🔥 CodebuffAI/freebuff

英文 | 简体中文

五款可用于编程、构建和研究的免费 AI 产品。 无需订阅、额度或 API key。

Freebuff 将专门化 Agent 与多款领先模型带到你的终端、桌面端、浏览器和 GitHub 仓库中。内置模型的访问由文字广告支持。

在终端中任意项目内运行 Freebuff：

npm install -g freebuff
cd ~/my-project
freebuff

然后描述你的需求。Freebuff 会找到相关文件、进行修改，并运行对项目重要的检查。

Freebuff 包含经过精选的模型目录。常规模型选择器目前提供：

尽管上游价格较高，有两项情况属于临时安排：V4 Flash 采用高级会话制，而非无限使用；DeepSeek 模型可能通过量化（Q8_0）版本提供服务以控制成本。与此同时，MiMo 2.5 可无限使用。这两项安排均计划恢复原状。

除常规模型选择器之外：

• GLM 5.2 通过可赚取的会话提供，而不是作为始终解锁的模型。
• Gemini 3.1 Flash Lite 为文件查找和研究等专门任务提供支持，而不会出现在主选择器中。

可用性和限制取决于你的访问层级、产品及当前容量。Freebuff Desktop 还可以使用你现有的服务商账户运行本地安装的 Claude Code 和 Codex Agent；这些已连接模型独立于 Freebuff 的内置模型目录。

Freebuff 使用专门化 Agent，而非将每项任务都交给同一个模型和同一套提示词。根据任务不同，Agent 会收集上下文、规划、编辑或研究、运行工具，并审查结果。

• 代码库上下文 — 文件查找 Agent 会在编辑前梳理项目中的相关部分。
• 实现与审查 — Agent 可以拆分工作、进行修改、运行命令并检查结果。
• 研究与浏览器使用 — Agent 可以调研文档，并在真实浏览器中测试应用。
• 并行本地工作 — Desktop 会将并发 Agent 隔离在不同工作区中。
• 托管环境 — Web 和 Cloud 提供沙箱、预览、终端和部署工作流。

Freebuff 在所有国家和地区均可使用。受支持地区可获得完整访问；其他地区及 VPN 用户获得受限访问，目前为每天三个、每次一小时的 MiMo 2.5 会话，最多可通过赚取方式增加至七个。

文字广告为内置模型提供支持。Freebuff 会在你开始前展示适用的会话限制，以及任何模型特定的数据使用说明。

我的数据会被用于训练 AI 吗？ 仅当模型或功能说明数据可能被用于 AI 训练时才会如此。届时，Freebuff 或服务商可能会保留提交内容，用于开发、训练、测试、评估、微调和改进 AI 模型或产品。

我的数据如何被使用和存储？ 我们使用提示词、消息、代码、文件和仓库数据来提供服务。我们可能会分析提示词和消息——包括粘贴的内容——以使用 Freebuff 系统及代表我们行事的服务提供商来个性化广告。单独上传的内容和已连接的仓库不会提供给广告服务商。在法律要求的地区，我们提供广告选择并遵守公认的退出信号；在其他地区，此类处理可能是使用免费服务的必要条件。有关保留期限和详细信息，请参阅隐私政策。

完整详情请参阅隐私政策。

Freebuff 是一个使用 Bun 构建的 TypeScript monorepo。欢迎为产品、Agent、工具、文档和底层运行时作出贡献。

本地开发需要 Docker 和已配置的 .env.local；在启动服务前，请参阅贡献指南。

git clone https://github.com/CodebuffAI/freebuff.git
cd freebuff
bun install
bun up

请单独启动 CLI：

有关环境设置以及在创建 pull request 前需要运行的检查，请参阅贡献指南、开发指南和测试指南。

Freebuff 构建于Codebuff之上，后者是为其编排、工具和 SDK 提供支持的开放式多 Agent 框架。若要创建自定义 Agent 或将其嵌入其他应用，请参阅 Codebuff 文档和@codebuff/sdk。

English | 简体中文

Five free AI products for coding, building, and research. No subscription, credits, or API key required.

Freebuff brings specialized agents and a choice of leading models to your terminal, desktop, browser, and GitHub repositories. Text ads support access to the included models.

Run Freebuff in any project from your terminal:

npm install -g freebuff
cd ~/my-project
freebuff

Then describe what you want. Freebuff finds the relevant files, makes changes, and runs the checks that matter for your project.

Freebuff includes a curated model catalog. The regular picker currently offers:

While upstream prices are high, two things are temporary : V4 Flash uses a premium session rather than being unlimited, and the DeepSeek models may serve from a quantized (Q8_0) build to keep costs down. MiMo 2.5 is unlimited in the meantime. Both are intended to be reverted.

Beyond the regular picker:

• GLM 5.2 is available through earned sessions rather than as an always-unlocked model.
• Gemini 3.1 Flash Lite powers specialist tasks such as file finding and research rather than appearing in the main picker.

Availability and limits depend on your access tier, product, and current capacity. Freebuff Desktop can also run locally installed Claude Code and Codex agents using your existing provider account; those connected models are separate from Freebuff's included catalog.

Freebuff uses specialized agents instead of sending every task through one model and one prompt. Depending on the task, agents gather context, plan, edit or research, run tools, and review the result.

• Codebase context — File-finding agents map the relevant parts of a project before editing.
• Implementation and review — Agents can divide work, make changes, run commands, and inspect the result.
• Research and browser use — Agents can investigate documentation and test applications in a real browser.
• Parallel local work — Desktop isolates concurrent agents in separate workspaces.
• Hosted environments — Web and Cloud provide sandboxes, previews, terminals, and deployment workflows.

Freebuff is available in every country. Supported regions receive full access; other regions and VPN users receive limited access, currently MiMo 2.5 with three one-hour sessions per day, earnable up to seven.

Text ads support the included models. Freebuff shows the applicable session limits and any model-specific data-use notice before you start.

Is my data used to train AI? Only when a model or feature says data may be used for AI training. Freebuff or the provider may then keep submissions to develop, train, test, evaluate, fine-tune, and improve AI models or products.

How is my data used and stored? We use prompts, messages, code, files, and repository data to provide the service. We may analyze prompts and messages—including pasted content—to personalize ads, using Freebuff systems and service providers acting on our behalf. Separate uploads and connected repositories are not provided to advertising providers. Where required by law, we provide advertising choices and honor recognized opt-out signals; elsewhere, this processing may be required to use the free service. See the Privacy Policy for retention and details.

See the Privacy Policy for complete details.

Freebuff is a TypeScript monorepo built with Bun. Contributions to the products, agents, tools, documentation, and underlying runtime are welcome.

Local development requires Docker and a configured .env.local; see the Contributing Guide before starting the services.

git clone https://github.com/CodebuffAI/freebuff.git
cd freebuff
bun install
bun up

Start the CLI separately with:

See the Contributing Guide, development guide, and testing guide for environment setup and the checks to run before opening a pull request.

Freebuff is built on Codebuff, the open multi-agent framework that powers its orchestration, tools, and SDK. To create custom agents or embed them in another application, see the Codebuff documentation and @codebuff/sdk.