# genkit-ai/genkit

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/genkit-ai-genkit).**

6,141 stars · 774 forks · TypeScript · Apache-2.0

## Links

- GitHub: https://github.com/genkit-ai/genkit
- Homepage: https://genkit.dev
- awesome-repositories: https://awesome-repositories.com/repository/genkit-ai-genkit.md

## Description

Genkit is an LLM application framework and generative AI developer toolkit designed for building production AI applications. It serves as an AI workflow orchestrator that coordinates model calls and agentic tool usage through type-safe execution flows.

The project provides a unified model interface and plugin architecture to standardize access to diverse large language models, vector stores, and telemetry backends. It distinguishes itself with a dedicated observability suite for tracing execution steps and a developer toolkit for prompting, debugging, and evaluating AI logic via a local interface.

The framework covers a broad capability surface including agent orchestration with tool-calling and sub-agent delegation, retrieval-augmented generation via vector database integration, and structured output generation using schema-based validation. It also includes systems for stateful session management, event-based response streaming, and the ability to expose AI flows as scalable HTTP endpoints.

Development is supported by a command-line interface for running functions and managing logs.

## Tags

### Artificial Intelligence & ML

- [AI Workflow Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-orchestration.md) — Coordinates model calls and tool usage through type-safe execution flows with built-in tracing. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [LLM Application Development](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/llm-application-development.md) — Provides standardized interfaces for model interaction and data retrieval to build production LLM applications.
- [Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-integrations.md) — Connects AI models to external functions and APIs to perform complex tasks and retrieve real-time data. ([source](https://github.com/genkit-ai/genkit#readme))
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Offers unified interfaces for connecting and configuring multiple different language model providers. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [AI Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-orchestration.md) — Coordinates specialized agents that combine custom instructions, tools, and document retrieval.
- [Tool Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-model-integrations/tool-definitions.md) — Provides a system for defining the schemas and logic of functions that AI models can invoke. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [AI Observability Suites](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-observability-suites.md) — Ships a diagnostic toolkit for tracing, evaluating, and monitoring the performance and quality of LLM applications.
- [AI Observability Tracing](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-observability-tracing.md) — Records every step of model invocations and tool calls to provide detailed execution timelines.
- [Observable Flow Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-observability-tracing/observable-flow-definitions.md) — Wraps AI logic into flows with built-in observability, tracing, and deployment capabilities. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [AI Workflow Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-orchestrators.md) — Manages multi-step reasoning and operational sequences through type-safe execution flows.
- [Retrieval Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation.md) — Grounds model responses in private or up-to-date information by integrating external data retrieval. ([source](https://github.com/genkit-ai/genkit#readme))
- [LLM Application Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-application-frameworks.md) — Provides methodologies and patterns for building production applications powered by large language models.
- [LLM Response Streaming](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-response-streaming.md) — Delivers model outputs to frontends incrementally to reduce perceived latency. ([source](https://github.com/genkit-ai/genkit/tree/main/samples))
- [Structured Output Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-code-generators/structured-generation-engines/structured-output-generators.md) — Forces models to return data in specific formats and validates results against predefined schemas. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [RAG Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/rag-implementations.md) — Implements architectures that retrieve relevant documents from vector stores to augment prompt context.
- [Agent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-delegation.md) — Implements mechanisms for a primary agent to assign tasks to specialized sub-agents. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [HTTP Agent Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-integration-apis/http-agent-servers.md) — Serves stateful agents as HTTP endpoints to handle conversational turns via web requests. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [AI Performance Monitoring](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-performance-monitoring.md) — Tracks request volumes, latency, and error rates via a production observability dashboard. ([source](https://github.com/genkit-ai/genkit#readme))
- [Automated Output Evaluation](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-output-evaluation.md) — Provides automated tools to score model responses for quality, safety, and correctness. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [Context-Aware Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/context-aware-generation.md) — Produces text, images, and type-safe data using prompt templates and context-aware generation. ([source](https://github.com/genkit-ai/genkit#readme))
- [Conversational Session Management](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-session-management.md) — Tracks unique session identifiers to maintain context across multi-turn interactions. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [Event-Driven Model Streaming](https://awesome-repositories.com/f/artificial-intelligence-ml/event-driven-model-streaming.md) — Delivers model output incrementally using Server-Sent Events to reduce perceived latency.
- [Persistent Chat Histories](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/persistent-chat-histories.md) — Maintains conversation state and history across user sessions to support multi-turn dialogue. ([source](https://github.com/genkit-ai/genkit#readme))
- [Conversational Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-models/conversational-interfaces.md) — Connects large language models to frontends to create real-time conversational interfaces. ([source](https://github.com/genkit-ai/genkit/tree/main/samples))
- [AI Flow Response Streams](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities/real-time-streaming/agent-response-streams/ai-flow-response-streams.md) — Sends real-time data from AI flows to clients using Server-Sent Events. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [Prompt Templates](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-templates.md) — Standardizes model instructions using template files with variables and schemas. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [Text Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-numeric-transformations/text-embeddings.md) — Transforms text into vector representations for use in similarity searches and retrieval pipelines. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [AI Flow API Endpoints](https://awesome-repositories.com/f/artificial-intelligence-ml/unified-ai-api-endpoints/ai-flow-api-endpoints.md) — Exposes AI workflows as programmable API endpoints for external integration. ([source](https://github.com/genkit-ai/genkit/tree/main/go))

### Data & Databases

- [Schema Validators](https://awesome-repositories.com/f/data-databases/data-governance-modeling/data-modeling-schemas/data-schemas/schema-validated-data-structures/schema-enforced-output-parsers/llm-schema-outputs/schema-validators.md) — Validates generated JSON responses against predefined schemas to ensure type-safe structured output.
- [Structured JSON Generation](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-serialization/json-schema/structured-json-generation.md) — Produces JSON output that maps directly to predefined, type-safe data structures. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [Vector Database Integrations](https://awesome-repositories.com/f/data-databases/vector-database-integrations.md) — Provides an integration layer for embedding text and retrieving content from specialized vector databases.
- [Vector Document Indexing](https://awesome-repositories.com/f/data-databases/database-management-systems/database-engines/vector-databases/vector-document-indexing.md) — Indexes documents into vector stores to enable efficient similarity searches. ([source](https://github.com/genkit-ai/genkit/tree/main/py))
- [Indexed Document Retrieval](https://awesome-repositories.com/f/data-databases/search-indexing/indexed-document-retrieval.md) — Searches vector stores to retrieve documents related to a specific query. ([source](https://github.com/genkit-ai/genkit/tree/main/py))

### Development Tools & Productivity

- [AI Development Toolkits](https://awesome-repositories.com/f/development-tools-productivity/ai-development-toolkits.md) — Provides a comprehensive set of tools for prompting, debugging, and evaluating AI logic via a local interface.
- [Tool-Call Orchestrators](https://awesome-repositories.com/f/development-tools-productivity/workflow-automation-triggers/tool-call-orchestrators.md) — Maps model-generated parameters to executable code and manages the return of results to the model.
- [Agent Session Persistence](https://awesome-repositories.com/f/development-tools-productivity/database-session-management/session-state-persistence/agent-session-persistence.md) — Persists conversation history and state across requests to maintain context for agentic interactions.
- [Local AI Workflow Debuggers](https://awesome-repositories.com/f/development-tools-productivity/workflow-automations/ai-driven-debugging-workflows/local-ai-workflow-debuggers.md) — Includes local developer interfaces for inspecting and stepping through AI workflows to refine logic. ([source](https://github.com/genkit-ai/genkit/blob/main/README.md))

### Software Engineering & Architecture

- [Provider Plugins](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/extensibility/third-party-plugins/provider-plugins.md) — Standardizes access to diverse LLMs and vector stores through a common plugin-based interface.
- [Unified Model Interfaces](https://awesome-repositories.com/f/software-engineering-architecture/unified-model-interfaces.md) — Provides a standardized API that maintains a consistent execution interface across diverse model providers. ([source](https://github.com/genkit-ai/genkit#readme))
- [AI Model Middleware](https://awesome-repositories.com/f/software-engineering-architecture/middleware/custom-middleware-implementations/ai-model-middleware.md) — Wraps model calls to implement cross-cutting behaviors such as retries and fallbacks. ([source](https://github.com/genkit-ai/genkit/tree/main/go))
- [Request Interception Middleware](https://awesome-repositories.com/f/software-engineering-architecture/request-interception-middleware.md) — Wraps model calls and tool executions in a chain of functions for logging and safety checks.
- [Model Call Interceptors](https://awesome-repositories.com/f/software-engineering-architecture/request-interception-middleware/model-call-interceptors.md) — Offers architectural hooks to intercept and modify language model requests and responses for logging and safety. ([source](https://github.com/genkit-ai/genkit/tree/main/py))

### Part of an Awesome List

- [AI Workflow Testing Interfaces](https://awesome-repositories.com/f/awesome-lists/devtools/development-and-debugging/ai-workflow-testing-interfaces.md) — Offers local development interfaces for testing and debugging AI workflows before production deployment. ([source](https://github.com/genkit-ai/genkit#readme))
- [Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/agent-frameworks.md) — Google-backed framework for building AI-powered applications.

### DevOps & Infrastructure

- [AI Deployment Frameworks](https://awesome-repositories.com/f/devops-infrastructure/cloud-deployment/ai-deployment-frameworks.md) — Provides configurations and tools for deploying AI-specific workloads to cloud functions and containers. ([source](https://github.com/genkit-ai/genkit/blob/main/README.md))

### Networking & Communication

- [Incremental Data Streamers](https://awesome-repositories.com/f/networking-communication/api-integration-frameworks/http-client-libraries/http-client-utilities/response-streaming/incremental-data-streamers.md) — Yields validated text or structured JSON objects incrementally as the model generates them. ([source](https://github.com/genkit-ai/genkit/tree/main/go))

### Testing & Quality Assurance

- [AI Logic Verification](https://awesome-repositories.com/f/testing-quality-assurance/ai-logic-verification.md) — Provides tools for executing AI prompts and comparing outputs to verify the correctness of generative logic. ([source](https://github.com/genkit-ai/genkit#readme))