xiaojiou176-open

AI Work Command Tower for Codex and Claude Code workflows with Model Context Protocol (MCP)-readable proof, replay, and Workflow Cases.

11
2
100% credibility
Found Apr 12, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

CortexPilot provides a web dashboard and orchestration system for teams to plan, track, and verify AI-driven coding workflows with proof and replay features.

How It Works

1
πŸ” Discover CortexPilot

You find the dashboard, a friendly command center for guiding AI teams on coding tasks without constant babysitting.

2
πŸ“ Pick a simple task

Choose a ready example like summarizing news, enter your topic, and describe what you want in plain words.

3
πŸ’¬ Chat your goal

Type your request in the easy chat box, like 'make a news summary on AI trends', and hit send.

4
πŸš€ Watch it work live

See your task move through the command tower, tracking progress, handoffs, and any issues in real time.

5
πŸ” Check the proof

Review the results, evidence bundles, comparisons, and replays to confirm everything went right.

βœ… Task complete and shareable

Enjoy your finished work with full proof, ready to share or reuse without doubts.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 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 CortexPilot-public?

CortexPilot-public is a Python-based command tower for orchestrating AI engineering workflows with Codex and Claude Code, providing a web dashboard to plan, delegate, track, resume, and prove long-running tasks via read-only Model Context Protocol (MCP). It delivers workflow cases with replayable proof, run comparisons, and live session oversight, solving the chaos of scattered chats and uninspectable agent outputs. Users get quickstarts like news_digest for digesting topics from public domains, plus PM intake for task templating and command station views for queue posture.

Why is it gaining traction?

It stands out with governed boundaries like diff gates, approvals, and evidence bundles that let operators inspect what agents actually did, unlike basic chat wrappers. The fiery work command station hooks devs with real-time Command Tower for GitHub work items tracking, work in progress PRs, and replay without guessing. MCP-readable cases make sharing proof across GitHub work and personal accounts straightforward, turning vague agent runs into auditable work commands.

Who should use this?

AI ops leads managing multi-agent Codex/Claude Code pipelines for production tasks like topic briefs or page summaries. PMs delegating scoped engineering with acceptance criteria and replay needs. Teams handling GitHub work directory locks, work item tracking, or collaborative work together on workflow cases.

Verdict

Early alpha (11 stars, 1.0% credibility) with solid docs and quickstart proofs, but low maturity means expect rough edgesβ€”test the news_digest path first. Worth starring for AI workflow oversight if you need MCP truth over hype.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.