NVlabs/ToolOrchestra

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

57
/ 100
Established

ToolOrchestra helps AI developers and researchers train specialized AI models to efficiently solve complex, multi-step problems. It takes in a challenging task and orchestrates the use of various AI tools, including search engines, code interpreters, and other large language models, to produce an accurate and cost-effective solution. This is ideal for those building or evaluating advanced AI agents.

677 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you are an AI researcher or developer focused on building and optimizing intelligent agents that need to use multiple tools and models to solve complex, multi-turn tasks efficiently.

Not ideal if you are looking for a pre-built, general-purpose AI application rather than a framework for training and evaluating specialized AI orchestrators.

AI Agent Development Reinforcement Learning Large Language Model (LLM) Orchestration Complex Task Automation AI Research
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 21 / 25

How are scores calculated?

Stars

677

Forks

92

Language

Python

License

Apache-2.0

Last pushed

Jan 27, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/NVlabs/ToolOrchestra"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.