pickfit

BrowseDeveloper CLIs

cc-copilot-bridge

Bash router that switches Claude Code CLI between Anthropic, Copilot, and Ollama.

Tested on Linux

Use it

Linux x86_64

You need first

  • System packages: jq, nc
  • Keys or accounts: ANTHROPIC_API_KEY
  1. Download install.sh for reading before running

    curl -fsSL https://raw.githubusercontent.com/FlorianBruniaux/cc-copilot-bridge/main/install.sh -o /tmp/install.sh
  2. Create dirs and run install.sh non-interactively

    mkdir -p ~/.claude ~/bin && printf '\n\n\n' | bash /tmp/install.sh

    Runs a downloaded script: read it before you run it.

  3. Put claude-switch on PATH via ~/.local/bin symlink

    mkdir -p ~/.local/bin && ln -sf ~/bin/claude-switch ~/.local/bin/claude-switch
Where the README and reality differ
  • README: curl -fsSL .../install.sh | bash works on fresh machine
    What worked: mkdir -p ~/.claude before running install.sh; reran with dir present

Check that it works

claude-switch --help

The output should contain “Claude Code Multi-Provider Switcher v1.7.0”.

First thing to try

claude-switch status

Run claude-switch status to see which provider Claude Code is currently set to use.

What it does

  • Route Claude Code through different providers
    Not shown working
  • Switch between Anthropic, Copilot and Ollama
    Not shown working
  • Use Claude, GPT and Gemini models
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • switch Claude Code CLI between Anthropic, Copilot, and Ollama
  • use Claude Code with existing GitHub Copilot subscription
  • run Claude Code offline with Ollama for proprietary code

An alternative to @musistudio/claude-code-router and OpenCode.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.7.0

Differences the test machine hit

  • README: installer puts claude-switch on PATH
    In the test: symlink ~/bin/claude-switch to ~/.local/bin/claude-switch (installer uses ~/bin, PATH starts with ~/.local/bin)
  • README: ccs
    In the test: source ~/.claude/aliases.sh and eval ccs (ccs is a shell alias, not a binary; non-interactive bash needs eval/interactive shell)

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.