
Genkit is Google's open-source framework for developers building AI applications and agents with local or cloud models. Its shared API connects to Ollama as well as hosted providers such as Gemini, OpenAI and Anthropic. You can host the application logic yourself. The framework uses the Apache 2.0 license.
Model choice determines where inference happens: Ollama supports local LLM use, while hosted providers process model requests through their services. Genkit's server-side code can run wherever its programming language is supported, including your own server, Firebase or Google Cloud Run. Google services are optional.
For application features, Genkit supports text and image generation, multimodal input and output, and structured data that matches declared types. Tool calling lets models use application functions, while workflows support tasks with multiple steps. It also includes prompt templates, persisted chat and retrieval-augmented generation (RAG) for answers grounded in retrieved information.
The local Developer UI gives developers a place to test prompts and workflows, compare model outputs and inspect execution traces. Tests can use individual inputs or datasets. Production monitoring tracks latency, errors, request volumes and model performance, with a dashboard in Firebase.
JavaScript/TypeScript and Go have full feature support. Client SDKs and helpers connect the server-side AI logic to web and mobile apps, including Next.js, React, Angular, iOS and Android.
Claim this page with an email at genkit.dev. Genkit gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Genkit?Promote it
Something wrong or outdated on this page?
3.9KUpdated 1 week agoApache-2.0
Docker · Web#Distributed execution#LoRA#MCP
LazyLLM is a Python framework for developers building multi-agent applications with locally deployed models or cloud services. It combines application assembly with data preparation, evaluation and model fine-tuning, so developers can test a prototype and improve the parts that perform poorly. It's open source under Apache 2.0.
38.5KUpdated 23 hours agoMIT
#Code execution#MCP#Multimodal input
10.7KUpdated 4 days agoMIT
Web#Guardrails#Human approval#LLM tracing
9.4KUpdated 2 hours agoApache-2.0
macOS · Windows · Linux · iOS · Android · Web#Batch processing#LLM tracing#Structured output
3.1KUpdated 3 days agoApache-2.0
macOS · Windows · Linux · Web#Code execution#MCP#Multi-agent workflows
5.1KUpdated 2 days ago
macOS · Windows · Linux#Git integration#MCP#Multi-agent workflows
Kiln is a desktop workbench for teams building AI applications on macOS, Windows and Linux. It keeps a task and its dataset together across evaluation, prompt optimization, RAG and fine-tuning, so teams can compare changes against the same examples. Engineers, data scientists, QA staff and subject matter experts can contribute through the app.
DSPy is a Python framework for developers building AI applications whose tasks need clear inputs, predictable output types, and measurable results. You define what a language model should produce, then compose those tasks into a larger program. It's open source under the MIT license.
VoltAgent is an MIT-licensed TypeScript AI agent framework for developers building assistants and automated workflows. It pairs code-based agent development with VoltOps, a console for inspecting execution and managing agents. The console can run on your own server or as a cloud service; managed deployment uses hosted infrastructure.
BAML is a programming language for developers building AI agents, with typed model calls and local tracing built into the language. It runs standalone on macOS, Linux and Windows, or alongside an existing application. The language is open source under Apache 2.0, and works offline.
BotSharp is a self-hosted framework for .NET developers building AI agents into business applications. Written in C#, it runs on Windows, Linux and macOS and is open source software under Apache 2.0. Its plugin design lets teams choose their model provider, storage and interface while keeping agent coordination in the same framework.