FireConnect

Point Claude Code, Cursor IDE, Codex, Copilot, and the rest at Fireworks with one FireConnect command

FireConnect is the easiest way to use Fireworks models in the coding harness you already use. It is an open-source CLI that rewrites your harness settings to call Fireworks, adds Fireworks models and FireRouter to the model picker, and restores your original settings when you turn it off. You do not need to host a service or edit config files by hand.

Claude Code

Codex CLI, Codex app, and ChatGPT

OpenCode

Cursor IDE

VS Code

More harnesses

Pi, Copilot App and CLI, and DeepSeek Harness

Quick start

1. Install

   curl -fsSL https://fireconnect.fireworks.ai/install.sh | bash
   

   Requires Node.js 18 or later. On Windows, run it from Git Bash; PowerShell breaks the script’s line endings.

   Alternative installer

   curl -fsSL \
     https://raw.githubusercontent.com/fw-ai/fireconnect/main/install.sh \
     | bash
   
2. Sign in

   fireconnect login
   

   Sign in with your browser, or paste a Fireworks key.

3. Connect a harness

   fireconnect claude
   

   Replace claude with any harness from Coding Harnesses. cursor means Cursor IDE only; Cursor CLI is not supported.

4. Restart and check

   fireconnect claude status
   

   status shows the configured model and the Fireworks models in the picker.

Rather edit settings yourself? Each harness in Coding Harnesses has a Manual setup tab with the exact settings FireConnect would write.

In Claude Code

When you select FireRouter in Claude Code, the header shows the active profile:

Claude Code connected through FireRouter

Open /model to choose FireRouter, an open-model router, or a Fireworks model:

Fireworks models and routers in the Claude Code model picker

Connect and restore

• Connect rewrites the harness config to call Fireworks and saves a snapshot under ~/.fireconnect/.
• off restores file-based harnesses from that snapshot byte-for-byte. For IDE databases, it removes the settings and models FireConnect added.
• Sign-in credentials and harness configurations are stored separately. fireconnect login saves your credential through FireConnect’s secret store. If a harness requires the key in its own configuration, FireConnect copies it there and restricts the file permissions. Run fireconnect status to see the active storage backend without revealing the key.

Choose a model

Connecting registers coding-ready Fireworks models, including auto. Use --model when you want to add or select an explicit model or router:

fireconnect claude --model firerouter/opus

Restart or reopen the harness after changing a model. See Coding Harnesses for app-specific rules.

See FireRouter for router behavior, Open Models for aliases and pinned versions, and Harness Compatibility for FireRouter and MCP support.

Use closed models without an LLM gateway

FireConnect does not require an LLM gateway. In Claude Code, routes with Claude models can use your Claude login. Some other harnesses accept a local Anthropic key. OpenAI models need an OpenAI key in Provider Keys. See Harness Compatibility for each harness.

Web search

Web search works through Fireworks with no extra setup. In Claude Code, the native WebSearch and WebFetch tools run server-side on Fireworks. The Codex CLI, the Codex app, and the ChatGPT desktop app keep their native web search. Search works with any Fireworks model or FireRouter ID. Web search pricing will be published soon; see Web Search.

Earlier FireConnect versions installed a fireworks-websearch MCP server for Claude Code. That MCP is no longer available. Run fireconnect upgrade to remove it; your own MCP servers are not changed. See Web Search.

Upgrade and uninstall

For upgrade and uninstall commands, see the CLI Reference.