tigranbs/mcgravity
by Various
Fast TUI that orchestrates AI coding tools (Claude Code, Codex, Gemini) in a plan→execute→review loop. Breaks work into atomic tasks for easier verification and course-correction.
MCP
tigranbs/mcgravity
Added 1 June 2026
Overview
A fast terminal UI that orchestrates multiple AI coding tools including Claude Code, Codex, and Gemini. It runs a plan-execute-review loop and breaks work into atomic tasks for easier verification and course correction.
Best for
Best for
Developers who want a structured, multi-tool AI coding workflow with built-in verification steps.
Use cases
- Coordinate multiple AI coding assistants in a single terminal session
- Break complex coding tasks into atomic subtasks for incremental verification
- Iterate on code with structured review and correction loops
How to use
Install
npm install -g mcgravity Tools exposed
@anthropic-ai/claude-code@openai/codex@google/gemini-cli
Tested with
Claude Code, Codex, Gemini CLI
Notes
A fast terminal UI that orchestrates multiple AI coding tools including Claude Code, Codex, and Gemini. It runs a plan-execute-review loop and breaks work into atomic tasks for easier verification and course correction.
98 stars on GitHub. Last updated 2026-02-15.
Use cases
- Coordinate multiple AI coding assistants in a single terminal session
- Break complex coding tasks into atomic subtasks for incremental verification
- Iterate on code with structured review and correction loops
Pros
- Fast performance due to Rust implementation
- Supports multiple popular AI coding tools in one workflow
- Atomic task breakdown improves error detection and correction
Cons
- Limited to the three listed AI tools (Claude Code, Codex, Gemini)
- Requires terminal proficiency and comfort with TUI interfaces
- Small community and early-stage project (98 stars)
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Fast performance due to Rust implementation
- Supports multiple popular AI coding tools in one workflow
- Atomic task breakdown improves error detection and correction
Cons
- Limited to the three listed AI tools (Claude Code, Codex, Gemini)
- Requires terminal proficiency and comfort with TUI interfaces
- Small community and early-stage project (98 stars)
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.