{"id":13737689,"url":"https://github.com/firebase/genkit","last_synced_at":"2026-03-13T02:09:52.634Z","repository":{"id":237555080,"uuid":"793795224","full_name":"firebase/genkit","owner":"firebase","description":"An open source framework for building AI-powered apps with familiar code-centric patterns. Genkit makes it easy to develop, integrate, and test AI features with observability and evaluations. Genkit works with various models and platforms.","archived":false,"fork":false,"pushed_at":"2025-05-12T14:51:07.000Z","size":142648,"stargazers_count":1831,"open_issues_count":469,"forks_count":252,"subscribers_count":46,"default_branch":"main","last_synced_at":"2025-05-12T15:23:09.135Z","etag":null,"topics":["agents","ai","embedders","genkit","llm","machine-learning","multimodal","rag","vector-database"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/firebase.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-04-29T22:04:42.000Z","updated_at":"2025-05-12T15:09:52.000Z","dependencies_parsed_at":"2024-05-27T17:51:51.333Z","dependency_job_id":"2c269ea3-9f4a-4f1c-8059-003bb2d4df9e","html_url":"https://github.com/firebase/genkit","commit_stats":{"total_commits":2337,"total_committers":58,"mean_commits":"40.293103448275865","dds":0.795464270432178,"last_synced_commit":"b1869b78591ff10d8e5b23ffb6ea42d628a2720a"},"previous_names":["firebase/genkit"],"tags_count":1266,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/firebase%2Fgenkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/firebase%2Fgenkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/firebase%2Fgenkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/firebase%2Fgenkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/firebase","download_url":"https://codeload.github.com/firebase/genkit/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253764127,"owners_count":21960517,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai","embedders","genkit","llm","machine-learning","multimodal","rag","vector-database"],"created_at":"2024-08-03T03:01:57.375Z","updated_at":"2026-01-07T03:19:38.601Z","avatar_url":"https://github.com/firebase.png","language":"TypeScript","readme":"![Genkit logo](docs/resources/genkit-logo-dark.png#gh-dark-mode-only 'Genkit')\n![Genkit logo](docs/resources/genkit-logo.png#gh-light-mode-only 'Genkit')\n\n[Genkit](https://genkit.dev) is an open-source framework for building full-stack AI-powered applications, built and used in production by Google's Firebase. It provides SDKs for multiple programming languages with varying levels of stability:\n\n- **JavaScript/TypeScript**: Production-ready with full feature support\n- **Go**: Production-ready with full feature support\n- **Python (Alpha)**: Early development with core functionality\n\nIt offers a unified interface for integrating AI models from providers like [Google](https://genkit.dev/docs/plugins/google-genai), [OpenAI](https://genkit.dev/docs/plugins/openai), [Anthropic](https://thefireco.github.io/genkit-plugins/docs/plugins/genkitx-anthropic), [Ollama](https://genkit.dev/docs/plugins/ollama/), and more. Rapidly build and deploy production-ready chatbots, automations, and recommendation systems using streamlined APIs for multimodal content, structured outputs, tool calling, and agentic workflows.\n\nGet started with just a few lines of code:\n\n```ts\nimport { genkit } from 'genkit';\nimport { googleAI } from '@genkit-ai/google-genai';\n\nconst ai = genkit({ plugins: [googleAI()] });\n\nconst { text } = await ai.generate({\n    model: googleAI.model('gemini-2.5-flash'),\n    prompt: 'Why is Firebase awesome?'\n});\n```\n\n## Explore \u0026 build with Genkit\n\nPlay with AI sample apps, with visualizations of the Genkit code that powers\nthem, at no cost to you.\n\n[Explore Genkit by Example](https://examples.genkit.dev)\n\n## Key capabilities\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eBroad AI model support\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eUse a unified interface to integrate with hundreds of models from providers like \u003ca href=\"https://genkit.dev/docs/plugins/google-genai\"\u003eGoogle\u003c/a\u003e, \u003ca href=\"https://genkit.dev/docs/plugins/openai\"\u003e\n    OpenAI\u003c/a\u003e, \u003ca href=\"https://thefireco.github.io/genkit-plugins/docs/plugins/genkitx-anthropic\"\u003e\n    Anthropic\u003c/a\u003e, \u003ca href=\"https://genkit.dev/docs/plugins/ollama\"\u003eOllama\u003c/a\u003e, and more. Explore, compare, and use the best models for your needs.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eSimplified AI development\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eUse streamlined APIs to build AI features with \u003ca href=\"https://genkit.dev/docs/models#structured-output\"\u003e\n    structured output\u003c/a\u003e, \u003ca href=\"https://genkit.dev/docs/tool-calling\"\u003eagentic tool calling\u003c/a\u003e, \u003ca href=\"https://genkit.dev/docs/rag\"\u003econtext-aware generation\u003c/a\u003e, \u003ca href=\"https://genkit.dev/docs/models#multimodal\"\u003emulti-modal input/output\u003c/a\u003e, and more. Genkit handles the complexity of AI development, so you can build and iterate faster.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eWeb and mobile ready\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eIntegrate seamlessly with frameworks and platforms including Next.js, React, Angular, iOS, Android, using purpose-built \u003ca href=\"https://genkit.dev/docs/firebase\"\u003eclient SDKs\u003c/a\u003e and helpers.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eCross-language support\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eBuild with the language that best fits your project. Genkit provides SDKs for JavaScript/TypeScript, Go, and Python (Alpha) with consistent APIs and capabilities across all supported languages.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eDeploy anywhere\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eDeploy AI logic to any environment that supports your chosen programming language, such as \u003ca href=\"https://genkit.dev/docs/firebase\"\u003eCloud Functions for Firebase\u003c/a\u003e,\n    \u003ca href=\"https://genkit.dev/docs/cloud-run\"\u003eGoogle Cloud Run\u003c/a\u003e, or \u003ca href=\"https://genkit.dev/docs/deploy-node\"\u003ethird-party platforms\u003c/a\u003e,\n    with or without Google services.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eDeveloper tools\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eAccelerate AI development with a purpose-built, local \u003ca href=\"https://genkit.dev/docs/devtools\"\u003eCLI and Developer UI\u003c/a\u003e. Test prompts and\n    flows against individual inputs or datasets, compare outputs from different models, debug with detailed execution traces, and use immediate visual feedback to iterate rapidly on prompts.\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cstrong\u003eProduction monitoring\u003c/strong\u003e\u003c/td\u003e\n    \u003ctd\u003eShip AI features with confidence using comprehensive production monitoring. Track model performance, and request volumes, latency, and error rates in a \u003ca href=\"https://genkit.dev/docs/observability/getting-started\"\u003e purpose-built dashboard\u003c/a\u003e. Identify issues quickly with detailed observability metrics, and ensure your AI features meet quality and performance targets in real-world usage.\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n## How does it work?\n\nGenkit simplifies AI integration with an open-source SDK and unified APIs that\nwork across various model providers and programming languages. It abstracts away complexity so you can focus on delivering great user experiences.\n\nSome key features offered by Genkit include:\n\n* [Text and image generation](https://genkit.dev/docs/models)\n* [Type-safe, structured data generation](https://genkit.dev/docs/models#structured-output)\n* [Tool calling](https://genkit.dev/docs/tool-calling)\n* [Prompt templating](https://genkit.dev/docs/dotprompt)\n* [Persisted chat interfaces](https://genkit.dev/docs/chat)\n* [AI workflows](https://genkit.dev/docs/flows)\n* [AI-powered data retrieval (RAG)](https://genkit.dev/docs/rag)\n\nGenkit is designed for server-side deployment in multiple language environments, and also provides seamless client-side integration through dedicated helpers and [client SDKs](https://genkit.dev/docs/firebase).\n\n## Implementation path\n\n\u003ctable\u003e\n\u003ctr\u003e\n  \u003ctd\u003e\u003cspan\u003e1\u003c/span\u003e\u003c/td\u003e\n  \u003ctd\u003eChoose your language and model provider\u003c/td\u003e\n  \u003ctd\u003eSelect the Genkit SDK for your preferred language (JavaScript/TypeScript, Go, or Python (Alpha)). Choose a model provider like \u003ca href=\"https://genkit.dev/docs/plugins/google-genai\"\u003eGoogle Gemini\u003c/a\u003e or Anthropic, and get an API key. Some providers, like \u003ca href=\"https://genkit.dev/docs/plugins/vertex-ai\"\u003eVertex AI\u003c/a\u003e, may rely on a different means of authentication.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd\u003e\u003cspan\u003e2\u003c/span\u003e\u003c/td\u003e\n  \u003ctd\u003eInstall the SDK and initialize\u003c/td\u003e\n  \u003ctd\u003eInstall the Genkit SDK, model-provider package of your choice, and the Genkit CLI. Import the Genkit and provider packages and initialize Genkit with the provider API key.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd\u003e\u003cspan\u003e3\u003c/span\u003e\u003c/td\u003e\n  \u003ctd\u003eWrite and test AI features\u003c/td\u003e\n  \u003ctd\u003eUse the Genkit SDK to build AI features for your use case, from basic text generation to complex multi-step workflows and agents. Use the CLI and Developer UI to help you rapidly test and iterate.\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd\u003e\u003cspan\u003e4\u003c/span\u003e\u003c/td\u003e\n  \u003ctd\u003eDeploy and monitor\u003c/td\u003e\n  \u003ctd\u003eDeploy your AI features to Firebase, Google Cloud Run, or any environment that supports your chosen programming language. Integrate them into your app, and monitor them in production in the Firebase console.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## Get started\n\n- [JavaScript/TypeScript quickstart](https://genkit.dev/docs/get-started)\n- [Go quickstart](https://genkit.dev/go/docs/get-started-go)\n- [Python quickstart](https://genkit.dev/python/docs/get-started/) (Alpha)\n\n## Development tools\n\nGenkit provides a CLI and a local UI to streamline your AI development workflow.\n\n### CLI\n\nThe Genkit CLI includes commands for running and evaluating your Genkit functions (flows) and collecting telemetry and logs.\n\n- **Install:** `npm install -g genkit-cli`\n- **Run a command, wrapped with telemetry, a interactive developer UI, etc:** `genkit start -- \u003ccommand to run your code\u003e`\n\n### Developer UI\n\nThe Genkit developer UI is a local interface for testing, debugging, and iterating on your AI application.\n\nKey features:\n\n- **Run:** Execute and experiment with Genkit flows, prompts, queries, and more in dedicated playgrounds.\n- **Inspect:** Analyze detailed traces of past executions, including step-by-step breakdowns of complex flows.\n- **Evaluate:** Review the results of evaluations run against your flows, including performance metrics and links to relevant traces.\n\n\u003cimg src=\"docs/resources/readme-ui-traces-screenshot.png\" width=\"700\" alt=\"Screenshot of Genkit Developer UI showing traces\"\u003e\n\n## Try Genkit in Firebase Studio\n\nWant to skip the local setup? Click below to try out Genkit using [Firebase Studio](https://firebase.studio), Google's AI-assisted workspace for full-stack app development in the cloud.\n\n\u003ca href=\"https://studio.firebase.google.com/new/genkit\"\u003e\n  \u003cimg\n    height=\"32\"\n    alt=\"Open in Firebase Studio\"\n    src=\"https://cdn.firebasestudio.dev/btn/open_bright_32.svg\"\u003e\n\u003c/a\u003e\n\n## Connect with us\n\n- [**Join us on Discord**](https://discord.gg/qXt5zzQKpc) – Get help, share\nideas, and chat with other developers.\n- [**Contribute on GitHub**](https://github.com/firebase/genkit/issues) – Report\nbugs, suggest features, or explore the source code.\n- [**Contribute to Documentation and Samples**](https://github.com/genkit-ai/) – Report\nissues in Genkit's [documentation](https://github.com/genkit-ai/docsite), or contribute to the [samples](https://github.com/genkit-ai/samples).\n\n[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/firebase/genkit)\n\n## Contributing\n\nContributions to Genkit are welcome and highly appreciated! See our [Contribution Guide](CONTRIBUTING.md) to get started.\n\n## Authors\n\nGenkit is built by [Firebase](https://firebase.google.com/) with contributions from the [Open Source Community](https://github.com/firebase/genkit/graphs/contributors).\n","funding_links":[],"categories":["MCP Clients","🔌 Integration Tools","Follow","TypeScript","Recently Updated","Clients","📦 Other","Agent Integration \u0026 Deployment Tools","Other Tools and Integrations","クライアント","Large Language Model","Deployment and Serving","Repos","Uncategorized","Table of Contents","2. Libraries \u0026 Frameworks","Other"],"sub_categories":["Weather","Clients \u0026 Interfaces","Dart - Official","[Sep 15, 2024](/content/2024/09/15/README.md)","AI Agent Deployment","🎧 \u003ca name=\"text-to-speech\"\u003e\u003c/a\u003eテキスト読み上げ","DevTools","Java (Unofficial) - Community","Uncategorized","AI Services","JavaScript / TypeScript"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffirebase%2Fgenkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffirebase%2Fgenkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffirebase%2Fgenkit/lists"}