免费 / 开源由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI,token 成本极低。

sidellama is a lightweight browser-augmented chat client for open-source language models, packaged as a Chrome extension. It connects to a local Ollama or LM Studio server, or to open-source models through Groq, and lets you chat with the content of the page you are viewing plus live web search results.
| 维度 / 指标 | ![]() | |
|---|---|---|
| 官方域名 | jan.ai | chromewebstore.google.com |
| 定价模式 | 免费 | 免费 |
| 月访问量 | 29.19万 (291,894) | 0 (0) |
| 月度环比流量变化 | -3.08万 (-9.6%) | 0 (—) |
| 主要市场与份额 | 🇺🇸 美国 (23%) | 🌐 全球 (—) |
| 直接访问 / 月 | 10.56万 | 0 |
| 用户评分 | 4.6 | 4.3 |
| 支持的平台 | 网站 | 浏览器扩展 |
在你的电脑本地运行的免费开源 AI 助手
在本机下载并运行 Llama、Mistral、Qwen、Gemma、DeepSeek 等开放模型,对话数据保存在设备本地。
可选配置 OpenAI、Anthropic、Gemini、Mistral 等供应商的 API 密钥,在同一界面中调用前沿模型。
Jan 提供符合 OpenAI API 规范的本地服务端点,现有 SDK 与工具无需改代码即可对接本地模型。
可创建带独立系统指令、模型选择和参数的助手,并在多轮对话中反复使用。

sidellama is a lightweight browser-augmented chat client for open-source language models, packaged as a Chrome extension. It connects to a local Ollama or LM Studio server, or to open-source models through Groq, and lets you chat with the content of the page you are viewing plus live web search results.
Point sidellama at a local Ollama or LM Studio server, or use open-source models through Groq.
Share the text of the page you are reading, or its HTML source in development mode, with a configurable character limit.
Create and modify personal assistants with system prompts and custom instructions for different tasks.
Run asynchronous searches through DuckDuckGo or Brave and answer questions using live public data.
免费 / 开源由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI,token 成本极低。
免费 / 开源在本地或云端运行和构建开源 AI 模型

免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.
免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.
专项更强专注于文档对话与本地 RAG 工作流程,但相比 Jan,比较少着重于通用模型的调整。
免费 / 开源Acts as an open-source local AI server supporting multimodal models, though it is less established as a desktop client.
免费 / 开源Acts as an open-source local AI server supporting multimodal models, though it is less established as a desktop client.