DexCode brings AI slide decks to terminal

// 71d agoPRODUCT LAUNCH

DexCode brings AI slide decks to terminal

DexCode is an open-source, AI-first slide authoring tool that lets developers create, revise, and share decks from the same terminal workflow they use for coding. It supports agent-driven authoring (including Claude Code, Codex, Gemini CLI, and Cursor) while the browser app stays focused on previewing, presenting, and link sharing.

// ANALYSIS

DexCode is a sharp bet on “slides as code” for engineering teams, and it feels more like a developer workflow upgrade than another presentation app.

–Terminal-first authoring removes app switching and keeps deck work inside existing AI coding flows.
–MIT-licensed, open-source distribution lowers lock-in risk versus closed AI presentation tools.
–Built-in Cloudflare Tunnel sharing makes fast async review practical without extra deployment setup.
–The upside is biggest for technical teams; non-CLI users may still prefer traditional GUI slide editors.

// TAGS

dexcodecliagentai-codingdevtoolopen-source

DISCOVERED

71d ago

2026-03-17

PUBLISHED

71d ago

2026-03-17

RELEVANCE

8/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE2h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE3h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE6h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.