[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-openinterpreter--open-interpreter":3,"tool-openinterpreter--open-interpreter":64},[4,17,25,39,48,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,14,15],"开发框架","Agent","语言模型","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":10,"last_commit_at":23,"category_tags":24,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,15],{"id":26,"name":27,"github_repo":28,"description_zh":29,"stars":30,"difficulty_score":10,"last_commit_at":31,"category_tags":32,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[33,34,35,36,14,37,15,13,38],"图像","数据工具","视频","插件","其他","音频",{"id":40,"name":41,"github_repo":42,"description_zh":43,"stars":44,"difficulty_score":45,"last_commit_at":46,"category_tags":47,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,3,"2026-04-04T04:44:48",[14,33,13,15,37],{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":45,"last_commit_at":54,"category_tags":55,"status":16},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74913,"2026-04-05T10:44:17",[15,33,13,37],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":45,"last_commit_at":62,"category_tags":63,"status":16},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[15,14,13,36],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":99,"forks":100,"last_commit_at":101,"license":102,"difficulty_score":10,"env_os":103,"env_gpu":104,"env_ram":105,"env_deps":106,"category_tags":113,"github_topics":114,"view_count":121,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":122,"updated_at":123,"faqs":124,"releases":125},2114,"openinterpreter\u002Fopen-interpreter","open-interpreter","A natural language interface for computers","Open Interpreter 是一款让大型语言模型（LLM）直接在您的本地计算机上运行代码的开源工具。它通过终端提供一个类似 ChatGPT 的对话界面，让您能用自然语言指挥电脑完成复杂任务，例如处理图片和视频、控制浏览器进行调研、或分析大规模数据集。\n\n这款工具主要解决了云端代码解释器的诸多限制。相比于受限于网络隔离、预装包较少且有时长约束的云端服务，Open Interpreter 在本地运行，拥有完整的互联网访问权限，不受运行时间和文件大小限制，并能调用您系统中已安装的任何软件库。此外，它在执行任何代码前都会请求用户确认，确保了操作的安全性与可控性。\n\nOpen Interpreter 特别适合开发者、数据分析师及研究人员使用，能极大提升自动化脚本编写和数据处理的效率；同时，对于希望用自然语言直接操控电脑功能的进阶普通用户，它也是一个强大的助手。其核心技术亮点在于将大模型的推理能力与本地环境的无限扩展性完美结合，既保留了 AI 的智能，又突破了沙箱环境的束缚，让 AI 真正成为您电脑的全能助手。","\u003Ch1 align=\"center\">● Open Interpreter\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FHvz9Axh84z\">\n        \u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1146610656779440188?logo=discord&style=flat&logoColor=white\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_JA.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fドキュメント-日本語-white.svg\" alt=\"JA doc\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_ZH.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F文档-中文版-white.svg\" alt=\"ZH doc\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_ES.md\"> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEspañol-white.svg\" alt=\"ES doc\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_UK.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FУкраїнська-white.svg\" alt=\"UK doc\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_IN.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHindi-white.svg\" alt=\"IN doc\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=license&message=AGPL&color=white&style=flat\" alt=\"License\"\u002F>\u003C\u002Fa>\n    \u003Cbr>\n    \u003Cbr>\u003Ca href=\"https:\u002F\u002F0ggfznkwh4j.typeform.com\u002Fto\u002FG21i9lJ2\">Get early access to the desktop app\u003C\u002Fa>‎ ‎ |‎ ‎ \u003Ca href=\"https:\u002F\u002Fdocs.openinterpreter.com\u002F\">Documentation\u003C\u002Fa>\u003Cbr>\n\u003C\u002Fp>\n\n\u003Cbr>\n\n\u003Cimg alt=\"local_explorer\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fopeninterpreter_open-interpreter_readme_b0263e9e59a1.png\">\n\n\u003Cbr>\n\u003C\u002Fp>\n\u003Cbr>\n\n**Open Interpreter** lets LLMs run code (Python, Javascript, Shell, and more) locally. You can chat with Open Interpreter through a ChatGPT-like interface in your terminal by running `$ interpreter` after installing.\n\nThis provides a natural-language interface to your computer's general-purpose capabilities:\n\n- Create and edit photos, videos, PDFs, etc.\n- Control a Chrome browser to perform research\n- Plot, clean, and analyze large datasets\n- ...etc.\n\n**⚠️ Note: You'll be asked to approve code before it's run.**\n\n\u003Cbr>\n\n## Demo\n\nhttps:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fassets\u002F63927363\u002F37152071-680d-4423-9af3-64836a6f7b60\n\n#### An interactive demo is also available on Google Colab:\n\n[![Open In Colab](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1WKmRXZgsErej2xUriKzxrEAXdxMSgWbb?usp=sharing)\n\n#### Along with an example voice interface, inspired by _Her_:\n\n[![Open In Colab](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1NojYGHDgxH6Y1G1oxThEBBb2AtyODBIK)\n\n## Quick Start\n\n\n### Install\n\n```shell\npip install git+https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter.git\n```\n\n> Not working? Read our [setup guide](https:\u002F\u002Fdocs.openinterpreter.com\u002Fgetting-started\u002Fsetup).\n\n### Terminal\n\nAfter installation, simply run `interpreter`:\n\n```shell\ninterpreter\n```\n\n### Python\n\n```python\nfrom interpreter import interpreter\n\ninterpreter.chat(\"Plot AAPL and META's normalized stock prices\") # Executes a single command\ninterpreter.chat() # Starts an interactive chat\n```\n\n### GitHub Codespaces\n\nPress the `,` key on this repository's GitHub page to create a codespace. After a moment, you'll receive a cloud virtual machine environment pre-installed with open-interpreter. You can then start interacting with it directly and freely confirm its execution of system commands without worrying about damaging the system.\n\n## Comparison to ChatGPT's Code Interpreter\n\nOpenAI's release of [Code Interpreter](https:\u002F\u002Fopenai.com\u002Fblog\u002Fchatgpt-plugins#code-interpreter) with GPT-4 presents a fantastic opportunity to accomplish real-world tasks with ChatGPT.\n\nHowever, OpenAI's service is hosted, closed-source, and heavily restricted:\n\n- No internet access.\n- [Limited set of pre-installed packages](https:\u002F\u002Fwfhbrian.com\u002Fmastering-chatgpts-code-interpreter-list-of-python-packages\u002F).\n- 100 MB maximum upload, 120.0 second runtime limit.\n- State is cleared (along with any generated files or links) when the environment dies.\n\n---\n\nOpen Interpreter overcomes these limitations by running in your local environment. It has full access to the internet, isn't restricted by time or file size, and can utilize any package or library.\n\nThis combines the power of GPT-4's Code Interpreter with the flexibility of your local development environment.\n\n## Commands\n\n**Update:** The Generator Update (0.1.5) introduced streaming:\n\n```python\nmessage = \"What operating system are we on?\"\n\nfor chunk in interpreter.chat(message, display=False, stream=True):\n  print(chunk)\n```\n\n### Interactive Chat\n\nTo start an interactive chat in your terminal, either run `interpreter` from the command line:\n\n```shell\ninterpreter\n```\n\nOr `interpreter.chat()` from a .py file:\n\n```python\ninterpreter.chat()\n```\n\n**You can also stream each chunk:**\n\n```python\nmessage = \"What operating system are we on?\"\n\nfor chunk in interpreter.chat(message, display=False, stream=True):\n  print(chunk)\n```\n\n### Programmatic Chat\n\nFor more precise control, you can pass messages directly to `.chat(message)`:\n\n```python\ninterpreter.chat(\"Add subtitles to all videos in \u002Fvideos.\")\n\n# ... Streams output to your terminal, completes task ...\n\ninterpreter.chat(\"These look great but can you make the subtitles bigger?\")\n\n# ...\n```\n\n### Start a New Chat\n\nIn Python, Open Interpreter remembers conversation history. If you want to start fresh, you can reset it:\n\n```python\ninterpreter.messages = []\n```\n\n### Save and Restore Chats\n\n`interpreter.chat()` returns a List of messages, which can be used to resume a conversation with `interpreter.messages = messages`:\n\n```python\nmessages = interpreter.chat(\"My name is Killian.\") # Save messages to 'messages'\ninterpreter.messages = [] # Reset interpreter (\"Killian\" will be forgotten)\n\ninterpreter.messages = messages # Resume chat from 'messages' (\"Killian\" will be remembered)\n```\n\n### Customize System Message\n\nYou can inspect and configure Open Interpreter's system message to extend its functionality, modify permissions, or give it more context.\n\n```python\ninterpreter.system_message += \"\"\"\nRun shell commands with -y so the user doesn't have to confirm them.\n\"\"\"\nprint(interpreter.system_message)\n```\n\n### Change your Language Model\n\nOpen Interpreter uses [LiteLLM](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fproviders\u002F) to connect to hosted language models.\n\nYou can change the model by setting the model parameter:\n\n```shell\ninterpreter --model gpt-3.5-turbo\ninterpreter --model claude-2\ninterpreter --model command-nightly\n```\n\nIn Python, set the model on the object:\n\n```python\ninterpreter.llm.model = \"gpt-3.5-turbo\"\n```\n\n[Find the appropriate \"model\" string for your language model here.](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fproviders\u002F)\n\n### Running Open Interpreter locally\n\n#### Terminal\n\nOpen Interpreter can use OpenAI-compatible server to run models locally. (LM Studio, jan.ai, ollama etc)\n\nSimply run `interpreter` with the api_base URL of your inference server (for LM studio it is `http:\u002F\u002Flocalhost:1234\u002Fv1` by default):\n\n```shell\ninterpreter --api_base \"http:\u002F\u002Flocalhost:1234\u002Fv1\" --api_key \"fake_key\"\n```\n\nAlternatively you can use Llamafile without installing any third party software just by running\n\n```shell\ninterpreter --local\n```\n\nfor a more detailed guide check out [this video by Mike Bird](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CEs51hGWuGU?si=cN7f6QhfT4edfG5H)\n\n**How to run LM Studio in the background.**\n\n1. Download [https:\u002F\u002Flmstudio.ai\u002F](https:\u002F\u002Flmstudio.ai\u002F) then start it.\n2. Select a model then click **↓ Download**.\n3. Click the **↔️** button on the left (below 💬).\n4. Select your model at the top, then click **Start Server**.\n\nOnce the server is running, you can begin your conversation with Open Interpreter.\n\n> **Note:** Local mode sets your `context_window` to 3000, and your `max_tokens` to 1000. If your model has different requirements, set these parameters manually (see below).\n\n#### Python\n\nOur Python package gives you more control over each setting. To replicate and connect to LM Studio, use these settings:\n\n```python\nfrom interpreter import interpreter\n\ninterpreter.offline = True # Disables online features like Open Procedures\ninterpreter.llm.model = \"openai\u002Fx\" # Tells OI to send messages in OpenAI's format\ninterpreter.llm.api_key = \"fake_key\" # LiteLLM, which we use to talk to LM Studio, requires this\ninterpreter.llm.api_base = \"http:\u002F\u002Flocalhost:1234\u002Fv1\" # Point this at any OpenAI compatible server\n\ninterpreter.chat()\n```\n\n#### Context Window, Max Tokens\n\nYou can modify the `max_tokens` and `context_window` (in tokens) of locally running models.\n\nFor local mode, smaller context windows will use less RAM, so we recommend trying a much shorter window (~1000) if it's failing \u002F if it's slow. Make sure `max_tokens` is less than `context_window`.\n\n```shell\ninterpreter --local --max_tokens 1000 --context_window 3000\n```\n\n### Verbose mode\n\nTo help you inspect Open Interpreter we have a `--verbose` mode for debugging.\n\nYou can activate verbose mode by using its flag (`interpreter --verbose`), or mid-chat:\n\n```shell\n$ interpreter\n...\n> %verbose true \u003C- Turns on verbose mode\n\n> %verbose false \u003C- Turns off verbose mode\n```\n\n### Interactive Mode Commands\n\nIn the interactive mode, you can use the below commands to enhance your experience. Here's a list of available commands:\n\n**Available Commands:**\n\n- `%verbose [true\u002Ffalse]`: Toggle verbose mode. Without arguments or with `true` it\n  enters verbose mode. With `false` it exits verbose mode.\n- `%reset`: Resets the current session's conversation.\n- `%undo`: Removes the previous user message and the AI's response from the message history.\n- `%tokens [prompt]`: (_Experimental_) Calculate the tokens that will be sent with the next prompt as context and estimate their cost. Optionally calculate the tokens and estimated cost of a `prompt` if one is provided. Relies on [LiteLLM's `cost_per_token()` method](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fcompletion\u002Ftoken_usage#2-cost_per_token) for estimated costs.\n- `%help`: Show the help message.\n\n### Configuration \u002F Profiles\n\nOpen Interpreter allows you to set default behaviors using `yaml` files.\n\nThis provides a flexible way to configure the interpreter without changing command-line arguments every time.\n\nRun the following command to open the profiles directory:\n\n```\ninterpreter --profiles\n```\n\nYou can add `yaml` files there. The default profile is named `default.yaml`.\n\n#### Multiple Profiles\n\nOpen Interpreter supports multiple `yaml` files, allowing you to easily switch between configurations:\n\n```\ninterpreter --profile my_profile.yaml\n```\n\n## Sample FastAPI Server\n\nThe generator update enables Open Interpreter to be controlled via HTTP REST endpoints:\n\n```python\n# server.py\n\nfrom fastapi import FastAPI\nfrom fastapi.responses import StreamingResponse\nfrom interpreter import interpreter\n\napp = FastAPI()\n\n@app.get(\"\u002Fchat\")\ndef chat_endpoint(message: str):\n    def event_stream():\n        for result in interpreter.chat(message, stream=True):\n            yield f\"data: {result}\\n\\n\"\n\n    return StreamingResponse(event_stream(), media_type=\"text\u002Fevent-stream\")\n\n@app.get(\"\u002Fhistory\")\ndef history_endpoint():\n    return interpreter.messages\n```\n\n```shell\npip install fastapi uvicorn\nuvicorn server:app --reload\n```\n\nYou can also start a server identical to the one above by simply running `interpreter.server()`.\n\n## Android\n\nThe step-by-step guide for installing Open Interpreter on your Android device can be found in the [open-interpreter-termux repo](https:\u002F\u002Fgithub.com\u002FMikeBirdTech\u002Fopen-interpreter-termux).\n\n## Safety Notice\n\nSince generated code is executed in your local environment, it can interact with your files and system settings, potentially leading to unexpected outcomes like data loss or security risks.\n\n**⚠️ Open Interpreter will ask for user confirmation before executing code.**\n\nYou can run `interpreter -y` or set `interpreter.auto_run = True` to bypass this confirmation, in which case:\n\n- Be cautious when requesting commands that modify files or system settings.\n- Watch Open Interpreter like a self-driving car, and be prepared to end the process by closing your terminal.\n- Consider running Open Interpreter in a restricted environment like Google Colab or Replit. These environments are more isolated, reducing the risks of executing arbitrary code.\n\nThere is **experimental** support for a [safe mode](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FSAFE_MODE.md) to help mitigate some risks.\n\n## How Does it Work?\n\nOpen Interpreter equips a [function-calling language model](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Fgpt\u002Ffunction-calling) with an `exec()` function, which accepts a `language` (like \"Python\" or \"JavaScript\") and `code` to run.\n\nWe then stream the model's messages, code, and your system's outputs to the terminal as Markdown.\n\n# Access Documentation Offline\n\nThe full [documentation](https:\u002F\u002Fdocs.openinterpreter.com\u002F) is accessible on-the-go without the need for an internet connection.\n\n[Node](https:\u002F\u002Fnodejs.org\u002Fen) is a pre-requisite:\n\n- Version 18.17.0 or any later 18.x.x version.\n- Version 20.3.0 or any later 20.x.x version.\n- Any version starting from 21.0.0 onwards, with no upper limit specified.\n\nInstall [Mintlify](https:\u002F\u002Fmintlify.com\u002F):\n\n```bash\nnpm i -g mintlify@latest\n```\n\nChange into the docs directory and run the appropriate command:\n\n```bash\n# Assuming you're at the project's root directory\ncd .\u002Fdocs\n\n# Run the documentation server\nmintlify dev\n```\n\nA new browser window should open. The documentation will be available at [http:\u002F\u002Flocalhost:3000](http:\u002F\u002Flocalhost:3000) as long as the documentation server is running.\n\n# Contributing\n\nThank you for your interest in contributing! We welcome involvement from the community.\n\nPlease see our [contributing guidelines](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FCONTRIBUTING.md) for more details on how to get involved.\n\n# Roadmap\n\nVisit [our roadmap](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FROADMAP.md) to preview the future of Open Interpreter.\n\n**Note**: This software is not affiliated with OpenAI.\n\n![thumbnail-ncu](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fopeninterpreter_open-interpreter_readme_4fd87f816bb6.png)\n\n> Having access to a junior programmer working at the speed of your fingertips ... can make new workflows effortless and efficient, as well as open the benefits of programming to new audiences.\n>\n> — _OpenAI's Code Interpreter Release_\n\n\u003Cbr>\n","\u003Ch1 align=\"center\">● 开放解释器\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FHvz9Axh84z\">\n        \u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1146610656779440188?logo=discord&style=flat&logoColor=white\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_JA.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fドキュメント-日本語-white.svg\" alt=\"日文文档\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_ZH.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F文档-中文版-white.svg\" alt=\"中文文档\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_ES.md\"> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEspañol-white.svg\" alt=\"西班牙文文档\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_UK.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FУкраїнська-white.svg\" alt=\"乌克兰文文档\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"docs\u002FREADME_IN.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHindi-white.svg\" alt=\"印地语文档\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=license&message=AGPL&color=white&style=flat\" alt=\"许可证\"\u002F>\u003C\u002Fa>\n    \u003Cbr>\n    \u003Cbr>\u003Ca href=\"https:\u002F\u002F0ggfznkwh4j.typeform.com\u002Fto\u002FG21i9lJ2\">抢先体验桌面应用\u003C\u002Fa>‎ ‎ |‎ ‎ \u003Ca href=\"https:\u002F\u002Fdocs.openinterpreter.com\u002F\">文档\u003C\u002Fa>\u003Cbr>\n\u003C\u002Fp>\n\n\u003Cbr>\n\n\u003Cimg alt=\"local_explorer\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fopeninterpreter_open-interpreter_readme_b0263e9e59a1.png\">\n\n\u003Cbr>\n\u003C\u002Fp>\n\u003Cbr>\n\n**Open Interpreter** 允许大型语言模型在本地运行代码（Python、Javascript、Shell 等）。安装后，您只需在终端中运行 `$ interpreter`，即可通过类似 ChatGPT 的界面与 Open Interpreter 交流。\n\n这为您的计算机的通用功能提供了一个自然语言接口：\n\n- 创建和编辑照片、视频、PDF 等文件。\n- 控制 Chrome 浏览器进行研究。\n- 绘制、清洗和分析大型数据集。\n- …等等。\n\n**⚠️ 注意：在代码执行前，系统会要求您批准。**\n\n\u003Cbr>\n\n## 演示\n\nhttps:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fassets\u002F63927363\u002F37152071-680d-4423-9af3-64836a6f7b60\n\n#### Google Colab 上也有一个交互式演示：\n\n[![在 Colab 中打开](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1WKmRXZgsErej2xUriKzxrEAXdxMSgWbb?usp=sharing)\n\n#### 还有一个受电影《她》启发的语音交互示例：\n\n[![在 Colab 中打开](https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1NojYGHDgxH6Y1G1oxThEBBb2AtyODBIK)\n\n## 快速开始\n\n\n### 安装\n\n```shell\npip install git+https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter.git\n```\n\n> 如果无法正常工作？请阅读我们的 [设置指南](https:\u002F\u002Fdocs.openinterpreter.com\u002Fgetting-started\u002Fsetup)。\n\n### 终端\n\n安装完成后，只需运行 `interpreter`：\n\n```shell\ninterpreter\n```\n\n### Python\n\n```python\nfrom interpreter import interpreter\n\ninterpreter.chat(\"绘制 AAPL 和 META 的归一化股价\") # 执行单个命令\ninterpreter.chat() # 启动交互式对话\n```\n\n### GitHub Codespaces\n\n在本仓库的 GitHub 页面上按下 `,` 键即可创建一个 codespace。片刻之后，您将获得一个预装了 open-interpreter 的云端虚拟机环境。您可以直接与其互动，并自由确认其执行系统命令的过程，而无需担心对系统造成损害。\n\n## 与 ChatGPT 的 Code Interpreter 对比\n\nOpenAI 随 GPT-4 推出的 [Code Interpreter](https:\u002F\u002Fopenai.com\u002Fblog\u002Fchatgpt-plugins#code-interpreter) 为使用 ChatGPT 完成实际任务提供了绝佳机会。\n\n然而，OpenAI 的服务是托管的、闭源的，并且受到严格限制：\n\n- 无互联网访问权限。\n- [预装软件包有限](https:\u002F\u002Fwfhbrian.com\u002Fmastering-chatgpts-code-interpreter-list-of-python-packages\u002F)。\n- 最大上传文件大小为 100 MB，运行时长上限为 120 秒。\n- 当环境关闭时，状态（包括生成的文件和链接）会被清除。\n\n---\n\nOpen Interpreter 则通过在您的本地环境中运行来克服这些限制。它拥有完全的互联网访问权限，不受时间和文件大小的限制，并且可以使用任何软件包或库。\n\n这将 GPT-4 的 Code Interpreter 的强大功能与您本地开发环境的灵活性相结合。\n\n## 命令\n\n**更新：** Generator Update (0.1.5) 引入了流式传输：\n\n```python\nmessage = \"我们当前使用的操作系统是什么？\"\n\nfor chunk in interpreter.chat(message, display=False, stream=True):\n  print(chunk)\n```\n\n### 交互式对话\n\n要在终端中启动交互式对话，您可以从命令行运行 `interpreter`：\n\n```shell\ninterpreter\n```\n\n或者从 .py 文件中调用 `interpreter.chat()`：\n\n```python\ninterpreter.chat()\n```\n\n**您也可以逐块流式输出：**\n\n```python\nmessage = \"我们当前使用的操作系统是什么？\"\n\nfor chunk in interpreter.chat(message, display=False，stream=True):\n  print(chunk)\n```\n\n### 编程式对话\n\n为了更精确地控制，您可以直接将消息传递给 `.chat(message)`：\n\n```python\ninterpreter.chat(\"为 \u002Fvideos 目录下的所有视频添加字幕。\")\n\n# ... 将输出流式传输到终端，完成任务 ...\n\ninterpreter.chat(\"这些看起来很棒，但你能把字幕再放大一点吗？\")\n\n# ...\n```\n\n### 开始新对话\n\n在 Python 中，Open Interpreter 会记住对话历史。如果您想从头开始，可以将其重置：\n\n```python\ninterpreter.messages = []\n```\n\n### 保存和恢复对话\n\n`interpreter.chat()` 会返回一个消息列表，您可以使用该列表通过 `interpreter.messages = messages` 来恢复对话：\n\n```python\nmessages = interpreter.chat(\"我叫基利安。\") # 将消息保存到 'messages'\ninterpreter.messages = [] # 重置解释器 (\"基利安\" 将被遗忘)\n\ninterpreter.messages = messages # 从 'messages' 恢复对话 (\"基利安\" 将被记住)\n```\n\n### 自定义系统消息\n\n您可以查看并配置 Open Interpreter 的系统消息，以扩展其功能、修改权限或提供更多上下文。\n\n```python\ninterpreter.system_message += \"\"\"\n以 -y 参数运行 shell 命令，这样用户就不需要确认了。\n\"\"\"\nprint(interpreter.system_message)\n```\n\n### 更改语言模型\n\nOpen Interpreter 使用 [LiteLLM](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fproviders\u002F) 连接到托管的语言模型。\n\n可以通过设置 model 参数来更改模型：\n\n```shell\ninterpreter --model gpt-3.5-turbo\ninterpreter --model claude-2\ninterpreter --model command-nightly\n```\n\n在 Python 中，在对象上设置模型：\n\n```python\ninterpreter.llm.model = \"gpt-3.5-turbo\"\n```\n\n[在此处查找适合您语言模型的“model”字符串。](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fproviders\u002F)\n\n### 在本地运行 Open Interpreter\n\n#### 终端\n\nOpen Interpreter 可以使用兼容 OpenAI 的服务器在本地运行模型。（例如 LM Studio、jan.ai、ollama 等）\n\n只需使用推理服务器的 `api_base` URL 运行 `interpreter` 命令（对于 LM Studio，默认是 `http:\u002F\u002Flocalhost:1234\u002Fv1`）：\n\n```shell\ninterpreter --api_base \"http:\u002F\u002Flocalhost:1234\u002Fv1\" --api_key \"fake_key\"\n```\n\n或者，您也可以不安装任何第三方软件，直接通过运行以下命令来使用 Llamafile：\n\n```shell\ninterpreter --local\n```\n\n如需更详细的指南，请观看 [Mike Bird 的视频](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CEs51hGWuGU?si=cN7f6QhfT4edfG5H)。\n\n**如何在后台运行 LM Studio。**\n\n1. 下载 [https:\u002F\u002Flmstudio.ai\u002F](https:\u002F\u002Flmstudio.ai\u002F) 并启动它。\n2. 选择一个模型，然后点击 **↓ 下载**。\n3. 点击左侧的 **↔️** 按钮（位于 💬 下方）。\n4. 在顶部选择您的模型，然后点击 **启动服务器**。\n\n服务器启动后，您就可以开始与 Open Interpreter 对话了。\n\n> **注意：** 本地模式会将您的 `context_window` 设置为 3000，`max_tokens` 设置为 1000。如果您的模型有不同的要求，请手动设置这些参数（见下文）。\n\n#### Python\n\n我们的 Python 包让您对每个设置拥有更多控制权。要复制并连接到 LM Studio，请使用以下设置：\n\n```python\nfrom interpreter import interpreter\n\ninterpreter.offline = True # 禁用在线功能，如 Open Procedures\ninterpreter.llm.model = \"openai\u002Fx\" # 告诉 OI 使用 OpenAI 格式发送消息\ninterpreter.llm.api_key = \"fake_key\" # 我们用来与 LM Studio 通信的 LiteLLM 需要此密钥\ninterpreter.llm.api_base = \"http:\u002F\u002Flocalhost:1234\u002Fv1\" # 将其指向任何兼容 OpenAI 的服务器\n\ninterpreter.chat()\n```\n\n#### 上下文窗口和最大标记数\n\n您可以修改本地运行模型的 `max_tokens` 和 `context_window`（以标记数为单位）。\n\n对于本地模式，较小的上下文窗口会占用更少的内存，因此我们建议在出现故障或运行缓慢时尝试使用更短的窗口（约 1000）。请确保 `max_tokens` 小于 `context_window`。\n\n```shell\ninterpreter --local --max_tokens 1000 --context_window 3000\n```\n\n### 详细模式\n\n为了帮助您检查 Open Interpreter，我们提供了一个用于调试的 `--verbose` 模式。\n\n您可以通过使用该标志（`interpreter --verbose`）或在对话过程中激活详细模式：\n\n```shell\n$ interpreter\n...\n> %verbose true \u003C- 打开详细模式\n\n> %verbose false \u003C- 关闭详细模式\n```\n\n### 交互模式命令\n\n在交互模式中，您可以使用以下命令来提升体验。以下是可用命令列表：\n\n**可用命令：**\n\n- `%verbose [true\u002Ffalse]`: 切换详细模式。不带参数或使用 `true` 时进入详细模式。使用 `false` 时退出详细模式。\n- `%reset`: 重置当前会话的对话。\n- `%undo`: 从消息历史中移除上一条用户消息及 AI 的回复。\n- `%tokens [prompt]`: （实验性）计算下一条提示中作为上下文发送的标记数，并估算其成本。如果提供了 `prompt`，还可以可选地计算该提示的标记数和预估成本。预估成本依赖于 [LiteLLM 的 `cost_per_token()` 方法](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fcompletion\u002Ftoken_usage#2-cost_per_token)。\n- `%help`: 显示帮助信息。\n\n### 配置 \u002F 配置文件\n\nOpen Interpreter 允许您使用 `yaml` 文件设置默认行为。\n\n这提供了一种灵活的方式来配置解释器，而无需每次都更改命令行参数。\n\n运行以下命令以打开配置文件目录：\n\n```\ninterpreter --profiles\n```\n\n您可以在那里添加 `yaml` 文件。默认配置文件名为 `default.yaml`。\n\n#### 多个配置文件\n\nOpen Interpreter 支持多个 `yaml` 文件，允许您轻松切换不同的配置：\n\n```\ninterpreter --profile my_profile.yaml\n```\n\n## FastAPI 服务器示例\n\n生成器更新使 Open Interpreter 能够通过 HTTP REST 端点进行控制：\n\n```python\n# server.py\n\nfrom fastapi import FastAPI\nfrom fastapi.responses import StreamingResponse\nfrom interpreter import interpreter\n\napp = FastAPI()\n\n@app.get(\"\u002Fchat\")\ndef chat_endpoint(message: str):\n    def event_stream():\n        for result in interpreter.chat(message, stream=True):\n            yield f\"data: {result}\\n\\n\"\n\n    return StreamingResponse(event_stream(), media_type=\"text\u002Fevent-stream\")\n\n@app.get(\"\u002Fhistory\")\ndef history_endpoint():\n    return interpreter.messages\n```\n\n```shell\npip install fastapi uvicorn\nuvicorn server:app --reload\n```\n\n您也可以通过简单运行 `interpreter.server()` 来启动与上述相同的服务器。\n\n## 安卓\n\n在 [open-interpreter-termux 仓库](https:\u002F\u002Fgithub.com\u002FMikeBirdTech\u002Fopen-interpreter-termux) 中可以找到在您的 Android 设备上安装 Open Interpreter 的分步指南。\n\n## 安全提示\n\n由于生成的代码会在您的本地环境中执行，它可能会与您的文件和系统设置交互，从而导致意外后果，例如数据丢失或安全风险。\n\n**⚠️ Open Interpreter 在执行代码前会请求用户确认。**\n\n您可以通过运行 `interpreter -y` 或将 `interpreter.auto_run = True` 来绕过此确认，在这种情况下：\n\n- 请求修改文件或系统设置的命令时务必小心。\n- 请像对待自动驾驶汽车一样密切关注 Open Interpreter，并准备好通过关闭终端来终止进程。\n- 考虑在受限环境（如 Google Colab 或 Replit）中运行 Open Interpreter。这些环境更加隔离，可以降低执行任意代码的风险。\n\n目前还存在一项【实验性】支持的[安全模式](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FSAFE_MODE.md)，有助于缓解部分风险。\n\n## 工作原理是什么？\n\nOpen Interpreter 为一个具有函数调用能力的语言模型（[function-calling language model](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Fgpt\u002Ffunction-calling)）配备了一个 `exec()` 函数，该函数接受一种“语言”（如 “Python” 或 “JavaScript”）和要运行的“代码”。\n\n随后，我们将模型的消息、代码以及您系统的输出以 Markdown 格式流式传输到终端。\n\n# 离线访问文档\n\n完整的 [文档](https:\u002F\u002Fdocs.openinterpreter.com\u002F) 可以随时随地访问，无需互联网连接。\n\n[Node](https:\u002F\u002Fnodejs.org\u002Fen) 是先决条件：\n\n- 版本 18.17.0 或任何更高版本的 18.x.x 系列。\n- 版本 20.3.0 或任何更高版本的 20.x.x 系列。\n- 从 21.0.0 开始的任何版本，没有上限限制。\n\n安装 [Mintlify](https:\u002F\u002Fmintlify.com\u002F)：\n\n```bash\nnpm i -g mintlify@latest\n```\n\n进入文档目录并运行相应命令：\n\n```bash\n# 假设您位于项目的根目录\ncd .\u002Fdocs\n\n# 启动文档服务器\nmintlify dev\n```\n\n此时应会打开一个新的浏览器窗口。只要文档服务器运行着，您就可以在 [http:\u002F\u002Flocalhost:3000](http:\u002F\u002Flocalhost:3000) 访问文档。\n\n# 贡献\n\n感谢您对贡献的兴趣！我们欢迎社区成员的参与。\n\n请参阅我们的[贡献指南](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FCONTRIBUTING.md)，了解更多关于如何参与的信息。\n\n# 路线图\n\n访问[我们的路线图](https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fblob\u002Fmain\u002Fdocs\u002FROADMAP.md)，预览 Open Interpreter 的未来发展方向。\n\n**注意**：本软件与 OpenAI 无任何关联。\n\n![thumbnail-ncu](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fopeninterpreter_open-interpreter_readme_4fd87f816bb6.png)\n\n> 拥有一个能以指尖速度工作的初级程序员……可以让新的工作流程变得轻松高效，同时也为更多人打开了编程的大门。\n>\n> — _OpenAI 的 Code Interpreter 发布声明_\n\n\u003Cbr>","# Open Interpreter 快速上手指南\n\nOpen Interpreter 是一款让大语言模型（LLM）在本地运行代码（Python、JavaScript、Shell 等）的开源工具。它通过终端提供类似 ChatGPT 的交互界面，赋予自然语言控制电脑的能力，如数据处理、文件操作、浏览器自动化等。\n\n> **⚠️ 安全提示**：生成的代码在执行前会请求用户确认。如需自动执行，请谨慎使用并建议在隔离环境中运行。\n\n## 环境准备\n\n- **操作系统**：Windows、macOS 或 Linux\n- **Python 版本**：建议 Python 3.8 及以上\n- **依赖管理**：需安装 `pip` 包管理工具\n- **网络要求**：首次安装需访问 GitHub 和 PyPI；若使用在线模型（如 GPT-4），需确保网络通畅\n- **可选本地模型**：若希望完全离线运行，可预先安装 [LM Studio](https:\u002F\u002Flmstudio.ai\u002F)、[Ollama](https:\u002F\u002Follama.com\u002F) 或 [jan.ai](https:\u002F\u002Fjan.ai\u002F) 等本地推理服务\n\n## 安装步骤\n\n### 方式一：通过 pip 安装（推荐）\n\n```shell\npip install git+https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter.git\n```\n\n> 如遇下载缓慢，可尝试配置国内 pip 镜像源（如清华源）：\n> ```shell\n> pip install git+https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter.git -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n> ```\n\n### 方式二：本地模式（无需额外服务端）\n\n安装后直接使用 `--local` 参数即可调用内置的轻量级本地模型支持（基于 llamafile）：\n\n```shell\ninterpreter --local\n```\n\n## 基本使用\n\n### 1. 启动交互式终端\n\n安装完成后，在终端直接运行：\n\n```shell\ninterpreter\n```\n\n随后即可输入自然语言指令，例如：\n```\nPlot the stock prices of AAPL and META\n```\n\n系统会生成代码并询问是否执行，输入 `y` 确认后即可运行。\n\n### 2. 在 Python 脚本中调用\n\n```python\nfrom interpreter import interpreter\n\n# 执行单条指令\ninterpreter.chat(\"Add subtitles to all videos in \u002Fvideos.\")\n\n# 启动交互式对话\ninterpreter.chat()\n```\n\n### 3. 切换大模型\n\n默认使用 OpenAI 模型，可通过参数切换：\n\n```shell\ninterpreter --model gpt-3.5-turbo\ninterpreter --model claude-2\n```\n\n在 Python 中设置：\n\n```python\ninterpreter.llm.model = \"gpt-3.5-turbo\"\n```\n\n支持的所有模型名称请参考 [LiteLLM 文档](https:\u002F\u002Fdocs.litellm.ai\u002Fdocs\u002Fproviders\u002F)。\n\n### 4. 本地运行私有模型\n\n若已启动本地兼容 OpenAI API 的服务（如 LM Studio 默认地址为 `http:\u002F\u002Flocalhost:1234\u002Fv1`）：\n\n```shell\ninterpreter --api_base \"http:\u002F\u002Flocalhost:1234\u002Fv1\" --api_key \"fake_key\"\n```\n\n或在 Python 中配置：\n\n```python\nfrom interpreter import interpreter\n\ninterpreter.offline = True\ninterpreter.llm.model = \"openai\u002Fx\"\ninterpreter.llm.api_key = \"fake_key\"\ninterpreter.llm.api_base = \"http:\u002F\u002Flocalhost:1234\u002Fv1\"\n\ninterpreter.chat()\n```\n\n---\n\n现在你已可以快速开始使用 Open Interpreter。通过自然语言直接操控本地环境，开启高效的开发新体验。","数据分析师小林需要处理散落在本地文件夹中的上百个销售 CSV 文件，并立即生成可视化的季度趋势报告。\n\n### 没有 open-interpreter 时\n- 必须手动编写完整的 Python 脚本，反复调试 pandas 读取路径和 matplotlib 绘图参数，耗时且易错。\n- 遇到缺失值或格式不统一时，需中断流程去搜索清洗代码片段，再复制粘贴回编辑器修改。\n- 无法直接操作浏览器获取最新汇率或竞品数据，只能手动切换窗口查询后人工录入表格。\n- 每次调整图表样式（如颜色、标签）都需要重新运行整个脚本，迭代反馈周期长达数分钟。\n\n### 使用 open-interpreter 后\n- 只需在终端输入“合并当前目录下所有 CSV 并绘制季度销售趋势图”，open-interpreter 自动编写并执行代码完成全流程。\n- 遇到数据异常时，直接对话要求“自动填充缺失值并剔除异常点”，open-interpreter 即时修正逻辑并重新运行。\n- 指令“打开 Chrome 搜索今日美元汇率并更新到数据集”，open-interpreter 直接控制浏览器抓取数据并完成清洗。\n- 提出“把线条改成红色并添加数据标签”，open-interpreter 毫秒级修改代码并重绘图表，实现所见即所得的分析体验。\n\nopen-interpreter 将繁琐的编码与操作流程转化为自然语言对话，让技术人员能专注于业务逻辑而非实现细节。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fopeninterpreter_open-interpreter_4fd87f81.png","openinterpreter","Open Interpreter","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fopeninterpreter_81186676.png","",null,"www.openinterpreter.com","https:\u002F\u002Fgithub.com\u002Fopeninterpreter",[83,87,91,95],{"name":84,"color":85,"percentage":86},"Python","#3572A5",98.5,{"name":88,"color":89,"percentage":90},"PowerShell","#012456",0.8,{"name":92,"color":93,"percentage":94},"Shell","#89e051",0.7,{"name":96,"color":97,"percentage":98},"Dockerfile","#384d54",0.1,63009,5440,"2026-04-05T10:11:01","AGPL-3.0","Linux, macOS, Windows","非必需。本地运行模式可配合 LM Studio、Ollama 或 Llamafile 使用，具体显卡需求取决于用户选择的本地大语言模型；若使用云端模型则无需本地 GPU。","未说明（本地运行模式建议根据所选模型调整上下文窗口大小以节省内存，如设置为~1000 tokens）",{"notes":107,"python":108,"dependencies":109},"该工具主要通过调用外部 API（如 OpenAI、Claude 或本地兼容服务器）运行，自身不捆绑大型模型。若在本地运行模型，需自行部署兼容 OpenAI 接口的推理服务（如 LM Studio、Ollama）。执行代码前默认会请求用户确认，可通过参数跳过确认但存在安全风险，建议在受限环境（如 Docker 或虚拟机）中运行。Android 用户可通过 Termux 安装。","未明确说明（通常需 Python 3.8+ 以支持 pip 安装及现代 AI 库）",[110,111,112],"litellm","fastapi","uvicorn",[15],[115,116,117,118,119,120],"chatgpt","gpt-4","python","interpreter","javascript","nodejs",37,"2026-03-27T02:49:30.150509","2026-04-06T05:17:50.100247",[],[126,131,136,141,146,151,156,161,166,171,176,181,186,191,196,201,206,211,216,221],{"id":127,"version":128,"summary_zh":129,"released_at":130},107000,"v0.4.2","Prepped for new OAI compatible endpoint, fixes for Windows and Python 3.10!","2024-10-24T21:22:03",{"id":132,"version":133,"summary_zh":134,"released_at":135},107001,"v0.4.1","Better Windows support!","2024-10-24T21:20:18",{"id":137,"version":138,"summary_zh":139,"released_at":140},107002,"v0.4.0","New `interpreter --os` powered by Anthropic! + ❤️ @leetwito's dynamic computer tools and @MikeBirdTech's screenpipe demo.\r\n\r\n## What's Changed\r\n* Integrate with Screenpipe by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1484\r\n* Feat dynamic computer tools list by @leetwito in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1482\r\n* New `interpreter --os` powered by Anthropic by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1493\r\n\r\n## New Contributors\r\n* @leetwito made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1482\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.14...v0.4.0","2024-10-24T01:04:02",{"id":142,"version":143,"summary_zh":144,"released_at":145},107003,"v0.3.14","❤️\r\n\r\n## What's Changed\r\n* AWS Profiles by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1463\r\n* Fixed disable_telemetry being overwritten to False by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1442\r\n* Fixes #925: Exiting by Ctrl-D throws EOFError by @erhhung in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1456\r\n* Development by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1465\r\n* More cookbooks by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1472\r\n* Update computer-api.mdx – fix typo by @MrJarnould in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1459\r\n* line breaker character made invalid for filenames by @QUAGZA in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1448\r\n* Add sudo support for apt package installation in Terminal by @lolsZz in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1445\r\n* Update setup.mdx update links by @Notnaton in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1439\r\n* re: add markdown message for insufficient_quota error in openai by @cyai in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1349\r\n* Development by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1477\r\n* Fix tests by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1479\r\n\r\n## New Contributors\r\n* @erhhung made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1456\r\n* @MrJarnould made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1459\r\n* @QUAGZA made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1448\r\n* @lolsZz made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1445\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.13...v0.3.14","2024-10-15T18:39:24",{"id":147,"version":148,"summary_zh":149,"released_at":150},107004,"v0.3.13","Open Interpreter now can handle `stdin`-requiring inputs by waiting for 15-60 seconds between outputs, then asking the LLM to decide if it wants to enter keystrokes. It can also `CTRL-C` out of frozen processes.\r\n\r\nFor the 01, we also made changes to support \"Always listen for context\" mode. We also removed a `torch` dependency.","2024-09-15T22:42:40",{"id":152,"version":153,"summary_zh":154,"released_at":155},107005,"v0.3.12","Minor release: Experimental new browser computer tool that can navigate webpages instead of just search. A blazing fast new cerebras profile. Better docs. Better skills.\r\n\r\n❤️ \r\n\r\n## What's Changed\r\n* Cerebras AI Profile by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1431\r\n* Sync main by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1435\r\n* replaced the KillianLucas urls with OpenInterpreter by @yelizsevinc in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1429\r\n* Development by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1440\r\n\r\n## New Contributors\r\n* @yelizsevinc made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1429\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.10...v0.3.12","2024-09-05T06:34:23",{"id":157,"version":158,"summary_zh":159,"released_at":160},107006,"v0.3.10","Fixed a welcome message error that would appear if you didn't have an OPENAI_API_KEY.\r\n\r\n## What's Changed\r\n* Update dev from main by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1428\r\n* Fix welcome message error by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1433\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.8...v0.3.10","2024-08-29T22:55:44",{"id":162,"version":163,"summary_zh":164,"released_at":165},107007,"v0.3.9","Actually a lot? Server fixes, documentation fixes, new installer, better skills, new `--stdin` flag which feels very unix-y:\r\n\r\n```bash\r\npip install open-interpreter\r\n\"What operating system are you on?\" | interpreter --stdin -y\r\n```\r\n\r\n**Note:** Unintentionally bumped the version before pushing to `pip`, so we skipped 0.3.8!\r\n\r\nGreat work all!\r\n\r\n## What's Changed\r\n* Conda installer by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1395\r\n* Obsidian Profile by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1398\r\n* Added Ukrainian README.md translation by @okineadev in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1271\r\n* Development Merge by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1405\r\n* Ollama llama3.1 loading fix by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1400\r\n* Add starlette to pyproject.toml by @Notnaton in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1411\r\n* Profile Tutorial video in docs by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1407\r\n* Hide missing cost completion map warnings LiteLLM by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1409\r\n* Fix Documentation by @rbrisita in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1258\r\n* Merge Development Branch by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1416\r\n* Handle empty system messages by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1417\r\n* Server fixes, `stdin`, better skills by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1426\r\n* Examples by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1421\r\n* Update cloudflare.mdx by @pstoryomni in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1425\r\n* Updated fast mode to gpt-4o-mini & Profile version updated by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1418\r\n* Documentation and profile updates by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1427\r\n\r\n## New Contributors\r\n* @rbrisita made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1258\r\n* @pstoryomni made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1425\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.7...v0.3.8","2024-08-26T16:52:08",{"id":167,"version":168,"summary_zh":169,"released_at":170},107008,"v0.3.7","Minor update!\r\n\r\n## What's Changed\r\n* 0.3.7 better server by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1391\r\n* Hallucination fix by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1392\r\n* Ollama model list fix and a typo by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1388\r\n* Development by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1393\r\n* Added jupyter retries, minor robust fixes by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1394\r\n* Server robustness by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1396\r\n* Robuster Server by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1397\r\n* Version Bump by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1399\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.6...v0.3.7","2024-08-15T17:55:17",{"id":172,"version":173,"summary_zh":174,"released_at":175},107009,"v0.3.6","\u003Cimg width=\"1093\" alt=\"mf\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F2c917bfe-8af4-4c38-b0a5-bb504319a48e\">\r\n\r\n\r\n----------------------------------------------------------------------------\r\n\r\n- First-class Claude support\r\n- Java execution support by @CyanideByte\r\n- Moondream fix, docs update, `--groq` profile by @MikeBirdTech\r\n- '-nhl' command to disable active line highlighting by @cyai\r\n- Improved Linux support by @PiyushDuggal-source\r\n- Export to `%markdown` magic by @Steve235lab\r\n- Remote Ollama server support by @raajikhan\r\n- Much better error messaging by @JSee98 \r\n- Many llamafile updates by @CyanideByte\r\n- Server life-saving by @imapersonman\r\n- Docs fixes by @kevinmangan\r\n- Run from `exe` by @jbexta\r\n- **and more below...**\r\n\r\nFANTASTIC work this cycle everyone! More capable and more compatible all around.\r\n\r\n## What's Changed\r\n* Update dev branch by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1327\r\n* Java language execution support by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1326\r\n* Linux support by @PiyushDuggal-source in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1332\r\n* Update Development Branch by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1340\r\n* Sync Main \u003C> Development Branches by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1341\r\n* updated markdown message for tip by @JSee98 in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1339\r\n* Development Update by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1346\r\n* re: remove redundant new line char for the tip by @cyai in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1344\r\n* Update multiple-instances.mdx with correct key\u002Fvalue pairs for message dicts by @kevinmangan in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1342\r\n* Big server upgrades, documentation edits by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1347\r\n* Server tests by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1348\r\n* Server authentication by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1353\r\n* New `review` chunks by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1355\r\n* Claude support by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1358\r\n* Claude support by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1360\r\n* Claude Support by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1362\r\n* Llama 3.1 talk to your database profile by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1356\r\n* Fixed tool using bugs by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1363\r\n* Allow running from an executable by @jbexta in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1357\r\n* feat: let people turn of active highlighting by @cyai in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1354\r\n* Export conversation to markdown by @Steve235lab in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1282\r\n* Disable active line highlighting, export to `md`, allow running from executable by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1364\r\n* Fix: Unused HOST and PORT environment variables by @imapersonman in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1365\r\n* Koissi's critical server fix, shrink image fix, huge logs fix, security improvements by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1369\r\n* Added a YouTube video tutorial to the \"Setup\" guide by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1372\r\n* New setup tutorial, more reliable server by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1375\r\n* Docs update by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1345\r\n* Update Dev Branch by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1378\r\n* Fix error message on invalid model name and groq access to open inter… by @ighoshsubho in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1377\r\n* Added Groq profile and flag by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1376\r\n* New `--groq` profile + error message fix by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1379\r\n* Template Profile by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1381\r\n* add remote server support for ollama by @raajikhan in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1383\r\n* Llamafile updates by @CyanideByte in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1380\r\n* Add remote server support for Ollama, Add template profile, Updated Llamafiles by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpe","2024-08-08T01:16:17",{"id":177,"version":178,"summary_zh":179,"released_at":180},107010,"v0.3.4","Updated vision dependent profiles as [`gpt-4-vision-preview` is deprecated.](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fdeprecations\u002Fdeprecation-history)\r\n\r\n## What's Changed\r\n* Create examples directory by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1275\r\n* Update vision model to gpt-4o by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1318\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.3...v0.3.4","2024-06-30T21:22:03",{"id":182,"version":183,"summary_zh":184,"released_at":185},107011,"v0.3.3","Quick bug fix for Local III when using `--vision`.","2024-06-20T23:25:25",{"id":187,"version":188,"summary_zh":189,"released_at":190},107012,"v0.3.2","Bug fixes, minor system message improvements, and [EasyOCR](https:\u002F\u002Fgithub.com\u002FJaidedAI\u002FEasyOCR\u002Ftree\u002Fmaster\u002Feasyocr) for more robust local vision.\r\n\r\n\r\n## What's Changed\r\n* Add Filesystem tests by @tiovikram in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1311\r\n\r\n## New Contributors\r\n* @tiovikram made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1311\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.1...v0.3.2","2024-06-20T19:35:53",{"id":192,"version":193,"summary_zh":194,"released_at":195},107013,"v0.3.1","Windows bugfix for Local III.\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.3.0...v0.3.1","2024-06-18T21:16:01",{"id":197,"version":198,"summary_zh":199,"released_at":200},107014,"v0.3.0","[Read more here.](https:\u002F\u002Fchanges.openinterpreter.com\u002Flog\u002Flocal-iii)","2024-06-18T15:41:42",{"id":202,"version":203,"summary_zh":204,"released_at":205},107015,"v0.2.6","The second Local II preview before the official release next week.","2024-06-08T22:59:34",{"id":207,"version":208,"summary_zh":209,"released_at":210},107016,"v0.2.5","Better local model support, bug fixes, faster load, new features. Official release + blog post coming soon.","2024-04-24T15:56:01",{"id":212,"version":213,"summary_zh":214,"released_at":215},107017,"v0.2.4","Fixed a potential recurring `computer` import that occurs when teaching new skills to the [`01`](https:\u002F\u002Fgithub.com\u002FKillianLucas\u002F01), along with several great fixes from the community:\r\n\r\n## What's Changed\r\n* 01 by @KillianLucas in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1104\r\n* fix for Files property missing on Computer module by @bars0um in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1107\r\n* check that the message content is a string before calling strip() by @hackley in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1117\r\n* Support OpenAI's new models. by @Steve235lab in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1099\r\n\r\n## New Contributors\r\n* @bars0um made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1107\r\n* @hackley made their first contribution in https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fpull\u002F1117\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FOpenInterpreter\u002Fopen-interpreter\u002Fcompare\u002Fv0.2.3...v0.2.4","2024-03-24T07:58:48",{"id":217,"version":218,"summary_zh":219,"released_at":220},107018,"v0.2.3","`interpreter --local` is really good now thanks to @tyfiero. Try it!\r\n\r\n## What's Changed\r\n* The first development to main merge by @KillianLucas in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1077\r\n* Better local messaging by @KillianLucas in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1078\r\n* Change docs as --local no longer uses LM Studio by @aj47 in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1074\r\n* Update by @KillianLucas in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1081\r\n* Interactive local mode. Fixes errors from 0.2.1 change by @tyfiero in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1089\r\n* Clear messages on %reset instead of instantiating a new Interpreter by @MikeBirdTech in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1095\r\n* does not prompt openapi key when running --api_base by @lorenzejay in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1093\r\n* Fix markdown in README_JA.md: Correct code block language and command… by @ishibashi-futos in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1091\r\n\r\n## New Contributors\r\n* @aj47 made their first contribution in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1074\r\n* @lorenzejay made their first contribution in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1093\r\n* @ishibashi-futos made their first contribution in https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fpull\u002F1091\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FKillianLucas\u002Fopen-interpreter\u002Fcompare\u002Fv0.2.2...v0.2.3","2024-03-20T06:28:45",{"id":222,"version":223,"summary_zh":224,"released_at":225},107019,"v0.2.2","Quick fixes for `computer.mail` and `computer.sms`.","2024-03-12T09:48:42"]