[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74378":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},74378,"thepopebot","stephengpope\u002Fthepopebot","stephengpope","The Pope Bot is an autonomous AI agent that you can configure and build to do just about anything you want, all day, everyday, 24\u002F7.","https:\u002F\u002Fskool.com\u002Fai-architects",null,"JavaScript",1826,660,37,36,0,1,5,47,3,65.66,"MIT License",false,"main",[],"2026-06-12 04:01:15","# thepopebot\n\nYour personal agent, coding environment, and communication platform — all in\none app. Works with any LLM or coding agent. Designed to be simple, unified,\nsecure, and easy.\n\n- 💬 **Smart chat integrations** — Telegram today; Slack and Discord coming soon. Plus the built-in web chat.\n- 🧠 **Any LLM** — Anthropic, OpenAI, Google, DeepSeek, MiniMax, Mistral, xAI, Kimi, OpenRouter, NVIDIA, or any OpenAI-compatible endpoint.\n- 🤖 **Any coding agent** — Claude Code, Codex, Gemini, OpenCode, Pi, or Kimi.\n- 💻 **Live coding workspaces** — open a terminal in your browser, attach to a running container, share the same session as your chat.\n- 🔧 **Real work, not just chat** — agent writes code, opens a PR, auto-merges, DMs you when it's done.\n- 🔐 **Yours, fully** — runs on your hardware, your repo, your tokens.\n\n\u003Ca href=\"https:\u002F\u002Fwww.skool.com\u002Fai-architects\">\u003Cimg src=\"docs\u002Fhero.png\" width=\"100\" alt=\"thepopebot\" \u002F>\u003C\u002Fa>\n\n[Get priority support HERE](https:\u002F\u002Fwww.skool.com\u002Fai-architects)\n\n---\n\n## How it works\n\nThree doors, one brain:\n\n```\n      ┌── Browser chat ──┐                  ┌── Telegram (verified per-user)\n      │                  ▼                  ▼\n      │            ┌──────────────────────────────────┐\n      │  attach    │           The Brain              │\n      │  a live    │     (your event handler)         │\n      │  terminal  │                                  │\n      │            │   • picks the coding agent       │\n      │            │   • picks the coding agent       │\n      │            │   • remembers the session        │\n      │            │   • runs Docker for you          │\n      └── Code ────┤                                  │\n        workspace  └──────────────┬───────────────────┘\n                                  │\n                         ┌────────┴────────┐\n                         ▼                 ▼\n                  ┌─────────────┐   ┌─────────────────┐\n                  │  Live chat  │   │   Agent job     │\n                  │ (right now) │   │  (background)   │\n                  │             │   │                 │\n                  │ same coding │   │ same coding     │\n                  │ agent runs  │   │ agent runs in   │\n                  │ in-process  │   │ a fresh Docker  │\n                  │ or in a     │   │ container,      │\n                  │ headless    │   │ opens a PR,     │\n                  │ container   │   │ DMs you back    │\n                  └─────────────┘   └─────────────────┘\n```\n\n### Live chat vs. agent job\n\n| Path           | When                          | What happens                                       |\n|----------------|-------------------------------|----------------------------------------------------|\n| **Live chat**  | Quick questions, small edits  | Coding agent runs now, streams to your screen      |\n| **Agent job**  | \"Build it. DM me when done.\"  | Background worker opens a PR, auto-merges, DMs you |\n\n### Two flavors of chat (`chatMode`)\n\n| `chatMode` | Repo & branch              | Use it for                                  |\n|------------|----------------------------|---------------------------------------------|\n| `agent`    | Your bot's own repo        | Talking *to* your bot — config, skills, ops |\n| `code`     | Any repo + branch you pick | Real coding sessions on a project           |\n\n### Live coding workspaces\n\nOpen a workspace from any code-mode chat and the browser attaches a terminal\nto a persistent container running your coding agent of choice. Workspace and\nchat share the same session — fire a question in chat, hop into the terminal,\nthe agent already knows what you were just talking about.\n\n### When you ask for a job\n\n```\n  you ──► chat ──► event handler ──► creates `agent-job\u002F\u003Cid>` branch\n                                              │\n                                              ▼\n                                    launches a Docker container\n                                    locally (your chosen agent)\n                                              │\n                                              ▼\n                                    agent commits, pushes,\n                                    opens a PR\n                                              │\n                                              ▼\n                                    auto-merge.yml ──► merged\n                                              │\n                                              ▼\n                                    notify-pr-complete.yml ──► DM to you\n```\n\n---\n\n## Install\n\nPrefer to follow along on video? 👇\n\n> ### 📺 \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FxmxEEAXFtm8\" target=\"_blank\" rel=\"noopener\">\u003Cstrong>Install Video (click here)\u003C\u002Fstrong>\u003C\u002Fa>\n\n### Prerequisites\n\n| Requirement | Install |\n|-------------|---------|\n| **Node.js 18+** | [nodejs.org](https:\u002F\u002Fnodejs.org) |\n| **Git** | [git-scm.com](https:\u002F\u002Fgit-scm.com) |\n| **GitHub CLI** | [cli.github.com](https:\u002F\u002Fcli.github.com) |\n| **Docker + Docker Compose** | [docker.com](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F) |\n| **ngrok*** | [ngrok.com](https:\u002F\u002Fngrok.com\u002Fdownload) (free account + authtoken) |\n\n*\\*ngrok is only needed for local installs without port forwarding. VPS\u002Fcloud deployments don't need it.*\n\n### Two steps\n\n**1. Scaffold the project.**\n\n```bash\nmkdir my-agent && cd my-agent\nnpx thepopebot@latest init\n```\n\n**2. Run the interactive setup wizard.**\n\n```bash\nnpm run setup\n```\n\nThe wizard checks prerequisites, creates a GitHub repo, generates a PAT, configures your URL, and starts Docker. Visit your APP_URL when it finishes.\n\n### After setup\n\nSign in at your APP_URL and configure these three, in order, before you can chat or run agent jobs:\n\n1. **Providers** — `\u002Fadmin\u002Fevent-handler\u002Fllms`. Add API keys for the LLM providers you want to use (Anthropic, OpenAI, Google, etc.). Everything else pulls from these credentials.\n2. **Helper LLM** — `\u002Fadmin\u002Fevent-handler\u002Fhelper-llm`. Pick provider + model for one-shot calls (chat titles, agent-job titles, PR-merge summaries). Only providers with keys from step 1 appear here.\n3. **Coding agent** — `\u002Fadmin\u002Fevent-handler\u002Fcoding-agents`. Pick which agent (Claude Code, Pi, Codex, Gemini, OpenCode, Kimi) drives live chat, code workspaces, and background agent jobs, and configure its model.\n\nOptional: connect Telegram at `\u002Fadmin\u002Fevent-handler\u002Ftelegram` to talk to your bot from your phone.\n\n> **Local installs**: your server needs to be reachable from the internet for GitHub webhooks and Telegram. Use [ngrok](https:\u002F\u002Fngrok.com) (`ngrok http 80`). If your ngrok URL changes, run `npx thepopebot set-var APP_URL \u003Cnew-url>` and re-register the Telegram webhook from `\u002Fadmin\u002Fevent-handler\u002Ftelegram`.\n\n---\n\n## Upgrade\n\n```bash\nnpx thepopebot upgrade          # latest stable\nnpx thepopebot upgrade @beta    # latest beta\nnpx thepopebot upgrade 1.2.72   # specific version\n```\n\nInstalls the new package, syncs managed files, rebuilds, restarts Docker.\n\n### What's protected, what gets updated\n\nTwo kinds of files behave differently — by design, so an upgrade never blows\naway your customizations.\n\n```\n   ┌─ Managed files ──────────────┐   ┌─ Your files ─────────────────┐\n   │  .github\u002Fworkflows\u002F          │   │  agent-job\u002FSYSTEM.md         │\n   │  docker-compose.yml          │   │  agent-job\u002FCRONS.json        │\n   │  .gitignore                  │   │  event-handler\u002FTRIGGERS.json │\n   │                              │   │  agents\u002F                     │\n   │  Always replaced with the    │   │  skills-library\u002F, skills\u002F    │\n   │  latest version on every     │   │  .env, secrets               │\n   │  init \u002F upgrade.             │   │  Never touched by upgrade.   │\n   └──────────────────────────────┘   └──────────────────────────────┘\n```\n\nSo you never lose your work — but you might miss a useful template change.\nThree commands let you pull updates in deliberately:\n\n```bash\nnpx thepopebot audit          # show what's drifted from the templates\nnpx thepopebot diff \u003Cfile>    # show the diff for one file\nnpx thepopebot reset \u003Cfile>   # replace one file with the latest template\nnpx thepopebot reset-all      # ⚠ nuclear: wipe local edits, restore everything\n```\n\nUse them when release notes mention a SYSTEM.md or workflow improvement you want.\n\n> **Upgrade failed?** See [Recovering from a Failed Upgrade](docs\u002FUPGRADE.md#recovering-from-a-failed-upgrade).\n\n---\n\n## How LLMs are wired\n\nTwo slots, you pick whether they share a model.\n\n- **Coding agent** — drives **everything you actually talk to**: live chat in the browser\u002FTelegram, code workspaces, and background agent jobs. One agent, one model. For Claude Code the chat runs in-process via the Claude Agent SDK; for any other agent (Pi, Codex, Gemini, OpenCode, Kimi) it runs in an ephemeral headless container — same chunk shape either way. Configured at `\u002Fadmin\u002Fevent-handler\u002Fcoding-agents`.\n- **Helper LLM** — small one-shot calls only: chat auto-titles, agent-job titles, PR-merge summaries. Independent provider\u002Fmodel from the coding agent. Configured at `\u002Fadmin\u002Fevent-handler\u002Fhelper-llm`.\n\nA coding-agent task can override its model per-run via `agent_backend` + `llm_model` on a cron, trigger, or chained agent job.\n\n### Using a Claude subscription\n\nIf you have Claude Pro or Max, you can power Claude Code with your subscription instead of API billing. Generate a token:\n\n```bash\nnpm install -g @anthropic-ai\u002Fclaude-code\nclaude setup-token\n```\n\nPaste it (starts with `sk-ant-oat01-`) into Admin > Event Handler > Coding Agents > Claude Code (auth mode: OAuth). The same token drives live chat *and* background agent jobs — no separate API key needed for chat. Add multiple tokens and they rotate LRU on each container launch.\n\nSee [Coding Agents](docs\u002FCODING_AGENTS.md) for details on all six agent backends.\n\n---\n\n## Connect Telegram (optional)\n\nTalk to your bot from your phone. Two steps:\n\n1. **Wire up the bot** — at `\u002Fadmin\u002Fevent-handler\u002Ftelegram`, paste the bot token from [@BotFather](https:\u002F\u002Ft.me\u002FBotFather) and click **Register webhook**.\n2. **Verify your account** — at `\u002Fprofile\u002Ftelegram`, generate a one-time code and send `\u002Fverify \u003Ccode>` to your bot. The bot only responds to verified users; unbound chats are silently dropped.\n\nOnce verified: `\u002Fsession` lists your active threads, `\u002Fsession \u003Cid>` switches the thread your messages route to. Voice notes are transcribed when an `ASSEMBLYAI_API_KEY` is set in `\u002Fadmin\u002Fevent-handler\u002Fvoice`.\n\nSee [Chat Integrations](docs\u002FCHAT_INTEGRATIONS.md) for the channel adapter pattern and how to add new channels (Slack, Discord coming soon).\n\n---\n\n## Security\n\nthepopebot includes API key authentication, webhook secret validation (fail-closed), session encryption (AES-256-GCM keyed off `AUTH_SECRET`), per-job API keys with maintenance-cron expiry, and auto-merge path restrictions. All software carries risk — thepopebot is provided as-is, and you are responsible for securing your own infrastructure. If you're running locally with a tunnel, your dev server endpoints are publicly accessible with no rate limiting and no TLS on the local hop.\n\nSee [Security](docs\u002FSECURITY.md) for full details.\n\n---\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=stephengpope\u002Fthepopebot&type=date&legend=top-left)](https:\u002F\u002Fwww.star-history.com\u002F#stephengpope\u002Fthepopebot&type=date&legend=top-left)\n\n---\n\n## Known Issues\n\n### Windows: `SQLITE_IOERR_SHMOPEN`\n\nSQLite can't create or open its shared-memory (`.shm`) file. Common causes:\n\n- **Antivirus** locking the database — add your project folder to the exclusion list\n- **Cloud-synced folders** (OneDrive, Dropbox, Google Drive) — move your project to a non-synced directory\n\n---\n\n## Docs\n\n| Document | Description |\n|----------|-------------|\n| [Architecture](docs\u002FARCHITECTURE.md) | Two-layer design, file structure, API endpoints, GitHub Actions, Docker agent |\n| [CLI Reference](docs\u002FCLI.md) | `init`, managed vs user files, template conventions, all CLI commands |\n| [Configuration](docs\u002FCONFIGURATION.md) | Admin UI, DB-backed config, infrastructure variables, Docker Compose |\n| [Customization](docs\u002FCUSTOMIZATION.md) | Personality, skills, operating system files, using your bot |\n| [Chat Integrations](docs\u002FCHAT_INTEGRATIONS.md) | Web chat, Telegram, adding new channels |\n| [Different Models](docs\u002FRUNNING_DIFFERENT_MODELS.md) | 10 built-in LLM providers, helper LLM vs coding agent split, per-job overrides, custom providers |\n| [Auto-Merge](docs\u002FAUTO_MERGE.md) | Auto-merge controls, ALLOWED_PATHS configuration |\n| [Deployment](docs\u002FDEPLOYMENT.md) | VPS setup, Docker Compose, HTTPS with Let's Encrypt |\n| [Coding Agents](docs\u002FCODING_AGENTS.md) | 6 coding agent backends, OAuth tokens, LiteLLM proxy, per-agent config |\n| [How to Build Skills](docs\u002FHOW_TO_BUILD_SKILLS.md) | Guide to building and activating agent skills |\n| [Pre-Release](docs\u002FPRE_RELEASE.md) | Installing beta\u002Falpha builds |\n| [Code Workspaces](docs\u002FCODE_WORKSPACES.md) | Interactive Docker containers with in-browser terminal |\n| [Clusters](docs\u002FCLUSTERS.md) | Agent clusters — groups of Docker containers spawned from role definitions |\n| [Hacks](docs\u002FHACKS.md) | Tips, tricks, and workarounds |\n| [Mobile Testing](docs\u002FMOBILE_TESTING.md) | Testing on mobile devices |\n| [Security](docs\u002FSECURITY.md) | Security disclaimer, local development risks |\n| [Upgrading](docs\u002FUPGRADE.md) | Automated upgrades, recovering from failed upgrades |\n\n### Maintainer\n\n| Document | Description |\n|----------|-------------|\n| [NPM](docs\u002FNPM.md) | Updating skills, versioning, and publishing releases |\n","The Pope Bot 是一个可配置的全天候自主AI代理，能够根据用户需求执行各种任务。它支持多种大型语言模型（如Anthropic、OpenAI等）和编码代理（如Claude Code、Codex等），并提供智能聊天集成（包括Telegram、即将支持Slack和Discord）、内置网页聊天功能以及实时编码工作区，允许用户在浏览器中直接打开终端并与运行中的容器连接。此外，该代理不仅能进行对话，还能编写代码、自动创建和合并拉取请求，并在完成时通过私信通知用户。由于其运行于用户的硬件上且使用个人令牌，确保了数据的安全性和隐私性。适用于需要自动化处理日常编程任务或希望拥有个性化AI助手的开发者及团队。",2,"2026-06-11 03:50:02","high_star"]