Package Exports

@polylogicai/polycode
@polylogicai/polycode/bin/polycode.mjs

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@polylogicai/polycode) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

polycode

An agentic coding CLI. Runs on your machine with your keys. Every turn is appended to a SHA-256 chained session log on disk, so your history is auditable, replayable, and portable across machines.

Install

The fastest way to try polycode is with npx. It works on macOS, Linux, and Windows from any terminal:

npx @polylogicai/polycode@latest

For repeated use, install it globally:

npm install -g @polylogicai/polycode
polycode

Quick start

Set your Groq API key, then run polycode:

# macOS and Linux
export GROQ_API_KEY=gsk_...
npx @polylogicai/polycode@latest

# Windows PowerShell
$env:GROQ_API_KEY = "gsk_..."
npx @polylogicai/polycode@latest

That opens an interactive session. For one-shot mode, pass your prompt as an argument:

npx @polylogicai/polycode@latest "read README.md and summarize it in one sentence"

A free Groq API key is available at console.groq.com.

Configuration

polycode reads configuration from environment variables and optionally from a ~/.polycode/secrets.env file (chmod 600 recommended).

Variable	Purpose	Required
`GROQ_API_KEY`	Primary inference key for tool-use and reasoning	yes
`ANTHROPIC_API_KEY`	Optional high-quality tier for long sessions	no
`POLYCODE_MODEL`	Override the default model	no
`POLYCODE_CWD`	Override the working directory	no

Usage

polycode runs a standard agentic loop: you ask, it thinks, it uses tools, it returns a result. Available tools are:

bash run a shell command in the working directory
read_file read a file relative to the working directory
write_file write a file to the working directory
edit_file replace a substring in a file
glob list files matching a pattern
grep search for a regex in files

All tool calls are sandboxed to the working directory. polycode refuses any path that escapes it.

Session history

Every turn polycode takes is appended to a SHA-256 chained JSONL file at ~/.polycode/history/YYYY-MM-DD.jsonl. You own this file. You can:

Read it to see exactly what the agent did
Back it up by copying it
Hand it to a teammate, who can replay the session on their machine
Run polycode --verify to confirm the chain is intact

Slash commands

Inside the REPL:

/help      show all commands
/clear     clear the terminal
/history   show the session history file path and row count
/verify    verify session history integrity
/exit      leave polycode

Command-line flags

polycode                    interactive REPL
polycode "<prompt>"         one-shot mode
polycode --version          print version
polycode --help             print help
polycode --history          print session history status
polycode --verify           verify session history integrity

Safety rules

polycode enforces a small set of non-negotiable safety rules out of the box:

Shell commands referencing system paths (/etc/passwd, ~/.ssh, private key files) are refused
Code patterns that evaluate untrusted input are refused
Tool output containing recognized secret patterns (AWS, GitHub, Stripe, Anthropic, Groq, PEM blocks) is redacted before it reaches the model or the terminal

Rules live in ~/.polycode/rules.yaml. You can add your own.

Requirements

Node.js 20 or newer
macOS, Linux, or Windows
A Groq API key

Documentation and support

Install and usage: polylogicai.com/polycode
Issues and questions: ajs10845@psu.edu

License

MIT. See LICENSE. Built by Polylogic AI.

polycode is inspired by Claude Code's public architecture at docs.claude.com. polycode is not affiliated with Anthropic. No Claude Code code or system prompts are copied.