pickfit

BrowseDeveloper CLIs

Orbit

Local-first runtime that queues coding-agent tasks and delivers them via sandboxed worktrees.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Node 18+
  1. Install Orbit CLI globally via npm

    npm install -g @orbit-tools/cli

Check that it works

orbit --version

The output should contain “orbit 0.38.0”.

First thing to try

orbit init --non-interactive --machine-name box --task-prefix BOX

In a git repository, run orbit workspace init --ship-mode local to set up Orbit for that project.

Linux x86_64

You need first

  • Runtimes: Node 18+
  1. install @orbit-tools/cli globally via npm

    npm install -g @orbit-tools/cli && orbit --version
Where the README and reality differ
  • README: README examples imply filing tasks via agent prompt
    What worked: orbit task add requires --title and --complexity; --prompt is not a flag, use --description

Check that it works

orbit --version

The output should contain “orbit 0.39.0”.

First thing to try

mkdir -p /tmp/orbit-demo && cd /tmp/orbit-demo && git init -q && git config user.email "test@test.com" && git config user.name "test" && touch README.md && git add . && git commit -qm init && orbit workspace init --ship-mode local && echo WORKSPACE_INIT_OK && ls -la .orbit/
cd /tmp/orbit-demo && orbit task add --title "Add hello.txt" --description "Add hello.txt containing hello" --complexity low --status backlog 2>&1

In a git repository, run orbit workspace init --ship-mode local to set up Orbit for that project.

What it does

  • Queue coding tasks that persist
    How to use it
    1. Inside a git repository, run orbit workspace init --ship-mode local once.
    2. Add a task with orbit task add --title "<title>" --description "<description>" --complexity low --status backlog.
    3. Note the task ID it prints, such as ORB-00000.
    Tested
  • Run agents in isolated worktrees
    Not tested
  • Deliver changes through a gated pipeline
    Not tested
  • Audit the prompt, plan and review
    Not shown working

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

Linux x86_64

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

Good for

  • run queued tasks through plan, execute and review in isolated worktrees
  • open a pull request for task output and close task after merge
  • inspect a task or run
  • open the dashboard to watch tasks
  • pick the default provider and model crew

How pickfit tested it

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

macOS arm64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 29 Oct 2026
  • Version 0.38.0

Differences the test machine hit

  • README: orbit init
    In the test: run non-interactively as `orbit init --non-interactive --machine-name box --task-prefix BOX` (any 2-5 uppercase-letter prefix); stdin is closed so the interactive prompts cannot be answered

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.39.0

Differences the test machine hit

  • README: orbit doctor
    In the test: orbit doctor exits 1 when checks fail (1 failure for missing machine identity); exit 1 signals findings not a crash
  • README: locks gate dispatch
    In the test: orbit task locks needs a subcommand (locks list); bare locks prints usage with exit 2

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.