by datarobot · Agent Tool · ★ 330
Efficient Search for Pareto-optimal Flows syftr is an agent optimizer that helps you find the best agentic workflows for a given budget. You bring your own dataset, compose the search space from models and components, and syftr finds the best combination of parameters for your budget. It uses advances in multi-objective Bayesian Optimization and a novel domain-specific "Pareto Pruner" to efficiently sample a search space of agentic and non-agentic flows to estimate a Pareto-frontier (optimal trade-off curve) between accuracy and objectives that compete like cost, latency, throughput.
| Stars | 330 |
| Forks | 28 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.1163875543185/100 |
| Open Issues | 20 |
| Last Updated | 2026-03-04 |
| Created | 2025-05-20 |
| Platforms | python |
| Est. Tokens | ~225k |
These tools work well together with syftr for enhanced workflows:
Explore other popular agent tool tools:
syftr is syftr is an agent optimizer that helps you find the best agentic workflows for your budget.. It is categorized as a Agent Tool with 330 GitHub stars.
syftr is primarily written in Python. It covers topics such as agents, ai, ai-agents.
You can find installation instructions and usage details in the syftr GitHub repository at github.com/datarobot/syftr. The project has 330 stars and 28 forks, indicating an active community.
syftr is released under the MIT license, making it free to use and modify according to the license terms.