Skip to main content
AIDiveForge AIDiveForge
Visit Drever

Get This Tool

License: MIT Any use incl. commercial
Local-run terms: MIT license permits commercial use, modification, distribution, and private use with attribution required.

Share This Tool

Compare This Tool
📋 Embed this tool on your site

Copy this code to embed a compact tool card:

Drever

FreeOpen SourceSelf-HostedAgentic

Pricing

Model
Free

Summary

Most presentation tools let you build slides fast and leave you stranded when the room pivots — no way to update live, no synchronized outputs, no connection between what the speaker sees and what the audience drives. Drever is built around that exact failure.

The core workflow is brief-in, plan-review, then slide authoring — the agent pauses after generating a page-by-page outline so you redirect emphasis, density, or motion intent before a single slide is authored. Once you approve, Drever generates a complete story across audience view, speaker notes, document, web, and PDF from one source. The MDX and React-based authoring pipeline is deterministic and inspectable, which matters when you need to trace why a transition behaves a certain way. The wall appears early for teams who do not write MDX: this is not a drag-and-drop canvas, and non-technical stakeholders will need a developer in the loop to do anything beyond the AI-generated draft. Requires Node.js 24.18+ and a Safari or Chromium-family browser — that narrows the install base before you start.

Bottom line: Pick Drever when a developer-led team needs a single authored story that lives simultaneously as a live room, PDF, and document — but plan for a different tool when your deck owner is a designer or PM who will not touch MDX.

Community Performance Report Card

No community ratings yet. Be the first to rate this tool!

Best For: Teams needing AI-assisted story planning with human approval, Presentations requiring synchronized live, web, PDF, and document outputs, Developers comfortable with MDX and React-based slide authoring, Workflows emphasizing editable plans before final slide generation

Community Benchmarks Community

No community benchmarks yet. Be the first to share a real-world data point.

  • The agent pauses for plan approval before authoring any slides, so you redirect story shape, emphasis, and motion intent while changes are still cheap — not after forty slides exist that need reworking.
  • One MDX source generates audience view, speaker notes, document, web page, and PDF simultaneously, which means a revision to the authored story propagates to every output without manual reformatting.
  • Live audience input during delivery is wired into the slide step sequence, so the exact moment the room asks for proof and you reveal it is preserved as a citable, searchable state across all surfaces — not lost when the presentation ends.
  • MIT-licensed and self-hostable, so your deck content and audience data never transit a vendor's cloud unless you choose to deploy there.
  • The compilation pipeline is deterministic and boundary-inspectable, so when a transition or layout behaves unexpectedly you can trace it through AST, runtime, and surface layers rather than filing a support ticket and waiting.
  • All authoring is MDX and React code — there is no visual canvas. A PM or designer who needs to edit slide copy or reorder sections without developer help cannot do so, which means every revision cycle requires a developer present. Teams where the deck owner is non-technical move to canvas-based tools and lose the multi-surface synchronization.
  • The runtime requires Node.js 24.18 or higher and a Safari or Chromium-family browser. On teams with locked-down environments, older Node versions, or Firefox as the standard browser, the tool does not run without IT intervention before the first demo.
  • No API surface is exposed. Plugging Drever into an existing content pipeline — pulling from a CMS, triggering builds from a CI system, or posting outputs to a shared drive — requires building against the MDX and build layer directly, which is undocumented territory beyond what the vendor page describes.

Community Reviews

No reviews yet. Be the first to share your experience.

About

Platforms
Web (browser), Node.js
API Available
No
Self-Hosted
Yes
Last Updated
2026-07-28T20:34:48.569Z

Best For

Who it's for

  • Teams needing AI-assisted story planning with human approval
  • Presentations requiring synchronized live, web, PDF, and document outputs
  • Developers comfortable with MDX and React-based slide authoring
  • Workflows emphasizing editable plans before final slide generation

What it does well

  • Creating live, interactive product decision decks
  • Building motion-driven evidence and data stories
  • Generating multi-surface presentations from a single brief
  • Live audience-driven slide refinement during delivery

Discussion Community

No discussion yet. Sign in to start the conversation.

Spotted incorrect or missing data? Join our community of contributors.

Sign Up to Contribute

Community Notes & Tips Community

Be the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.

Frequently Asked Questions

Is Drever free?
Yes — Drever is fully free to use. There is no paid tier.
Is Drever open source?
Yes. Drever is open source.
Can I self-host Drever?
Yes. Drever supports self-hosting on your own infrastructure.
What platforms does Drever support?
Drever is available on: Web (browser), Node.js.

Hours Saved & ROI Stories Community

Be the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."

Drever

Drever is an open-source, MIT-licensed presentation tool that turns a single brief into a live, multi-surface deck through an agent-assisted authoring pipeline. The agent handles project setup, generates a full brief and slide-by-slide outline, then pauses — explicitly waiting for your approval before it authors any slides. You reshape the plan: change emphasis, reorder, adjust motion intent, move detail to speaker notes. Only after you sign off does Drever produce the complete story and open a local preview. The runtime then serves the same authored content as an audience-facing live room, a speaker view, a web page, a PDF, and a document simultaneously.

The differentiating feature is live audience interaction tied to the authored story. During delivery, the room can surface a question or direction — the vendor’s showcase shows an audience choosing ‘Show us unaided completion’ — and the speaker reveals the corresponding step, preserving the exact slide state as a citable, searchable moment across every output surface. This is not a post-presentation export; the connection between live room and document is maintained throughout.

Drever fits developer-comfortable teams authoring in MDX and React who need outputs beyond a slide deck — documentation, a shareable web room, and a PDF from one source without manual reformatting. It breaks for teams expecting a visual canvas editor. The authoring layer is code: MDX files compiled through an AST to a React runtime. Non-technical contributors cannot self-serve edits, which means any revision cycle runs through whoever owns the codebase. Teams that hit this constraint and need a no-code editor tend to move to canvas-based tools and accept the loss of synchronized multi-surface output.

Installation requires Node.js 24.18 or higher and a current Safari or Chromium-family browser. The vendor provides a CLI bootstrapper via `npm create drever@latest`. No API is exposed — integration into existing pipelines requires working at the MDX and build layer directly. The architecture is described as a deterministic pipeline with inspectable boundaries between compilation, routing, runtime, and delivery surfaces.

Related Listings

Flux 3

The agent doesn't hand you a finished board and disappear — the vendor describes a multi-step workflow where the AI surfaces its reasoning…

VerifiedFreemium
View tool

Reline

The platform takes a CAD floor plan upload, lets you mark entrances, columns, and critical zones, then generates hundreds of layout…

Verified
View tool

Framesmith

Framesmith is an open-source MCP server that gives AI assistants a visual design canvas by rendering HTML/CSS scene graphs to PNG via…

VerifiedOSS
View tool