pickfit

BrowseDeveloper CLIs

code-evolve

Autonomous CLI that builds and improves a project from a vision and spec across scheduled sessions.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js >= 18, Python 3
  • System packages: Git
  • Keys or accounts: ANTHROPIC_API_KEY, OPENAI_API_KEY
  1. Install code-evolve globally via npm

    npm install -g code-evolve

Check that it works

code-evolve --version

The output should contain “0.2.0”.

First thing to try

mkdir -p evolve-demo/docs && cat > evolve-demo/docs/technical-spec.md <<'EOF'
# Technical Spec: Task Tracker

## Overview
A simple task tracker web app.

## Tech Stack
- TypeScript with Node.js
- SQLite for storage

## Architecture
Single-process server with REST API and static frontend.

## Features
- [ ] User authentication with JWT
- [ ] Task CRUD API
- [ ] Rate limiting middleware
EOF
cat evolve-demo/docs/technical-spec.md
cd evolve-demo && code-evolve migrate spec ./docs/technical-spec.md --yes

Go to your project folder and run code-evolve migrate spec <file> --yes to turn an existing spec into code-evolve format.

What it does

  • Convert existing docs to code-evolve format
    How to use it
    1. In your project folder, run code-evolve migrate spec <spec-file> --yes to pull the features out of an existing spec.
    2. Run code-evolve migrate vision <vision-file> --yes to convert an overview document into .evolve/vision.md.
    Tested
  • Build a project from a vision and spec
    Not tested
  • Improve a project over repeated sessions
    Not tested
  • Create a vision file through a guided interview
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • Generate vision document via guided interview
  • Convert existing spec document into code-evolve format
  • Run autonomous evolution engine on schedule
  • Run one evolution cycle manually
  • Check build progress with status

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 0.2.0

Differences the test machine hit

  • README: npx code-evolve init creates .evolve/ with templates
    In the test: init checks for agent binary (claude/codex/opencode/ollama) plus python3 and git and exits 3 with 'Missing required dependencies' when absent; Requirements lists the agent but Getting Started does not warn
  • README: code-evolve status checks progress after init
    In the test: migrate without init only creates .evolve/ dir with spec.md/vision.md; status still exits 1 'Not initialized' until full init provides scripts/evolve.sh and IDENTITY.md

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.