LibreAI / Video / AGI-Papers
// video · gyunggyung/AGI-Papers

AGI-Papers

AGI-Papers is an open-source video project by gyunggyung (gyunggyung/AGI-Papers on GitHub). It has 420 GitHub stars and 59 forks, is released under the MIT license, and was last updated on GitHub on 30 September 2026.

A curated archive of breakthrough papers in agents, RAG and on-device AI.

💎 Hidden gem★ 420 stars⑂ 59 forksMITupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
420
Forks
59
License
MIT
Last updated on GitHub
30 September 2026
Category
Video
Listing
Hidden gem — a shorter page for a lesser-known project
Official site
Official site
// how it works

How it works

  1. Open the archive

    Browse the curated paper collection.

  2. Pick your track

    Agents, architecture, training, RAG, or on-device.

  3. Read the breakthroughs

    Follow links to the original papers.

  4. Track the field

    Return as new papers are added.

// features

Why people love it

Curated archive

Breakthroughs, not every preprint.

Five tracks

Agents, architecture, training, RAG, on-device.

Paper links

Direct paths to the originals.

Field tracking

Watch AI progress in one place.

Researcher friendly

A reading list that stays current.

MIT licensed

Free to fork and extend.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/gyunggyung/AGI-Papers.git
    cd AGI-Papers
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project's launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// use cases

What you can build

  • Find breakthrough papers on AI agents.
  • Study RAG and on-device AI advances.
  • Build a reading list for architecture research.
  • Track training breakthroughs over time.
Advertisement
// faq

Questions, answered

Is AGI-Papers free to use?

MIT licensed — free with attribution.

Is it a tool or a list?

A curated archive — the value is the organized collection.

How often is it updated?

Check the commit history for update frequency.

Can I suggest papers?

Curated archives usually welcome PRs — check the README.

Does it cover video AI?

Its tracks are agents, architecture, training, RAG, and on-device AI.

// keep exploring

Similar tools

Video

awesome-generative-ai-apps

50+ open-source generative AI apps you can clone, deploy, and monetize — image generators, video tools, virtual try-ons, AI SaaS templates, and platform inte…

★ 3.4k starsMIT
View guide →
Video

UForm

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaV…

★ 1.3k starsApache-2.0
View guide →
Video

wunjo.wladradchenko.ru

Wunjo Make: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & …

★ 1.2k starsGPL-3.0
View guide →
Video

py-gpt

Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, …

★ 2.0k starsUnknown
View guide →
Video

cli

Official Alibaba Model Studio CLI — models, search and multimodal for agents.

★ 540 starsApache-2.0
View guide →
Video

Director

A framework for AI video agents — next-gen video workflows and interactions.

★ 1.5k starsMIT
View guide →
// alternatives

Alternatives in Video

The most-starred other Video projects in the LibreAI catalogue — the realistic shortlist if AGI-Papers is not the right fit.

  • yt-dlp★ 195.3k

    A feature-rich command-line audio/video downloader

  • Deep-Live-Cam★ 96.9k

    real time face swap and one-click video deepfake with only a single image

  • obs-studio★ 76.9k

    OBS Studio - Free and open source software for live streaming and screen recording

  • FFmpeg★ 64.7k

    Mirror of https://git.ffmpeg.org/ffmpeg.git

  • OpenMontage★ 62.7k

    World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your A…

// more in video

More in Video

Nearby Video projects in the catalogue, closest in stars to AGI-Papers — keep exploring the shelf either side of it.

  • World-R1★ 427

    Research model enforcing 3D constraints in text-to-video generation.

  • Nexior★ 398

    Consumer AI app — chat, image, video and music generation in one place.

  • ltx-video-mac★ 427

    Mac-native app generating AI video on-device with Apple Silicon — LTX, MiniMax.

  • Seedance-2-API★ 352

    Python wrapper for Seedance 2.0, 2.5 and 2 Mini — T2V and image-to-video.

  • ai-shortfilm-prompts★ 454

    Turn ideas into cinematic prompts for Sora, Kling, Veo and Seedance.

  • Open-AI-UGC★ 350

    Free open-source AI UGC ads — realistic AI actors via Veo 3.1 and Seedance.

Get AGI-Papers

Free and open — grab the source, star the repo, and start creating.