[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73752":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":22,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},73752,"cohere-toolkit","cohere-ai\u002Fcohere-toolkit","cohere-ai","Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.","",null,"TypeScript",3179,431,39,13,0,9,29.91,"MIT License",false,"main",true,[],"2026-06-12 02:03:17","![](\u002Fdocs\u002Fassets\u002Fbanner.png)\n\n# Cohere Toolkit\n\nToolkit is a deployable all-in-one RAG application that enables users to quickly build their LLM-based product.\n\n- [Try Toolkit](#try-now)\n- [About Toolkit](#about-toolkit)\n- [Toolkit Setup](\u002Fdocs\u002Fsetup.md)\n- [Troubleshooting](\u002Fdocs\u002Ftroubleshooting.md)\n- [How to guides](\u002Fdocs\u002Fhow_to_guides.md)\n  - [How to set up command model providers](\u002Fdocs\u002Fcommand_model_providers.md)\n  - [How to add tools](\u002Fdocs\u002Fcustom_tool_guides\u002Ftool_guide.md)\n  - [How to add auth to your tools](\u002Fdocs\u002Fcustom_tool_guides\u002Ftool_auth_guide.md)\n  - [How to setup Google Drive](\u002Fdocs\u002Fcustom_tool_guides\u002Fgoogle_drive.md)\n  - [How to setup Gmail](\u002Fdocs\u002Fcustom_tool_guides\u002Fgmail.md)\n  - [How to setup Slack Tool](\u002Fdocs\u002Fcustom_tool_guides\u002Fslack.md)\n  - [How to setup Github Tool](\u002Fdocs\u002Fcustom_tool_guides\u002Fgithub.md)\n  - [How to setup Sharepoint](\u002Fdocs\u002Fcustom_tool_guides\u002Fsharepoint.md)\n  - [How to setup Google Text-to-Speech](\u002Fdocs\u002Ftext_to_speech.md)\n  - [How to add authentication](\u002Fdocs\u002Fauth_guide.md)\n  - [How to deploy toolkit services](\u002Fdocs\u002Fservice_deployments.md)\n  - [How to debug dockerized Toolkit API with VSCode\u002FPyCharm](\u002Fdocs\u002Fdebugging.md)\n  - [How to set up Github Actions for automated DB migrations](\u002Fdocs\u002Fgithub_migrations_action.md)\n  - [How to customize the theme](\u002Fdocs\u002Ftheming.md)\n  - [How to contribute](#contributing)\n- [Try Cohere's Command Showcase](https:\u002F\u002Fcoral.cohere.com\u002F)\n\n![](\u002Fdocs\u002Fassets\u002Ftoolkit.gif)\n\n## Try Now:\n\nThere are two main ways for quickly running Toolkit: local and cloud. See the specific instructions given below.\n\n### Local\n\n_You will need to have [Docker](https:\u002F\u002Fwww.docker.com\u002Fproducts\u002Fdocker-desktop\u002F), [Docker-compose >= 2.22](https:\u002F\u002Fdocs.docker.com\u002Fcompose\u002Finstall\u002F), and [Poetry](https:\u002F\u002Fpython-poetry.org\u002Fdocs\u002F#installation) installed. [Go here for a more detailed setup.](\u002Fdocs\u002Fsetup.md)_\nNote: to include community tools when building locally, set the `INSTALL_COMMUNITY_DEPS` build arg in the `docker-compose.yml` to `true`.\n\nBoth options will serve the frontend at http:\u002F\u002Flocalhost:4000.\n\n#### Using `make`\n\nUse the provided Makefile to simplify and automate your development workflow with Cohere Toolkit, including Docker Compose management, testing, linting, and environment setup.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcohere-ai\u002Fcohere-toolkit.git\ncd cohere-toolkit\nmake first-run\n```\n\n#### Docker Compose only\n\nUse Docker Compose directly if you want to quickly spin up and manage your container environment without the additional automation provided by the Makefile.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcohere-ai\u002Fcohere-toolkit.git\ncd cohere-toolkit\ndocker compose up\ndocker compose run --build backend alembic -c src\u002Fbackend\u002Falembic.ini upgrade head\n```\n\n### Cloud\n\n#### GitHub Codespaces\n\nTo run this project using GitHub Codespaces, please refer to our [Codespaces Setup Guide](\u002Fdocs\u002Fgithub_codespaces.md).\n\n## About Toolkit\n\n![](\u002Fdocs\u002Fassets\u002Ftoolkit_graphic.png)\n\n- **Interfaces** - any client-side UI, currently contains two web apps, one agentic and one basic, and a Slack bot implementation.\n  - Defaults to Cohere's Web UI at `src\u002Finterfaces\u002Fassistants_web` - A web app built in Next.js. Includes a simple SQL database out of the box to store conversation history in the app.\n  - You can change the Web UI using the docker compose file.\n- **Backend API** - in `src\u002Fbackend` this follows a similar structure to the [Cohere Chat API](https:\u002F\u002Fdocs.cohere.com\u002Freference\u002Fchat) but also include customizable elements:\n  - **Model** - you can customize with which provider you access Cohere's Command models. By default included in the toolkit is Cohere's Platform, Sagemaker, Azure, Bedrock, HuggingFace, local models. [More details here.](\u002Fdocs\u002Fcommand_model_providers.md)\n  - **Retrieval**- you can customize tools and data sources that the application is run with.\n- **Service Deployment Guides** - we also include guides for how to deploy the toolkit services in production including with AWS, GCP and Azure. [More details here.](\u002Fdocs\u002Fservice_deployments.md)\n\n## Contributing\n\nContributions are what drive an open source community, any contributions made are greatly appreciated. To get started, check out our [documentation.](CONTRIBUTING.md)\n\n## Contributors\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcohere-ai\u002Fcohere-toolkit\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=cohere-ai\u002Fcohere-toolkit\" \u002F>\n\u003C\u002Fa>\n\nMade with [contrib.rocks](https:\u002F\u002Fcontrib.rocks).\n","Cohere Toolkit 是一个预构建组件集合，旨在帮助用户快速构建和部署基于检索增强生成（RAG）的应用程序。该项目采用 TypeScript 编写，提供了一套完整的工具和服务，支持多种数据源集成如 Google Drive、Gmail 和 Slack 等，并且具备强大的自定义能力，允许开发者根据需求添加新的工具或调整现有工具的行为。此外，它还支持通过 Docker 本地运行以及云服务部署，非常适合需要快速开发原型或搭建生产级 RAG 应用的场景。MIT 许可证下开源，社区活跃，拥有超过3千个星标。",2,"2026-06-11 03:47:12","high_star"]