "*": {
              "enabled": true
            }
          }
        }
      }
    }
  }
}

You can combine wildcard enablement with explicit disables:

{
  "plugins": {
    "entries": {
      "openai-apps": {
        "enabled": true,
        "config": {
          "allow_destructive_actions": "never",
          "connectors": {
            "*": {
              "enabled": true
            },
            "slack": {
              "enabled": false
            }
          }
        }
      }
    }
  }
}

Limitations

  • Currently, destructive actions do not support on-demand elicitation (dynamic permission prompts). The OpenClaw PI MCP client does not currently support MCP elicitations.

Runtime State

The bundle keeps its runtime state under plugin-runtimes/openai-apps/.

  • codex-home/: shared CODEX_HOME used for both snapshot refresh and per-tool invocation
  • connectors.snapshot.json: persisted connector records derived from app/list
  • refresh-debug.json: last refresh result/debug payload written by the bundle

Both refresh and invocation launch codex app-server with the same bundle-owned codex-home. Invocation still starts a fresh app-server thread for every tool call, but it now rewrites the derived apps config into the app-server-managed config inside that shared home before starting the turn instead of using a temporary invocation-only home.

Snapshot Shape

The persisted snapshot under plugin-runtimes/openai-apps/connectors.snapshot.json stores connector-level records derived from app/list. It does not persist raw inventory or any status payload.

Example:

{
  "version": 2,
  "fetchedAt": "2026-03-30T18:00:00.000Z",
  "projectedAt": "2026-03-30T18:00:00.000Z",
  "accountId": "acct_123",
  "authIdentityKey": "user@example.com",
  "connectors": [
    {
      "connectorId": "gmail",
      "appId": "asdk_app_gmail",
      "appName": "Gmail",
      "publishedName": "chatgpt_app_gmail",
      "appInvocationToken": "gmail",
      "description": "Read and send Gmail messages.",
      "pluginDisplayNames": ["Gmail"],
      "isAccessible": true,
      "isEnabled": true
    }
  ]
}

Internals

This bundle:

  • publishes one local MCP tool per enabled ChatGPT app connector
  • uses codex app-server as the single authority for both tool publication and invocation
  • reads OpenClaw-rooted openai-codex auth and projects it into the spawned app-server session

Published tool names use the chatgpt_app_<connectorId> namespace. Each tool accepts a single natural-language request string and executes the app on a fresh app-server thread.

For more information on plugin internal logic, see flows.

Appendix

Calls to App Server

Setting the developer message

[
  {
    approvalPolicy: {
      granular: {
        sandbox_approval: false,
        rules: false,
        skill_approval: false,
        request_permissions: true,
        mcp_elicitations: true,
      },
    },
    developerInstructions:
      'You are servicing one OpenClaw connector tool call for Gmail. Use the app mentioned in the user input instead of browsing or relying on unrelated tools. Do not use browser, shell, file, web, image, memory, or unrelated tools. Do not ask follow-up questions. Do not fabricate success. Return only JSON matching the schema {"status":"success|failure","result":"string","error":"string"}.',
    ephemeral: false,
    experimentalRawEvents: false,
    persistExtendedHistory: true,
  },
];

Example call

[
  {
    text: "$gmail Summarize my recent emails",
    text_elements: [],
    type: "text",
  },
  {
    name: "Gmail",
    path: "app://asdk_app_gmail",
    type: "mention",
  },
];