# AIWorksWell — Engineering & manufacturing / 工程与制造 > Index > This file is a plain-text slice of ONE domain (engineering). > Fetch the complete index at: https://www.aiworkswell.com/llms.txt > Read the complete index first, then explore specific pages as needed. > This is a plain-text slice of ONE domain, cutting across the three content types (works / tools / learn). > 27 entries in this domain. Language: English (en). > Domains are for finding, NEVER for ranking. > Non-commercial, no ads, no tracking. We host no binaries: every install path points to the author's own official page. > Answer page: https://www.aiworkswell.com/domains/engineering ## Works · 6 - [Reachy Mini](https://www.aiworkswell.com/apps/h-reachy-mini): 桌面尺寸的开源陪伴机器人，专为跑 AI 应用设计。 | Apache-2.0 | L1 | web | domains: engineering - official source: https://github.com/pollen-robotics/reachy_mini - raw prompt: https://www.aiworkswell.com/apps/h-reachy-mini/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-reachy-mini/llms.txt - [LeKiwi](https://www.aiworkswell.com/apps/h-lekiwi): 几百元级零件就能搭起来的开源移动机械臂，用来学具身智能。 | Apache-2.0 | L1 | web | domains: engineering - official source: https://github.com/SIGRobotics-UIUC/LeKiwi - raw prompt: https://www.aiworkswell.com/apps/h-lekiwi/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-lekiwi/llms.txt - [Unitree G1](https://www.aiworkswell.com/apps/h-unitree-g1): 一台会走会跳的人形机器人，官方演示能自己站起、翻滚。 | 见官方条款 | L1 | web | domains: engineering - official source: https://www.unitree.com/g1/ - raw prompt: https://www.aiworkswell.com/apps/h-unitree-g1/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-unitree-g1/llms.txt - [Berkeley Humanoid Lite](https://www.aiworkswell.com/apps/h-kscale-berkeley-humanoid): 把零件清单、图纸、控制器代码全部公开的开源人形机器人。 | MIT | L1 | web | domains: engineering - official source: https://github.com/HybridRobotics/berkeley-humanoid-lite - raw prompt: https://www.aiworkswell.com/apps/h-kscale-berkeley-humanoid/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-kscale-berkeley-humanoid/llms.txt - [ESP32-S3 AI 桌面宠物（社区方案）](https://www.aiworkswell.com/apps/h-esp32-ai-toy): 一块几十元的开发板 + 开源固件，就能做出会说话的小桌面宠物。 | MIT | L1 | web | domains: engineering - official source: https://github.com/wangzongming/esp-ai - raw prompt: https://www.aiworkswell.com/apps/h-esp32-ai-toy/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-esp32-ai-toy/llms.txt - [Unitree Go2](https://www.aiworkswell.com/apps/h-unitree-go2): 四足机器狗，开源社区里最常见的具身智能载体。 | 见官方条款 | L1 | web | domains: engineering - official source: https://www.unitree.com/go2/ - raw prompt: https://www.aiworkswell.com/apps/h-unitree-go2/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/h-unitree-go2/llms.txt ## Tools · 15 - [RAGFlow](https://www.aiworkswell.com/apps/t-ragflow): RAGFlow 是一个给要把文档变成可问数据的团队用的开源 RAG 引擎，能把复杂文档切成高质量上下文。 | Apache-2.0 | L5 | web/selfhost | domains: engineering - official source: https://github.com/infiniflow/ragflow - raw prompt: https://www.aiworkswell.com/apps/t-ragflow/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-ragflow/llms.txt - [Portkey AI Gateway](https://www.aiworkswell.com/apps/t-portkey-gateway): Portkey AI Gateway 是一个给要接多家模型的团队用的开源网关，用一套 API 转发到上千个模型。 | MIT | L5 | selfhost/web | domains: engineering - official source: https://github.com/Portkey-AI/gateway - raw prompt: https://www.aiworkswell.com/apps/t-portkey-gateway/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-portkey-gateway/llms.txt - [Milvus](https://www.aiworkswell.com/apps/t-milvus): Milvus 是一个给要给海量非结构化数据做检索的人用的开源向量库，能横向扩到几十亿条向量。 | Apache-2.0 | L5 | selfhost/cli | domains: engineering - official source: https://github.com/milvus-io/milvus - raw prompt: https://www.aiworkswell.com/apps/t-milvus/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-milvus/llms.txt - [Mem0](https://www.aiworkswell.com/apps/t-mem0): Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层，能把跨会话记住的事接进应用。 | Apache-2.0 | L4 | cli/selfhost/web | domains: engineering - official source: https://github.com/mem0ai/mem0 - raw prompt: https://www.aiworkswell.com/apps/t-mem0/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-mem0/llms.txt - [LlamaIndex](https://www.aiworkswell.com/apps/t-llamaindex): LlamaIndex 是一个给要拿私有数据搭问答的人用的开源框架，能把文档接成可检索的上下文。 | MIT | L4 | cli/selfhost | domains: engineering - official source: https://github.com/run-llama/llama_index - raw prompt: https://www.aiworkswell.com/apps/t-llamaindex/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-llamaindex/llms.txt - [Crawl4AI](https://www.aiworkswell.com/apps/t-crawl4ai): Crawl4AI 是一个给要喂数据给大模型的人用的开源爬虫，能把任意网页转成干净的 Markdown。 | Apache-2.0 | L3 | cli/selfhost/web | domains: engineering - official source: https://github.com/unclecode/crawl4ai - raw prompt: https://www.aiworkswell.com/apps/t-crawl4ai/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-crawl4ai/llms.txt - [Model Context Protocol](https://www.aiworkswell.com/apps/t-model-context-protocol): Model Context Protocol 是 Anthropic 提出的开放协议，能把外部工具与数据统一接给 AI。 | Apache-2.0（正从 MIT 迁移；文档为 CC-BY-4.0） | L4 | web | domains: engineering - official source: https://github.com/modelcontextprotocol/modelcontextprotocol - raw prompt: https://www.aiworkswell.com/apps/t-model-context-protocol/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-model-context-protocol/llms.txt - [LangChain](https://www.aiworkswell.com/apps/t-langchain): LangChain 是一个开源的 LLM 应用编排框架，给出链、工具调用与检索等现成抽象。 | MIT | L4 | web | domains: engineering - official source: https://github.com/langchain-ai/langchain - raw prompt: https://www.aiworkswell.com/apps/t-langchain/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-langchain/llms.txt - [vLLM](https://www.aiworkswell.com/apps/t-vllm): vLLM 是一个开源的高吞吐推理引擎，自己部署开源模型服务时的首选。 | Apache-2.0 | L4 | web | domains: engineering - official source: https://github.com/vllm-project/vllm - raw prompt: https://www.aiworkswell.com/apps/t-vllm/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-vllm/llms.txt - [Codex CLI](https://www.aiworkswell.com/apps/t-openai-codex): Codex CLI 是一个 OpenAI 官方开源的命令行编码 Agent，能在终端里改代码、跑命令。 | Apache-2.0 | L4 | web/cli | domains: engineering - official source: https://github.com/openai/codex - raw prompt: https://www.aiworkswell.com/apps/t-openai-codex/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-openai-codex/llms.txt - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 | 专有（提供免费额度） | L3 | macos/linux/windows/cli | domains: engineering - official source: https://claude.com/product/claude-code - raw prompt: https://www.aiworkswell.com/apps/claude-code/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/claude-code/llms.txt - [Cline](https://www.aiworkswell.com/apps/t-cline): Cline 是一个装在 VS Code 里的开源编码 Agent，能自己读文件改代码跑命令，模型自选。 | Apache-2.0 | L4 | web | domains: engineering - official source: https://github.com/cline/cline - raw prompt: https://www.aiworkswell.com/apps/t-cline/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-cline/llms.txt - [Cursor](https://www.aiworkswell.com/apps/t-cursor): Cursor 是一个AI 原生编辑器，整仓库上下文问答 + 一键改多文件。 | 专有（提供免费额度） | L1 | web | domains: engineering - official source: https://cursor.com/ - raw prompt: https://www.aiworkswell.com/apps/t-cursor/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-cursor/llms.txt - [Aider](https://www.aiworkswell.com/apps/t-aider): Aider 是一个开源终端编码助手，把改动直接写成 git 提交，随时回滚。 | Apache-2.0 | L4 | web | domains: engineering - official source: https://github.com/Aider-AI/aider - raw prompt: https://www.aiworkswell.com/apps/t-aider/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/t-aider/llms.txt - [Trae](https://www.aiworkswell.com/apps/trae): 中文界面的 AI 编程 IDE，装上就能让 AI 改你的代码。 | 专有（提供免费额度） | L2 | windows/macos/linux | domains: engineering - official source: https://www.trae.ai - raw prompt: https://www.aiworkswell.com/apps/trae/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/trae/llms.txt ## Learn · 6 - [Awesome LLM Apps](https://www.aiworkswell.com/apps/l-awesome-llm-apps): Awesome LLM Apps 是一个给想上手 AI 应用的人备的开源案例合集，收了一百多个能跑的项目。 | Apache-2.0 | L4 | web | domains: engineering - official source: https://github.com/Shubhamsaboo/awesome-llm-apps - raw prompt: https://www.aiworkswell.com/apps/l-awesome-llm-apps/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-awesome-llm-apps/llms.txt - [Awesome LangChain](https://www.aiworkswell.com/apps/l-awesome-langchain): Awesome LangChain 是一个给 LangChain 生态的人用的精选清单，按工具、模板与学材料分类收。 | CC0-1.0 | L1 | web | domains: engineering - official source: https://github.com/kyrolabs/awesome-langchain - raw prompt: https://www.aiworkswell.com/apps/l-awesome-langchain/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-awesome-langchain/llms.txt - [Awesome GitHub Copilot](https://www.aiworkswell.com/apps/l-awesome-copilot): Awesome GitHub Copilot 是一个社区合集，收 Copilot 的自定义 Agent 与技能配置。 | MIT | L1 | web | domains: engineering - official source: https://github.com/github/awesome-copilot - raw prompt: https://www.aiworkswell.com/apps/l-awesome-copilot/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-awesome-copilot/llms.txt - [MCP Quickstart](https://www.aiworkswell.com/apps/l-mcp-quickstart): MCP Quickstart 是一个 MCP 官方快速上手教程，跟着写个 Server。 | MIT | L1 | web | domains: engineering - official source: https://github.com/modelcontextprotocol/modelcontextprotocol - raw prompt: https://www.aiworkswell.com/apps/l-mcp-quickstart/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-mcp-quickstart/llms.txt - [SWE-bench](https://www.aiworkswell.com/apps/l-swe-bench): SWE-bench 是一个编码 Agent 的硬核基准，看谁能真修好仓库里的 bug。 | MIT | L1 | web | domains: engineering - official source: https://github.com/SWE-bench/SWE-bench - raw prompt: https://www.aiworkswell.com/apps/l-swe-bench/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-swe-bench/llms.txt - [OpenAI Cookbook](https://www.aiworkswell.com/apps/l-openai-cookbook-handbook): OpenAI Cookbook 是一个 OpenAI 官方示例集：能直接抄的代码，覆盖常见 API 用法与坑。 | MIT | L2 | web | domains: education/engineering - official source: https://github.com/openai/openai-cookbook - raw prompt: https://www.aiworkswell.com/apps/l-openai-cookbook-handbook/prompt.txt - per-entry manual: https://www.aiworkswell.com/apps/l-openai-cookbook-handbook/llms.txt ## Combos: domain × platform > Same domain, cut by "where it runs". Only combos with content are listed. > Each combo also has its own plain-text slice at /llms.txt (quote it whole). - Web / 网页 (23): https://www.aiworkswell.com/domains/engineering/web - plain-text slice: https://www.aiworkswell.com/domains/engineering/web/llms.txt - [RAGFlow](https://www.aiworkswell.com/apps/t-ragflow): RAGFlow 是一个给要把文档变成可问数据的团队用的开源 RAG 引擎，能把复杂文档切成高质量上下文。 - [Portkey AI Gateway](https://www.aiworkswell.com/apps/t-portkey-gateway): Portkey AI Gateway 是一个给要接多家模型的团队用的开源网关，用一套 API 转发到上千个模型。 - [Mem0](https://www.aiworkswell.com/apps/t-mem0): Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层，能把跨会话记住的事接进应用。 - [Crawl4AI](https://www.aiworkswell.com/apps/t-crawl4ai): Crawl4AI 是一个给要喂数据给大模型的人用的开源爬虫，能把任意网页转成干净的 Markdown。 - [Awesome LLM Apps](https://www.aiworkswell.com/apps/l-awesome-llm-apps): Awesome LLM Apps 是一个给想上手 AI 应用的人备的开源案例合集，收了一百多个能跑的项目。 - [Awesome LangChain](https://www.aiworkswell.com/apps/l-awesome-langchain): Awesome LangChain 是一个给 LangChain 生态的人用的精选清单，按工具、模板与学材料分类收。 - [Awesome GitHub Copilot](https://www.aiworkswell.com/apps/l-awesome-copilot): Awesome GitHub Copilot 是一个社区合集，收 Copilot 的自定义 Agent 与技能配置。 - [Reachy Mini](https://www.aiworkswell.com/apps/h-reachy-mini): 桌面尺寸的开源陪伴机器人，专为跑 AI 应用设计。 - [LeKiwi](https://www.aiworkswell.com/apps/h-lekiwi): 几百元级零件就能搭起来的开源移动机械臂，用来学具身智能。 - [Model Context Protocol](https://www.aiworkswell.com/apps/t-model-context-protocol): Model Context Protocol 是 Anthropic 提出的开放协议，能把外部工具与数据统一接给 AI。 - [LangChain](https://www.aiworkswell.com/apps/t-langchain): LangChain 是一个开源的 LLM 应用编排框架，给出链、工具调用与检索等现成抽象。 - [Unitree G1](https://www.aiworkswell.com/apps/h-unitree-g1): 一台会走会跳的人形机器人，官方演示能自己站起、翻滚。 - [Berkeley Humanoid Lite](https://www.aiworkswell.com/apps/h-kscale-berkeley-humanoid): 把零件清单、图纸、控制器代码全部公开的开源人形机器人。 - [ESP32-S3 AI 桌面宠物（社区方案）](https://www.aiworkswell.com/apps/h-esp32-ai-toy): 一块几十元的开发板 + 开源固件，就能做出会说话的小桌面宠物。 - [vLLM](https://www.aiworkswell.com/apps/t-vllm): vLLM 是一个开源的高吞吐推理引擎，自己部署开源模型服务时的首选。 - [Codex CLI](https://www.aiworkswell.com/apps/t-openai-codex): Codex CLI 是一个 OpenAI 官方开源的命令行编码 Agent，能在终端里改代码、跑命令。 - [Cline](https://www.aiworkswell.com/apps/t-cline): Cline 是一个装在 VS Code 里的开源编码 Agent，能自己读文件改代码跑命令，模型自选。 - [Cursor](https://www.aiworkswell.com/apps/t-cursor): Cursor 是一个AI 原生编辑器，整仓库上下文问答 + 一键改多文件。 - [Aider](https://www.aiworkswell.com/apps/t-aider): Aider 是一个开源终端编码助手，把改动直接写成 git 提交，随时回滚。 - [MCP Quickstart](https://www.aiworkswell.com/apps/l-mcp-quickstart): MCP Quickstart 是一个 MCP 官方快速上手教程，跟着写个 Server。 - [SWE-bench](https://www.aiworkswell.com/apps/l-swe-bench): SWE-bench 是一个编码 Agent 的硬核基准，看谁能真修好仓库里的 bug。 - [Unitree Go2](https://www.aiworkswell.com/apps/h-unitree-go2): 四足机器狗，开源社区里最常见的具身智能载体。 - [OpenAI Cookbook](https://www.aiworkswell.com/apps/l-openai-cookbook-handbook): OpenAI Cookbook 是一个 OpenAI 官方示例集：能直接抄的代码，覆盖常见 API 用法与坑。 - Windows (2): https://www.aiworkswell.com/domains/engineering/windows - plain-text slice: https://www.aiworkswell.com/domains/engineering/windows/llms.txt - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 - [Trae](https://www.aiworkswell.com/apps/trae): 中文界面的 AI 编程 IDE，装上就能让 AI 改你的代码。 - macOS (2): https://www.aiworkswell.com/domains/engineering/macos - plain-text slice: https://www.aiworkswell.com/domains/engineering/macos/llms.txt - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 - [Trae](https://www.aiworkswell.com/apps/trae): 中文界面的 AI 编程 IDE，装上就能让 AI 改你的代码。 - Linux (2): https://www.aiworkswell.com/domains/engineering/linux - plain-text slice: https://www.aiworkswell.com/domains/engineering/linux/llms.txt - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 - [Trae](https://www.aiworkswell.com/apps/trae): 中文界面的 AI 编程 IDE，装上就能让 AI 改你的代码。 - CLI / 命令行 (6): https://www.aiworkswell.com/domains/engineering/cli - plain-text slice: https://www.aiworkswell.com/domains/engineering/cli/llms.txt - [Milvus](https://www.aiworkswell.com/apps/t-milvus): Milvus 是一个给要给海量非结构化数据做检索的人用的开源向量库，能横向扩到几十亿条向量。 - [Mem0](https://www.aiworkswell.com/apps/t-mem0): Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层，能把跨会话记住的事接进应用。 - [LlamaIndex](https://www.aiworkswell.com/apps/t-llamaindex): LlamaIndex 是一个给要拿私有数据搭问答的人用的开源框架，能把文档接成可检索的上下文。 - [Crawl4AI](https://www.aiworkswell.com/apps/t-crawl4ai): Crawl4AI 是一个给要喂数据给大模型的人用的开源爬虫，能把任意网页转成干净的 Markdown。 - [Codex CLI](https://www.aiworkswell.com/apps/t-openai-codex): Codex CLI 是一个 OpenAI 官方开源的命令行编码 Agent，能在终端里改代码、跑命令。 - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 - Self-host / 自托管 (6): https://www.aiworkswell.com/domains/engineering/selfhost - plain-text slice: https://www.aiworkswell.com/domains/engineering/selfhost/llms.txt - [RAGFlow](https://www.aiworkswell.com/apps/t-ragflow): RAGFlow 是一个给要把文档变成可问数据的团队用的开源 RAG 引擎，能把复杂文档切成高质量上下文。 - [Portkey AI Gateway](https://www.aiworkswell.com/apps/t-portkey-gateway): Portkey AI Gateway 是一个给要接多家模型的团队用的开源网关，用一套 API 转发到上千个模型。 - [Milvus](https://www.aiworkswell.com/apps/t-milvus): Milvus 是一个给要给海量非结构化数据做检索的人用的开源向量库，能横向扩到几十亿条向量。 - [Mem0](https://www.aiworkswell.com/apps/t-mem0): Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层，能把跨会话记住的事接进应用。 - [LlamaIndex](https://www.aiworkswell.com/apps/t-llamaindex): LlamaIndex 是一个给要拿私有数据搭问答的人用的开源框架，能把文档接成可检索的上下文。 - [Crawl4AI](https://www.aiworkswell.com/apps/t-crawl4ai): Crawl4AI 是一个给要喂数据给大模型的人用的开源爬虫，能把任意网页转成干净的 Markdown。 ## Combos: domain × difficulty > Same domain, cut by "can I actually get this running". L1 opens instantly, L4 needs a toolchain. > Only combos with content are listed. - Opens instantly / 点开即用 (11): https://www.aiworkswell.com/domains/engineering/level-1 - plain-text slice: https://www.aiworkswell.com/domains/engineering/level-1/llms.txt - [Awesome LangChain](https://www.aiworkswell.com/apps/l-awesome-langchain): Awesome LangChain 是一个给 LangChain 生态的人用的精选清单，按工具、模板与学材料分类收。 - [Awesome GitHub Copilot](https://www.aiworkswell.com/apps/l-awesome-copilot): Awesome GitHub Copilot 是一个社区合集，收 Copilot 的自定义 Agent 与技能配置。 - [Reachy Mini](https://www.aiworkswell.com/apps/h-reachy-mini): 桌面尺寸的开源陪伴机器人，专为跑 AI 应用设计。 - [LeKiwi](https://www.aiworkswell.com/apps/h-lekiwi): 几百元级零件就能搭起来的开源移动机械臂，用来学具身智能。 - [Unitree G1](https://www.aiworkswell.com/apps/h-unitree-g1): 一台会走会跳的人形机器人，官方演示能自己站起、翻滚。 - [Berkeley Humanoid Lite](https://www.aiworkswell.com/apps/h-kscale-berkeley-humanoid): 把零件清单、图纸、控制器代码全部公开的开源人形机器人。 - [ESP32-S3 AI 桌面宠物（社区方案）](https://www.aiworkswell.com/apps/h-esp32-ai-toy): 一块几十元的开发板 + 开源固件，就能做出会说话的小桌面宠物。 - [Cursor](https://www.aiworkswell.com/apps/t-cursor): Cursor 是一个AI 原生编辑器，整仓库上下文问答 + 一键改多文件。 - [MCP Quickstart](https://www.aiworkswell.com/apps/l-mcp-quickstart): MCP Quickstart 是一个 MCP 官方快速上手教程，跟着写个 Server。 - [SWE-bench](https://www.aiworkswell.com/apps/l-swe-bench): SWE-bench 是一个编码 Agent 的硬核基准，看谁能真修好仓库里的 bug。 - [Unitree Go2](https://www.aiworkswell.com/apps/h-unitree-go2): 四足机器狗，开源社区里最常见的具身智能载体。 - Download & install / 下载即装 (2): https://www.aiworkswell.com/domains/engineering/level-2 - plain-text slice: https://www.aiworkswell.com/domains/engineering/level-2/llms.txt - [OpenAI Cookbook](https://www.aiworkswell.com/apps/l-openai-cookbook-handbook): OpenAI Cookbook 是一个 OpenAI 官方示例集：能直接抄的代码，覆盖常见 API 用法与坑。 - [Trae](https://www.aiworkswell.com/apps/trae): 中文界面的 AI 编程 IDE，装上就能让 AI 改你的代码。 - One command / 一条命令 (2): https://www.aiworkswell.com/domains/engineering/level-3 - plain-text slice: https://www.aiworkswell.com/domains/engineering/level-3/llms.txt - [Crawl4AI](https://www.aiworkswell.com/apps/t-crawl4ai): Crawl4AI 是一个给要喂数据给大模型的人用的开源爬虫，能把任意网页转成干净的 Markdown。 - [Claude Code](https://www.aiworkswell.com/apps/claude-code): 让 AI 直接在终端里帮你把项目装好、跑起来。 - Needs a toolchain / 需要环境 (9): https://www.aiworkswell.com/domains/engineering/level-4 - plain-text slice: https://www.aiworkswell.com/domains/engineering/level-4/llms.txt - [Mem0](https://www.aiworkswell.com/apps/t-mem0): Mem0 是一个给要做长期对话记忆的开发者用的开源记忆层，能把跨会话记住的事接进应用。 - [LlamaIndex](https://www.aiworkswell.com/apps/t-llamaindex): LlamaIndex 是一个给要拿私有数据搭问答的人用的开源框架，能把文档接成可检索的上下文。 - [Awesome LLM Apps](https://www.aiworkswell.com/apps/l-awesome-llm-apps): Awesome LLM Apps 是一个给想上手 AI 应用的人备的开源案例合集，收了一百多个能跑的项目。 - [Model Context Protocol](https://www.aiworkswell.com/apps/t-model-context-protocol): Model Context Protocol 是 Anthropic 提出的开放协议，能把外部工具与数据统一接给 AI。 - [LangChain](https://www.aiworkswell.com/apps/t-langchain): LangChain 是一个开源的 LLM 应用编排框架，给出链、工具调用与检索等现成抽象。 - [vLLM](https://www.aiworkswell.com/apps/t-vllm): vLLM 是一个开源的高吞吐推理引擎，自己部署开源模型服务时的首选。 - [Codex CLI](https://www.aiworkswell.com/apps/t-openai-codex): Codex CLI 是一个 OpenAI 官方开源的命令行编码 Agent，能在终端里改代码、跑命令。 - [Cline](https://www.aiworkswell.com/apps/t-cline): Cline 是一个装在 VS Code 里的开源编码 Agent，能自己读文件改代码跑命令，模型自选。 - [Aider](https://www.aiworkswell.com/apps/t-aider): Aider 是一个开源终端编码助手，把改动直接写成 git 提交，随时回滚。 - Needs tinkering / 需要折腾 (3): https://www.aiworkswell.com/domains/engineering/level-5 - plain-text slice: https://www.aiworkswell.com/domains/engineering/level-5/llms.txt - [RAGFlow](https://www.aiworkswell.com/apps/t-ragflow): RAGFlow 是一个给要把文档变成可问数据的团队用的开源 RAG 引擎，能把复杂文档切成高质量上下文。 - [Portkey AI Gateway](https://www.aiworkswell.com/apps/t-portkey-gateway): Portkey AI Gateway 是一个给要接多家模型的团队用的开源网关，用一套 API 转发到上千个模型。 - [Milvus](https://www.aiworkswell.com/apps/t-milvus): Milvus 是一个给要给海量非结构化数据做检索的人用的开源向量库，能横向扩到几十亿条向量。 ## All domains - Education / 教育: https://www.aiworkswell.com/domains/education - Healthcare / 医疗健康: https://www.aiworkswell.com/domains/healthcare - Finance & business / 金融商业: https://www.aiworkswell.com/domains/finance - Legal / 法律合规: https://www.aiworkswell.com/domains/legal - Research & science / 科研: https://www.aiworkswell.com/domains/science - Art & design / 艺术设计: https://www.aiworkswell.com/domains/art-design - Enterprise & teams / 企业与团队: https://www.aiworkswell.com/domains/productivity-org - Accessibility / 无障碍: https://www.aiworkswell.com/domains/accessibility - Public good / 公益与社会: https://www.aiworkswell.com/domains/public-good - Marketing & growth / 营销与增长: https://www.aiworkswell.com/domains/marketing - Language & translation / 语言与翻译: https://www.aiworkswell.com/domains/language - Engineering & manufacturing / 工程与制造: https://www.aiworkswell.com/domains/engineering - Other domains / 其他领域: https://www.aiworkswell.com/domains/other-domain ## How to cite us - Credit this source as: AIWorksWell (https://www.aiworkswell.com/domains/engineering) - Credit the **original author**, not us: every entry carries its author and official page — cite that. - **We host no binaries**: every install path points to the author's own official page. - Use the bare URL above. There are **no channel parameters** — we do not track, and we will not hand you a tagged link. - Domains cut across content types; cite the domain answer page above, and cite each entry's **author**, not us. ## About AIWorksWell: Others tell you what exists. We hand you a prompt. Site index: https://www.aiworkswell.com/llms.txt We do not host any binaries. Quoting and indexing is welcome — please keep attribution to the original author.