xerrors/Yuxi

xerrors/Yuxi

Agent

A guide for adding or maintaining an Agent backend in Yuxi, the software that runs an Agent's code. It explains where backend files go and how Yuxi discovers them.

xerrors/Yuxi

Agent

An evaluation workflow for AI agents that runs a fixed set of tasks through a real agent, its workers, and its tools, then records an experiment in Langfuse. Langfuse is a service for tracing and evaluating AI applications.

xerrors/Yuxi

Agent

A first-in, first-out request queue for agent conversations. It stores incoming requests, runs only one ordinary request at a time per conversation thread, and lets other requests wait, be cancelled, or be rejected.

xerrors/Yuxi

Agent

A reference for configuring software agents: programs that use a language model, tools and instructions to perform tasks. It explains how saved settings become the fields shown in an agent's configuration page and how those settings affect a run.

xerrors/Yuxi

Agent

A setup for MCP, a standard way for an AI agent to discover and call tools provided by outside services. It lets administrators add remote MCP servers and choose which servers and tools each agent can use.

xerrors/Yuxi

Agent

Middleware guidance for connecting files, reusable skills, sub-agents, memory, context shortening, approvals, and usage tracking to a LangGraph agent. LangGraph is a framework for building agents as connected steps or states.

xerrors/Yuxi

Agent

A guide to configuring isolated workspaces where an agent can safely run files and commands, using Docker containers or Kubernetes Pods.

xerrors/Yuxi

Agent

A management guide for skills, which are reusable instruction packages for agents. It explains how skills are stored, selected, shared, overridden, created, and removed.

xerrors/Yuxi

Agent

A management system for sub-agents, which are separate agents that a main agent can call for smaller tasks. They have their own configuration and cannot call another sub-agent.

xerrors/Yuxi

Agent

A tool-registration system for Yuxi agents, covering built-in tools, knowledge-base tools, and MCP tools. It controls how tools are defined and exposed to agents.