AnyModelBot: an open-source, local-first personal AI assistant that keeps its memory in Markdown on your disk
Personal AI assistants are moving past "a chat box you open when you need it." The newer kind is always on: a bot with a persona, long-term memory, and the ability to keep working in the background. Grok Bot, OpenAI dots, and Claude Duet all go in this direction.
Those products run in the vendor's cloud. Your conversations, your bot's memory, and the files it works on live on someone else's servers, and you use whichever model that vendor sells.
AnyModelBot does the same job, but differently. It's an open-source (MIT), local-first personal AI assistant that runs on your own Windows, macOS, or Linux machine, or on your Docker host. It is not affiliated with any of the products above. The app is free forever. You pick models with one Modelflare API key, which gives you 70+ models on pay-per-use pricing with no subscription.
- Site: anymodel.bot
- GitHub: modelflare-ai/AnyModelBot
This post covers the design choices behind it.
!AnyModelBot — local-first personal AI assistant
1. Local-first personal bots
!AnyModelBot personas
In AnyModelBot, "bot" means a persistent persona rather than a single chat thread. You can run several of them. One might be a research assistant, another might handle writing, and a third might take care of routine chores. Each one has its own persona and its own memory, and each can run background tasks while you do something else.
"Local-first" means the bot's state lives on your machine: chats, memory, and the files it touches. The model calls still go to a hosted provider through your API key, so this is not an offline tool. The data that makes your bot yours stays with you.
That has a few practical effects:
- Ownership. You can back up, move, or delete the bot by handling a folder.
- Inspectability. You can see what the bot knows.
- No lock-in. Switching models doesn't mean leaving your history behind.
2. Memory as Markdown on disk
Many assistants store long-term memory in an opaque database or a vendor-side vector store. AnyModelBot keeps long-term memory as Markdown files on disk.
Plain text was a deliberate choice:
- You can read it. Open the memory in any editor and you see what the bot has learned about you and your projects.
- You can edit it. If a fact is wrong, fix the line. If something shouldn't be remembered, delete it.
- It works with your tools. Put it under git and you get a diff of what changed in your bot's head. Grep it, sync it, or back it up like any other notes.
- It outlives the app. Markdown will still open in 20 years.
If you already keep notes in Markdown (Obsidian, plain folders, a docs repo), your bot's memory fits into the same workflow.
3. Computer use you control
An always-on assistant is most useful when it can act: read and write files, run steps, and work through a task while you're away. It also needs guardrails, because that's where things go wrong.
AnyModelBot's computer use has two main controls:
- Workspace limits. You decide where the bot can operate. It works inside the boundaries you set, not across your whole machine.
- Confirmations. You can require explicit approval for an action before it runs.
Chats and files stay local throughout. You get an agent that does real work on your machine, and you choose how much it can do.
!More AnyModelBot personas
4. One bot, three surfaces: desktop, Docker, local web UI
People run assistants in different places, so AnyModelBot ships several surfaces for the same bot with the same memory:
- Desktop app for Windows, macOS, and Linux. Install it and talk to your bots.
- Docker for running it on a home server, NAS, or always-on box, so background tasks keep going when your laptop is closed.
- Local web UI for reaching your bot from a browser.
The bot isn't tied to one window. Run it in Docker on a small server and its memory and personas stay consistent whichever surface you use.
A note on messaging integrations: the site documents WeChat and Feishu connections, aimed mainly at users in China. For an overseas audience, the supported paths to focus on today are desktop, Docker, and the local web UI. Please don't assume other chat-app integrations are available.
5. Any model, one key
Model quality changes month to month. GPT, Claude, Gemini, Grok, DeepSeek, and others each have strengths, and the best choice for coding may not be the best for writing or cheap background tasks.
AnyModelBot connects through one Modelflare API key with access to 70+ models:
- Switch models per bot or per task without managing a separate account and key for every provider.
- Pay per use. You pay for what your bots consume, and there's no subscription.
- The app itself is free. There's no paid tier gating features.
Because memory is plain Markdown and the app is MIT-licensed, nothing about your setup depends on staying with one model vendor.
Who it's for
- Developers who want an always-on assistant but don't want their memory in someone else's cloud
- Self-hosters with a home server or Docker host
- People who want to choose their model instead of accepting a default
- Anyone who wants to read and edit what their AI remembers
What it isn't
To set expectations:
- It's not an offline/local-model product. Models are reached through your Modelflare key.
- It's not affiliated with Grok Bot, OpenAI dots, or Claude Duet. It covers a similar job, local-first and open source.
Try it
- Site and downloads: anymodel.bot
- Source (MIT): modelflare-ai/AnyModelBot
Issues, PRs, and design feedback are welcome. We're especially interested in how you'd want Markdown memory structured and what guardrails you'd expect from computer use.
Mentions
modelflare-ai/anymodelbot: 🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key.... modelflare-ai/AnyModelBot
アカウント1つで70+モデルを選べる、OSSのデスクトップAIアシスタント AnyModelBot を作った 個人開発のデスクトップ AI アシスタント AnyModelBot を紹介します。Windows / macOS / Linux 向けの MIT オープンソースアプリで、UI は日本語・英語・中国語・韓国語・ロシア語に対応しています（日本語ページ: anymodel.bot ）。最新版は v0.1.21 です。 アプリ内でアカウントにログインすると、Claude / GPT / Grok / Gemini / DeepSeek など 70以上の最新モデルを自由に選んで使えます。記憶・会話履歴・ファイル・API キーは端末内に残し、モデルはユーザーが選んだホスト型プロバイダ経由で動かす、という構成です。アプリ本体は無料で、モデル利用は月額なしの従量課金です。 なぜ作ったか モデルごとに別クライアント・別課金・別ログイン、という状態が続いていました。AnyModelBot ではアカウント1つで70以上のモデルを同じアプリから呼べ、チャット中は /model でその場で切り替えられます。 できること マルチモデル＋チャネル アカウント1つで70+モデル、/model で会話単位の切替 WeChat / Feishu（Lark） チャネル（WeChat は QR 接続、画像・ファイル対応） アプリ内ボットに加え、普段使うメッセンジャー側でも同じボットを使える ファイル・コマンド・コンピュータ操作 ワークスペースでのファイル読み書き サンドボックス内コマンド実行 コンピュータ操作（macOS は Beta） 権限は3段階（読み取り専用 / ワークスペース既定 / フルアクセス）＋危険な操作の前の承認カード Super Agent（バックグラウンド） 調査やレポートなど時間がかかる作業をバックグラウンドタスクに投げ、チャットはそのまま続けられます。一文で定期ルールも書けます。承認待ちは needs-you に集約されます。 技術スタック デスクトップ: Electron バックエンド: Node.js + TypeScript UI: Preact ストレージ: SQLite（端末内） ライセンス: MIT データの扱い 記憶・会話履歴・ファイル・API キーはユーザーの端末に保存されます Claude や GPT などのクローズドモデルは、性質上クラウド側で推論されます。モデルはユーザーが選んだホスト型プロバイダ経由で動作します 送信したプロンプトやファイル内容は、選択したモデルへ送られます ダウンロード Releases: github.com/modelflare-ai/AnyModelBot/releases リポジトリ: modelflare-ai/AnyModelBot （⭐ Star 歓迎） 日本語サイト: anymodel.bot まだ v0.1.x の新しい OSS です。機能要望やバグ報告は GitHub Issues へどうぞ。優先的に検討します: github.com/modelflare-ai/AnyModelBot/issues
【Show】AnyModelBot v0.1.18 — 1つのキーで70+モデル、日本語UI対応のオープンソース・デスクトップAIアシスタント 個人開発のデスクトップ AI アシスタント AnyModelBot の v0.1.18 をリリースしました。Windows / macOS / Linux 向けの MIT オープンソースアプリで、UI は日本語・英語・中国語・韓国語・ロシア語に対応しています（日本語ページ: anymodel.bot ）。 「チャットクライアントを自分のマシンに置き、会話・記憶・ファイル・API キーは端末内に残しつつ、モデル推論は自分で選んだホスト側プロバイダ（Modelflare ゲートウェイ）経由で使う」という構成です。アプリ本体にサブスクはありません。モデル利用は従量課金です。 !AnyModelBot デモ なぜ作ったか モデルごとに別クライアント・別課金・別ログイン、という状態が続いていました。OpenAI 互換のゲートウェイ（Modelflare）を1本通せば、GPT / Claude / Gemini / Grok / DeepSeek / Kimi / GLM など 70以上のモデルを同じアプリから呼べます。チャット中は /model でその場で切り替えられます。 !モデル切り替え できること（v0.1.18） マルチモデル＋チャネル - 1キーで70+モデル、/model で会話単位の切替 - WeChat / Feishu（飛書） チャネル（WeChat は QR 接続、画像・ファイル対応） - アプリ内ボットに加え、普段使うメッセンジャー側でも同じボットを使える !WeChat チャネル ファイル・コマンド・コンピュータ操作 - ワークスペースでのファイル読み書き - サンドボックス内コマンド実行 - コンピュータ操作（macOS は Beta） - 権限は3段階（読み取り専用 / ワークスペース既定 / フルアクセス）＋承認カード !ファイル操作 !コンピュータ操作 Super Agent（バックグラウンド） 調査やレポートなど時間がかかる作業をバックグラウンドタスクに投げ、チャットはそのまま続けられます。一文言って定期ルールを書けます。承認待ちは needs-you に集約されます。 データの扱い（正直に） - 会話・記憶・ファイル・API キーはユーザーの端末に保存されます - モデル推論は、ユーザーが選んだホスト側プロバイダ（Modelflare）経由です。オフライン専用のローカルLLMアプリではありません - 送信したプロンプト・ファイル内容・スクリーンショット等は、選択したモデルベンダーへ転送されます - アプリは無料（MIT）。モデルは従量課金。AnyModelBot 自体の月額サブスクはありません ダウンロード - Releases v0.1.18: github.com/modelflare-ai/AnyModelBot/releases/tag… - リポジトリ: modelflare-ai/AnyModelBot （⭐ Star 歓迎） - 日本語サイト: anymodel.bot 正直な注意 プロジェクトはまだ v0.1.x の新しい独立 OSS です。ネイティブのスマホアプリやクラウドWeb版はありません。macOS のコンピュータ操作は Beta です。 お問い合わせ: magnus@anymodel.bot / support@anymodel.bot
把不同模型的 Agent 拉进一个群，最该盯的不是谁更会说，而是谁接手、记忆怎么分、钱算给谁。 AnyModelBot 这次的群聊更新挺具体：机器人能互相 @ 交接，各自保留模型、工作区和记忆，费用也分开记。 modelflare-ai/AnyModelBot 它是本地优先的开源助手，能从微信、飞书接任务，在后台执行命令；默认写出工作区要审批，任务有预算。比起又接了多少模型，这些边界更值得看。但本地优先不等于离线，模型请求仍经 Modelflare 转发。
AnyModelBot: tu asistente personal open source en tu PC, con memoria en Markdown y 70+ modelos con una sola llave. App gratis, pagas por uso. ¿Qué bot armas primero? modelflare-ai/AnyModelBot
Idéal pour automatiser des workflows desktop sans abonnement cloud, malgré une dépendance critique sur la latence des API de routage. 🔗 modelflare-ai/AnyModelBot
做了一个 AI Bot 的开源项目，欢迎大家体验 最近 xAI 、OpenAI 、Anthropic 都在做常驻的个人智能体：它在后台替你盯事，要拍板时再来问你。那些产品绑死一家模型和一份订阅，电脑还在人家云上。 我们做了另一个：AnyModelBot。MIT 开源，跑在你自己的 Windows 、macOS 、Linux 上，也可以丢进 Docker 。当前版本 v0.1.16 。 一个机器人就是一段人设，外加它自己的模型、工作区和记忆。六个毛绒头像只是长相，天天、闪闪、芽芽、哒哒、晶晶、飞飞不代表固定岗位，名字和职责都由你写。想养几个养几个，互不串记忆。 它能做的事 - 读写文件、跑命令。 默认只写自己的工作区，越界会停下来等你点头。权限分只读、工作区和完全权限三档，递归删除即使在完全权限下也会再问一次。 - 操作电脑。 看屏幕、开应用、点击、输入。模型只能用 24 个动作，脚本执行和结束进程对它不可见。默认自动做，也可以改成改界面之前先问。macOS 上这块还是 Beta 。 - 本地记忆。 记忆是硬盘上的 Markdown ，任何编辑器都能打开。看着像密码、密钥、证件号的内容会拒存。对话在本地 SQLite 里。 - 后台任务和定时规则。 比如「每天早上 8 点看一下，有情况再告诉我」。可以先观察、不发消息。任务默认预算 1 美元，规则每次 0.1 美元、每月 3 美元，快用完会停下来问你。 - 接入聊天软件。 微信、飞书、Telegram 、Slack 、Discord 里都能找到同一个机器人。微信能收发图片和文件。没有单独的 iOS / Android App ，手机上走这些聊天软件。 - 连接已有工具。 授权之后可以读你的 Notion （能读能写，不能删页面）和飞书消息（只读）。 模型和费用 模型全部来自 Modelflare ，一个账号里换 GPT 、Claude 、Gemini 、Grok 、DeepSeek 、Kimi 、GLM 等，文本、图片、视频都有。 App 没有月费，按 token 从余额扣。余额、每日用量、每个机器人的花费上限都在应用里。国际线路和中国大陆优化线路自己选，不会自动切。 几件用之前最好知道的事 - 不能离线，也不接本地模型。 - 你发给模型的内容会离开这台电脑，包括电脑操作时的屏幕。对话、记忆、文件和 Key 留在本机。Key 不进智能体子进程，界面只显示末 4 位。本地控制台只听 127.0.0.1，Docker 必须带访问令牌，别把 3600 端口直接开到公网。 - 微信有平台限制：你每发一条，之后 24 小时内它最多回 10 条。主动消息还有每日上限。飞书目前只处理单聊。 - 关窗口会留在托盘，电脑关机或休眠它就不在了，要 24 小时在线用 Docker 。 - 界面有简体中文和英文。安装包如果被系统拦住：macOS 到「隐私与安全性」里允许，Windows 选「仍要运行」，Linux 先 chmod +x。下载页有 SHA-256 。 Docker 部署 docker run -d --name amb -p 3600:3600 -v amb-data:/data ghcr.io/modelflare-ai/anymodel-bot docker exec amb cat /data/ui-token 然后打开 http://<主机>:3600/?token=<令牌>。 相关链接 - [官网]( anymodel.bot) - [下载]( anymodel.bot) - [源码]( modelflare-ai/AnyModelBot) - [安全说明]( anymodel.bot) - [价格]( modelflare.dev) 欢迎拍。踩过的坑、缺的渠道、电脑操作不敢开的理由，都可以直接说。
🚀 Trending on GitHub AnyModelBot by modelflare-ai ⭐ 751 🧠 A free, open-source AI agent you run on your own computer that works with any model (GPT, Claude, Gemini, DeepSeek and more) to handle tasks for you. modelflare-ai/AnyModelBot #GenAI #OpenSource #AI
把 DeepSeek 的 Super-agent 思路做成一个人的桌面助手： AnyModelBot，首个开箱即用的 DeepSeek Super Agent DeepSeek 前阵子开源了 [dsh-superagent 原型]( deepseek-ai/dsh-superagent-prototype)，核心原则就一句：占用尽量少的注意力，带来尽量多的价值。 不过它是面向团队、盯着 GitHub 仓库的研究原型，个人没法直接用。 我们把这套思路做进了开源桌面助手 AnyModelBot，装好就是开箱即用的 DeepSeek Super Agent ，这是它的首个实现，不需要任何配置。  Super Agent 三件套 - 后台任务：调研、做报告这类要跑一阵子的事，交代一句就在后台做，聊天照常，不用排队等。 - 定时规则：一句话写下长期吩咐，比如「每天早上 8 点看看 X 的价格，低于 200 告诉我」，按时自动执行。新规则可以先用「观察」模式试跑，只读、不打扰你。 - 「需要你」：所有等你回答、批准的事集中在一处，没事时不占地方。 不打扰是硬规矩：只推结果、决定和失败三种消息，默认 22:00–08:00 免打扰，每个任务和规则都有预算上限。  它本来就是一个完整的 AI 机器人 - 一个账号 70+ 模型：GPT 、Claude 、Gemini 、Grok 、DeepSeek 、Kimi 、GLM……每个对话用 /model 随时切换。  - 在微信和飞书里也能用：微信扫码连接，支持图片和文件；飞书是流式回复卡片。  - 能操作你的电脑：读写文件、沙箱执行命令、电脑操作（ macOS 为 Beta ），三档权限加审批卡片，你说了算。  - 本地优先、开源免费：对话、记忆、文件和 Key 都留在你的电脑上； MIT 开源，Windows / macOS / Linux / Docker 都能跑，模型按量付费、没有订阅。 想深入看 设计细节（和原型的差别、DeepSeek Harness 怎么跑、权限和预算怎么设计）都写在 GitHub 的设计文档里，功能介绍和下载在官网： - GitHub： modelflare-ai/AnyModelBot （欢迎 Star ⭐） - Super Agent 设计文档： github.com/modelflare-ai/AnyModelBot/blob/master/… - 官网： anymodel.bot 项目还很新（ v0.1.x ），是独立开源项目，与 DeepSeek 官方无关。欢迎试用、提 issue 、拍砖 🙏
AnyModelBot: an open-source, local-first personal AI assistant that keeps its memory in Markdown on your disk Personal AI assistants are moving past "a chat box you open when you need it." The newer kind is always on: a bot with a persona, long-term memory, and the ability to keep working in the background. Grok Bot, OpenAI dots, and Claude Duet all go in this direction. Those products run in the vendor's cloud. Your conversations, your bot's memory, and the files it works on live on someone else's servers, and you use whichever model that vendor sells. AnyModelBot does the same job, but differently. It's an open-source (MIT), local-first personal AI assistant that runs on your own Windows, macOS, or Linux machine, or on your Docker host. It is not affiliated with any of the products above. The app is free forever. You pick models with one Modelflare API key, which gives you 70+ models on pay-per-use pricing with no subscription. - Site: anymodel.bot - GitHub: modelflare-ai/AnyModelBot This post covers the design choices behind it. !AnyModelBot — local-first personal AI assistant 1. Local-first personal bots !AnyModelBot personas In AnyModelBot, "bot" means a persistent persona rather than a single chat thread. You can run several of them. One might be a research assistant, another might handle writing, and a third might take care of routine chores. Each one has its own persona and its own memory, and each can run background tasks while you do something else. "Local-first" means the bot's state lives on your machine: chats, memory, and the files it touches. The model calls still go to a hosted provider through your API key, so this is not an offline tool. The data that makes your bot yours stays with you. That has a few practical effects: - Ownership. You can back up, move, or delete the bot by handling a folder. - Inspectability. You can see what the bot knows. - No lock-in. Switching models doesn't mean leaving your history behind. 2. Memory as Markdown on disk Many assistants store long-term memory in an opaque database or a vendor-side vector store. AnyModelBot keeps long-term memory as Markdown files on disk. Plain text was a deliberate choice: - You can read it. Open the memory in any editor and you see what the bot has learned about you and your projects. - You can edit it. If a fact is wrong, fix the line. If something shouldn't be remembered, delete it. - It works with your tools. Put it under git and you get a diff of what changed in your bot's head. Grep it, sync it, or back it up like any other notes. - It outlives the app. Markdown will still open in 20 years. If you already keep notes in Markdown (Obsidian, plain folders, a docs repo), your bot's memory fits into the same workflow. 3. Computer use you control An always-on assistant is most useful when it can act: read and write files, run steps, and work through a task while you're away. It also needs guardrails, because that's where things go wrong. AnyModelBot's computer use has two main controls: - Workspace limits. You decide where the bot can operate. It works inside the boundaries you set, not across your whole machine. - Confirmations. You can require explicit approval for an action before it runs. Chats and files stay local throughout. You get an agent that does real work on your machine, and you choose how much it can do. !More AnyModelBot personas 4. One bot, three surfaces: desktop, Docker, local web UI People run assistants in different places, so AnyModelBot ships several surfaces for the same bot with the same memory: - Desktop app for Windows, macOS, and Linux. Install it and talk to your bots. - Docker for running it on a home server, NAS, or always-on box, so background tasks keep going when your laptop is closed. - Local web UI for reaching your bot from a browser. The bot isn't tied to one window. Run it in Docker on a small server and its memory and personas stay consistent whichever surface you use. A note on messaging integrations: the site documents WeChat and Feishu connections, aimed mainly at users in China. For an overseas audience, the supported paths to focus on today are desktop, Docker, and the local web UI. Please don't assume other chat-app integrations are available. 5. Any model, one key Model quality changes month to month. GPT, Claude, Gemini, Grok, DeepSeek, and others each have strengths, and the best choice for coding may not be the best for writing or cheap background tasks. AnyModelBot connects through one Modelflare API key with access to 70+ models: - Switch models per bot or per task without managing a separate account and key for every provider. - Pay per use. You pay for what your bots consume, and there's no subscription. - The app itself is free. There's no paid tier gating features. Because memory is plain Markdown and the app is MIT-licensed, nothing about your setup depends on staying with one model vendor. Who it's for - Developers who want an always-on assistant but don't want their memory in someone else's cloud - Self-hosters with a home server or Docker host - People who want to choose their model instead of accepting a default - Anyone who wants to read and edit what their AI remembers What it isn't To set expectations: - It's not an offline/local-model product. Models are reached through your Modelflare key. - It's not affiliated with Grok Bot, OpenAI dots, or Claude Duet. It covers a similar job, local-first and open source. Try it - Site and downloads: anymodel.bot - Source (MIT): modelflare-ai/AnyModelBot Issues, PRs, and design feedback are welcome. We're especially interested in how you'd want Markdown memory structured and what guardrails you'd expect from computer use.