datarobot/syftr
syftr is an agent optimizer that helps you find the best agentic workflows for your budget.
This tool helps AI application developers find the most efficient and accurate configurations for their AI workflows, especially those involving Large Language Models. You provide your own dataset and define the possible components (like different LLMs or RAG strategies). The tool then analyzes these options and outputs a set of optimal workflow configurations that balance performance (like accuracy) with competing factors like cost and speed.
330 stars. Available on PyPI.
Use this if you are building AI applications and need to systematically discover the best trade-off between performance metrics like accuracy and operational constraints like cost or latency for your agentic or non-agentic workflows.
Not ideal if you are a business user looking for a no-code solution to optimize existing reports or dashboards, as this tool requires familiarity with AI application development.
Stars
330
Forks
28
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Dependencies
102
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/datarobot/syftr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
elizaOS/eliza
Autonomous agents for everyone
Agent-Field/agentfield
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and...
gptme/gptme
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses...
SolaceLabs/solace-agent-mesh
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables...
langgenius/dify
Production-ready platform for agentic workflow development.