horizon-rl/strands-sglang
SGLang model provider for Strands Agents for on-policy agentic RL training.
This project helps machine learning engineers or researchers who are developing and training AI agents using reinforcement learning. It enables the Strands Agents SDK to work seamlessly with SGLang models, allowing for precise, token-level data capture during agent interactions. You feed it a language model and a task, and it produces an agent's responses along with detailed token data (token IDs, log probabilities, and loss masks) essential for training and evaluation.
Available on PyPI.
Use this if you are developing AI agents with the Strands Agents SDK and need to integrate SGLang models for reinforcement learning training, ensuring accurate, token-level data capture without retokenization issues.
Not ideal if you are looking for a general-purpose AI agent for end-user applications or if you don't require token-level data for on-policy reinforcement learning.
Stars
50
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/horizon-rl/strands-sglang"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
awslabs/agent-squad
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
jeremiah-k/agor
AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into...
microsoft/multi-agent-reference-architecture
Guide for designing adaptive, scalable, and secure enterprise multi-agent systems
rodmena-limited/stabilize
Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage...
aws-solutions-library-samples/guidance-for-multi-agent-orchestration-on-aws
Enables developers to build, deploy, and manage multiple specialized agents that work together...