Agentica Server

This is your complete reference for wiring up the Agentica SDK to use Claude CLI as the inference backend through a local proxy. You'll need three terminals running a specific stack: Claude proxy on 8080, agentica-server on 2345, and your agent script pointing at the server. The architecture is straightforward but the environment variables trip people up constantly because the SDK connects to the server and the server connects to the proxy, not the other way around. The skill documents the exact startup sequence, common connection errors, and why your agent might hallucinate success instead of actually using its Read/Write tools. If you're debugging why your Agentica agent can't talk to Claude or keeps describing actions instead of executing them, start here.

skills.sh installs: 476
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill agentica-server --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentica Server + Claude Proxy Setup

Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend.

When to Use

Use this skill when:

Starting Agentica development with Claude proxy
Debugging connection issues between SDK, server, and proxy
Setting up a fresh Agentica environment
Troubleshooting agent tool access or hallucination issues

Architecture

Agentica SDK (client code)
    | S_M_BASE_URL=http://localhost:2345
    v
ClientSessionManager
    |
    v
Agentica Server (agentica-server)
    | INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions
    v
Claude Proxy (claude_proxy.py)
    |
    v
Claude CLI (claude -p)

Environment Variables

Variable	Set By	Used By	Purpose
`INFERENCE_ENDPOINT_URL`	Human	agentica-server	Where server sends LLM inference requests
`S_M_BASE_URL`	Human	Agentica SDK client	Where SDK connects to session manager

KEY: These are NOT the same endpoint!