#6262nd of 82 in Agent frameworks and SDKs
genkit
Multi-language SDK for building LLM flows, tools and agents, with a local dev UI
- Stars
- 6.6k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
5,662 on 4 Apr 20266,562 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Genkit is a framework from Google's Firebase team for adding model calls, structured output, tool calling, RAG and multi-step flows to server-side apps. It has SDKs for JavaScript/TypeScript and Go (production-ready), Python (Beta) and Dart (Preview), with plugins for Google, OpenAI, Anthropic and Ollama. A local CLI and Developer UI run flows, show execution traces and review evaluations.
Who it is for: Developers adding LLM features to TypeScript, Go or Python backends
Strengths
- Same API across TypeScript, Go, Python and Dart SDKs
- Local Developer UI with playgrounds, execution traces and evaluation results
- Provider plugins for Google, OpenAI, Anthropic and Ollama behind one interface
- Deploys to Firebase, Cloud Run or any host that runs the chosen language
Weaknesses
- Python is Beta and Dart is Preview; only JS/TS and Go are production-ready
- Production monitoring dashboard is described in the Firebase console, tying it to Google
- Anthropic plugin is linked from a third-party docs site, not the main docs
- Library only: no hosted UI, user accounts or ready-made agent app
What it needs
- no GPU
- Needs Model provider API key (e.g. Google, OpenAI, Anthropic) or local Ollama
- Models: Google Gemini, OpenAI, Anthropic, Ollama, Vertex AI
Quick answers
Is genkit open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does genkit need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 82| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 90 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #5 | tradingagentsMulti-agent LLM framework that simulates a trading firm's analysis process | 89 out of 100 |