Editor Code Assistant AI Pair Programming
in Any Editor

A free, open-source, editor-agnostic tool that connects LLMs to your editor through a well-defined protocol — giving you the best AI coding experience everywhere.

Get Started GitHub
ECA — Emacs
ECA running in Emacs
Install in Emacs
ECA — VS Code
ECA running in VS Code
Install in VS Code
ECA — IntelliJ
ECA running in IntelliJ
Install in IntelliJ
ECA — Neovim
ECA running in Neovim
Install in Neovim
ECA — Desktop
ECA running as a Desktop app
Install Desktop version
ECA — CLI
ECA running in the terminal
Install CLI version

Why ECA?

A protocol-first approach to AI coding — one server connecting any editor to any LLM.
For ones interested in being in the loop inside your editor.

ECA rationale — LLMs connected to editors via protocol
Editor-Agnostic Protocol Inspired by LSP — any editor can integrate. One server, many clients.
Single Configuration Configure once, same experience everywhere — global or per-project.
Multi-Model Support OpenAI, Anthropic, Copilot, Ollama, and many more. Switch freely.
Free & Open Source Built with Clojure. Community-driven, transparent, and extensible.
OpenTelemetry Export metrics of tools, prompts, and server performance.

Major Features

Three core interactions powered by LLMs, plus a rich ecosystem of configuration and extensibility.

Chat

Pair program with an AI agent that can read, write, and refactor your code. Supports rollback, context injection, and multi-turn conversations.

Learn more

Rewrite

Select code, describe the change, accept or reject the diff. Fast, low-ceremony edits that work great with lightweight models.

Learn more

Completion

Inline AI-powered code suggestions as you type — multi-line, context-aware, similar to Copilot-style predictions.

Learn more
Agents & Intelligence

Agents & Subagents

Built-in code and plan agents, with subagents for isolated parallel tasks and context window savings.

Tools & MCP

Native file/shell/editor tools, MCP server integration, and custom tool definitions with fine-grained approval control.

Context

Attach files, directories, cursor position, MCP resources, or AGENTS.md auto-context to any prompt.

Customization & Extensibility

Rules

Define coding standards, conventions, and constraints the LLM must follow — globally or per project.

Skills

Structured knowledge units that teach the LLM how to handle specific tasks. Follows the agentskills.io spec.

Commands

Slash commands like /init, /compact, /resume, and custom commands you define yourself.

Hooks

Before/after event callbacks to validate, notify, or trigger side effects on tool calls and prompts.

Variants

Switch between configuration presets on the fly — different models, reasoning effort, or custom setups.

Metrics

OpenTelemetry integration for exporting tool usage, prompt performance, and server metrics.

Plugins

Extend ECA with community plugins — bundles of tools, rules, skills, and more from the marketplace.

Remote

Observe and control your chat session from a browser via an embedded web server and web.eca.dev.

One Config To LLM Them All

Everything is driven by a single JSON config. Here are a few things you can do.

Custom
Providers

Use any LLM provider

Built-in support for OpenAI, Anthropic, Copilot, Gemini, and Ollama. Point to any OpenAI-compatible API — DeepSeek, LM Studio, OpenRouter, your company’s internal endpoint — with a few lines of config.

Explore models config
~/.config/eca/config.json 
{
  "providers": {
    "my-company": {
      "api": "openai-chat",
      "url": "${env:MY_COMPANY_API_URL}",
      "key": "${env:MY_COMPANY_API_KEY}",
      "models": {
        "gpt-5": {},
        "deepseek-r1": {}
      }
    }
  }
}
Skills

Teach the LLM new abilities

Skills are structured knowledge units the agent loads on demand. Bundle instructions, scripts, and assets into a folder — the LLM learns to use them when the task matches. Follows the agentskills.io spec.

Explore skills config
~/.config/eca/skills/lint-fix/SKILL.md 
---
name: lint-fix
description: Learn how to lint and fix code
---

# Instructions

Run `clojure-lsp diagnostics` to find issues.
For each diagnostic, apply the suggested fix.
Always run diagnostics again after fixing to
confirm no regressions.
Hooks

Automate before & after events

Intercept tool calls to enforce policies, get desktop notifications when prompts finish, or run validation scripts automatically. Wire any shell command to any ECA event.

Explore hooks config
~/.config/eca/config.json 
{
  "hooks": {
    "notify-me": {
      "type": "postRequest",
      "visible": false,
      "actions": [{
        "type": "shell",
        "shell": "notify-send 'Prompt finished!'"
      }]
    }
  }
}
MCP Servers

Plug in any MCP server

Connect MCP-compatible servers for memory, databases, APIs, or anything else. Tools, resources, and prompts from the server become automatically available to the agent.

Explore MCP config
~/.config/eca/config.json 
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    },
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres",
              "${env:DATABASE_URL}"]
    }
  }
}
Custom Agents

Build specialized AI teammates

Create agents and subagents with their own system prompts, models, and tool access. Subagents run in isolated contexts for parallel work without polluting the main conversation.

Explore agents config
~/.config/eca/config.json