run-llama

run-llama / surreal-slides

Public

Agentic search through slides and presentation documents, backed by LlamaCloud and SurrealDB

30
2
100% credibility
Found Mar 10, 2026 at 26 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Surreal Slides is a tool that uses AI to parse presentation files, organize them into a structured library, and lets users query the content using natural language conversations.

How It Works

1
📰 Discover the tool

You hear about Surreal Slides, a handy helper that turns your messy presentation files into a smart library you can chat with.

2
💻 Get it ready

You easily download and set up the tool on your computer so it's all prepared to use.

3
🗄️ Set up storage

You create a simple, safe spot on your computer to hold all your organized slide collections.

4
🧠 Connect smart helpers

You link friendly AI thinkers that can read your slides deeply and answer your questions naturally.

5
📁 Add your presentations

You point the tool to a folder of your slide decks, and it quietly organizes everything inside.

6
💬 Start asking questions

You type everyday questions about your slides, and the assistant finds answers across all your files.

🥳 Insights at your fingertips

Now you effortlessly pull key info from any presentation without hunting through files yourself.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 26 to 30 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 surreal-slides?

Surreal-slides is a Python CLI tool that indexes your presentation files—like PowerPoints or PDFs—into a SurrealDB backend using LlamaCloud for parsing and structured extraction. It turns raw slides into searchable summaries and full text, letting you query your entire library with natural language via a Claude-powered agentic search agent. No more hunting through files; just load a directory and ask questions like "What's the key takeaway from slide 10 in the Q3 deck?"

Why is it gaining traction?

It stands out with dead-simple agentic workflows: CLI commands for setup, loading directories (non-recursive, concurrent processing), and running sessions that resume via ID. Backed by LlamaCloud for agentic parsing and SurrealDB for hybrid queries, it delivers agentic search llm capabilities without LangChain complexity or AWS/Microsoft overhead—pure Python install via uv. Developers dig the tool-exposed agent (list files, fetch content/summaries) for agentic RAG knowledge graphs in github agentic coding flows.

Who should use this?

Sales engineers sifting client pitch decks, researchers querying conference slides, or educators managing lecture libraries. Ideal for devs in agentic SDLC pipelines needing quick agentic search over docs, or teams prototyping github agentic chat without full agentic search systems.

Verdict

Promising for agentic search dummies but immature—25 stars and 1.0% credibility score signal early days with solid docs but no tests visible. Try for small slide sets if you want agentic optimization now; watch for production hardening.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.