Awesome GitHub RepositoriesTrajectory-Based Agent Optimization

Ruflo is an AI agent orchestration platform and workflow automation tool designed to decompose high-level goals into executable action plans. It functions as a manager for multi-agent swarms, organizing autonomous entities into collaborative topologies that utilize shared consensus to complete complex tasks. The framework distinguishes itself through a retrieval-augmented generation layer and knowledge graphs for reasoning over linked data. It incorporates a trajectory-based learning loop that analyzes previous execution paths to refine cognitive patterns and improve future reasoning accuracy

ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin

Klavis is a platform for managing Model Context Protocol (MCP) servers and providing sandboxed environments where AI agents can safely interact with external tools and services. It functions as an integration framework that orchestrates MCP server instances, exposes tools and resources for AI agents, and isolates agent interactions from production data through horizontally scalable sandbox environments. The platform distinguishes itself through its ability to generate long-horizon agentic tasks that simulate realistic tool-use workflows with live SaaS applications and production MCP servers.

OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca