EONYX is a terminal AI agent for working with code, written in Go. It connects directly to any OpenAI-compatible API (OpenAI, OpenRouter, DeepSeek, Moonshot, local Ollama / llama.cpp / LM Studio) — no external services, no telemetry, no OAuth. One process, one binary, everything local. Here: installation, the first run, and the full configuration.

Model Context Protocol (MCP) is an open standard through which an agent gains access to external systems: databases, APIs, issue trackers and any other services. EONYX has a built-in MCP client based on the official Go SDK (modelcontextprotocol/go-sdk) — servers are described right in eonyx.json and their tools show up for the model alongside the built-in ones.

One of the key differences of EONYX is that it is not tied to the cloud. Since the agent talks to any OpenAI-compatible API, you can point it at a local model server and work fully offline: the code never leaves the machine, no key is needed, and neither is the internet.

Every agent turn starts with the model receiving context. In EONYX it is built from three mechanisms: AGENTS.md — the project’s persistent instructions, sessions — the full conversation history on disk, and auto-summarization — compaction of older turns once the history approaches the limit of the context window.

EONYX and Claude Code are both terminal AI agents for working with code, and their workflow is similar: MCP, skills, hooks, subagents, plan mode, sessions. The difference is in the architecture and the freedom. Claude Code is tied to the cloud and to Anthropic models; EONYX is not. Here is what that gives you in practice.

A skill is a folder with a SKILL.md file: an instruction the agent loads when a task matches it. Skills let you package repetitive procedures — a code review, a deploy checklist, the rules for formatting a report — so that they don’t take up context until they’re needed.

EONYX talks to any OpenAI-compatible API. A provider is the way to reach a backend, a model binds an id to a provider. Here is how to connect cloud providers, hide secrets and configure price, context window and retries.

EONYX is written in Go and builds into a single static binary. Inside is a tidy set of packages built around one central abstraction. Let’s walk through how it is put together — useful both for contributors and for understanding the agent’s behaviour.

Hooks are shell commands that EONYX runs around tool calls: before (before) and after (after). They are a convenient way to bolt on auto-formatting, auditing, checks and guardrails without touching the agent’s code.

An agent that reads and edits code and runs commands must operate within explicit permissions. In EONYX security is several layers: a static gateway, a file sandbox, plan mode and a coarse block on dangerous commands. Let’s go through each of them.