Flyte 2 lets you define tasks and workflows in plain Python with async/await, then run them locally, through the flyte CLI, or on a remote backend. The same SDK deploys model-serving apps such as FastAPI endpoints. The open-source backend in this repository is not released yet; a production backend is offered by Union.ai.
Who it is for: ML and platform engineers orchestrating pipelines and model serving in Python
Strengths
Workflows are plain Python with asyncio.gather fan-out, no DSL or YAML
Same code runs via python script or the flyte CLI
Local Devbox, Codespaces and an optional TUI for development
LF AI & Data Graduated project under Apache-2.0
Weaknesses
Open-source Flyte 2 backend is listed as coming soon
Production-grade backend currently comes from Union.ai, a commercial service
Flyte 1 lives on the master branch, which splits code and docs
SDK code lives in a separate flyte-sdk repository
What it needs
Docker
Needs Python, Kubernetes (planned OSS backend)
Quick answers
Is flyte open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run flyte with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder
Live demo ↗
(opens in a new tab)188k stars+853 (+0.5%) in 30 dayscustom license
95 out of 100score
2
daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps69.9k stars+3,683 (+5.6%) in 30 daysMIT
95 out of 100score
3
LangflowVisual builder for AI agents and workflows, exposed as API or MCP server156.5k stars+1,251 (+0.8%) in 30 daysMIT
94 out of 100score
#4
deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills85.2k stars+1,752 (+2.1%) in 30 daysMIT
93 out of 100score
#5
DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs
Live demo ↗
(opens in a new tab)161k stars+3,111 (+2.0%) in 30 dayscustom license