Agent TUI

All projects

Agents / Skills

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

byxAI

PlayableOpen source

Agent TUI media is blocked

Allow external media to connect to the provider and play this content.

Description

A terminal-based AI coding agent and TUI fork of SpaceXAI's Grok Build. It provides an interactive interface for file editing, shell command execution, and task management across multiple AI model runtimes including Grok and Claude.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: An ambitious multi-vendor TUI harness for coding agents, enabling unified terminal-based interaction with Grok,…
Attributed to: @xai
Built with: Redwood AI Codex Grok 4.5
Links: x.ai
View tweet
View GitHub repo
Tags: #coding-agent #terminal-ui #rust #developer-tools

First posted: X · Jul 15, 2026
Listed: Added 19d ago
Build: Strong
Models: Strong

Prompts

Prompt 1

/deep-research Analyze the architecture of Grok Build's built-in /deep-research command. Use only primary Grok Build evidence: the installed documentation under /home/tetsuo/.grok/docs, the built-in workflow script projected into this live run, and the official xAI Workflows page at https://x.ai/news/workflows. Ignore every source outside that allowlist and do not compare other products. Establish the Plan, Research, Verify, and Report stages; the default four-question plan, six-claim investigator limit, 24-candidate cap, verifier sharding, fail-closed exact-ID validation, Partial and coverage behavior, and citation validation or deterministic fallback. Keep the report concise and cite exact paths or URLs.

Source

Prompt 2

Validate the cart total before charging the customer

Source

All projects

Agents / Skills

Agent TUI

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

byxAI

PlayableOpen source

Agent TUI media is blocked

Allow external media to connect to the provider and play this content.

Description

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: An ambitious multi-vendor TUI harness for coding agents, enabling unified terminal-based interaction with Grok,…
Attributed to: @xai
Built with: Redwood AI Codex Grok 4.5
Links: x.ai
View tweet
View GitHub repo
Tags: #coding-agent #terminal-ui #rust #developer-tools

First posted: X · Jul 15, 2026
Listed: Added 19d ago
Build: Strong
Models: Strong

Prompts

Prompt 1

/deep-research Analyze the architecture of Grok Build's built-in /deep-research command. Use only primary Grok Build evidence: the installed documentation under /home/tetsuo/.grok/docs, the built-in workflow script projected into this live run, and the official xAI Workflows page at https://x.ai/news/workflows. Ignore every source outside that allowlist and do not compare other products. Establish the Plan, Research, Verify, and Report stages; the default four-question plan, six-claim investigator limit, 24-candidate cap, verifier sharding, fail-closed exact-ID validation, Partial and coverage behavior, and citation validation or deterministic fallback. Keep the report concise and cite exact paths or URLs.

Source

Prompt 2

Validate the cart total before charging the customer

Source

Agent TUI

Description

Timeline

Agent TUI

Description

Timeline