skills.rest
Mesh-LLM
Mesh-LLMOFFICIAL
Explore all skills by this author →
WebsiteGitHub

connect-agents

Connect agent tools and OpenAI clients to a mesh-llm node.

3.1k|376|Updated Feb 11, 2026
Search Tags:#tooling#agents#openai#goose#connect#model-validation#mesh-llm
One-click install
npx skills add https://github.com/Mesh-LLM/mesh-llm --skill connect-agents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: connect-agents
Source: https://github.com/Mesh-LLM/mesh-llm/tree/main/.skills/connect-agents
Command: npx skills add https://github.com/Mesh-LLM/mesh-llm --skill connect-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Connects agent tools and OpenAI clients to a running mesh-llm node, enabling tool-enabled prompts, model routing, and centralized management. See docs/AGENTS.md for full reference.

Core Features & Use Cases

  • Built-in launchers (goose, claude, opencode, pi) that inject configuration and start a local client connected to the mesh.
  • Manual config guidance for any OpenAI client using the base URL http://<host>:9337/v1 with a non-empty API key.
  • Validating agent behavior and tool-call reliability with reference to the agent harness and mesh model routing.
  • Blackboard cross-mesh coordination with the blackboard plugin for cross-node status sharing (optional).

Quick Start

Connect an agent harness to the mesh-llm endpoint and verify a tool-enabled chat by issuing a request to http://127.0.0.1:9337/v1/chat/completions.

Frequently Asked Questions about connect-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect OpenAI clients to a custom mesh for tool-enabled prompts?▼

You can connect OpenAI clients to a mesh-llm node by configuring the base URL http://<host>:9337/v1 and providing a non-empty API key, which enables tool-enabled prompts and model routing validation.

Can I use Goose or Claude Code with a local mesh-llm endpoint?▼

Yes, built-in launchers for Goose and Claude Code inject configuration and start a local client connected to the mesh-llm endpoint, automatically validating tool access and model routing.

What is needed to validate agent behavior and tool execution on a remote mesh?▼

Validating agent behavior on a remote mesh requires the base URL http://<host>:9337/v1, a non-empty API key, and optional host overrides to configure and verify tool execution against the OpenAI-compatible API.

How do I test tool-enabled chat completions using curl against an OpenAI-compatible API?▼

You can test tool-enabled chat completions by issuing a curl request to http://127.0.0.1:9337/v1/chat/completions after configuring your client with a non-empty API key and the correct base URL.

Does mesh-llm support cross-node status sharing for coordinated agent tasks?▼

Yes, mesh-llm supports cross-node status sharing through the optional blackboard plugin, enabling cross-mesh coordination for distributed agent tasks across multiple running nodes.

Related Skills

Explore More Software Engineering Skills→
syeda-hoorain-alisyeda-hoorain-ali

llm-provider-configuration

Configure the OpenAI Agents SDK with a custom base URL and API key for alternative LLM providers.

Community
Intermediate
NaimalArain13NaimalArain13
2

chatkit-python

Build a FastAPI chat backend with SSE streaming and conversation persistence.

Community
Intermediate
LLM-Dev-OpsLLM-Dev-Ops
1

AgentDB Advanced Features

Configure distributed AgentDB clusters with QUIC synchronization and hybrid search.

Official
Advanced
SalmanO7SalmanO7

llm-provider-configuration

Configure the OpenAI Agents SDK with custom base URLs and API keys for alternative LLM providers.

Community
Intermediate