intellegix

intellegix / intellegix-code-agent-toolkit

Public

Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Claude Code CLI

55
10
100% credibility
Found Feb 26, 2026 at 42 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A set of enhancements for an AI coding assistant that adds automation loops, multi-expert queries, browser control, custom commands, and project oversight.

How It Works

1
🔍 Discover the toolkit

You find a helpful collection of tools that supercharges your AI coding assistant, making it smarter and more independent.

2
📥 Add to your setup

Place the tools in your AI assistant's special folder so it can use them right away.

3
🧩 Connect browser helper

Load a simple browser add-on that lets your AI control web pages like a human would.

4
🔗 Link research service

Share your web research login so your AI can look up facts without extra cost.

5
🚀 Launch smart sessions

Start an automated loop where your AI plans, researches, codes, and reviews on its own.

6
💬 Ask expert councils

Use quick commands to get advice from multiple AI experts at once.

✅ Enjoy autonomous projects

Your AI builds and manages coding projects reliably, saving you time and effort.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 42 to 55 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is intellegix-code-agent-toolkit?

This Python and Node.js toolkit supercharges Claude Code CLI into an autonomous coding agent, running automated loops with session continuity, budget caps, and stagnation checks. It integrates Perplexity research via browser automation—no API keys needed, just your Pro sub—and adds slash commands like /orchestrator for multi-phase planning, plus an MCP browser bridge for Chrome control. Solves the drudgery of babysitting AI through long coding sessions by creating a closed-loop system that iterates until PROJECT_COMPLETE.

Why is it gaining traction?

Zero-config Perplexity queries give Claude real-time web smarts mid-loop, with model fallbacks (Opus to Sonnet) and exponential backoff keeping things reliable. Custom commands streamline GitHub issue fixes, code reviews, and handoffs, while trace logs and metrics summaries make auditing dead simple. Devs dig the hands-off autonomy: launch once, steer via CLAUDE.md edits, no endless prompting.

Who should use this?

Backend devs automating feature branches or refactors with Claude Code. Indie hackers prototyping apps via agent loops, skipping manual iterations. Teams enforcing portfolio tiers to gate complexity on experimental GitHub repos.

Verdict

Try the smoke test if Claude Code is your daily driver—220 tests and crisp docs punch above 23 stars and 1.0% credibility. Early but mature enough for production pilots; watch for concurrent research scaling.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.