Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

raajmandale/XLifelineAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

16 Commits

Repository files navigation

πŸ€– XLifelineAI

Local AI that survives memory loss
Deterministic Fragment Graphs β€’ Continuity Engine β€’ Self-Healing Runtime

Failure is inevitable. Collapse is optional.


🎬 Live Runtime Surface

Interactive continuity-runtime simulation exploring self-healing AI memory, deterministic fragment graphs, and post-failure runtime reconstruction.


🌐 SGDS Ecosystem Surfaces

Surface Purpose Link
XPADI-SGDS Canonical survivability ecosystem root https://github.com/raajmandale/XPADI-SGDS
XPADI Proof Engine Runtime continuity reactor https://raajmandale.github.io/XPADI_Proof_Engine_V1/
Digital Lifeline Survivability architecture narrative https://github.com/raajmandale/digital-lifeline
XLifelineAI AI-native continuity & self-healing runtime https://github.com/raajmandale/XLifelineAI
XPADI-ProofCheck Recovery intelligence surface https://xpadi.com/proofcheck/
Research Paper SGDS architecture & theory https://zenodo.org/records/19500143


🌐 Mandale-OS Runtime Ecosystem

XLifelineAI now also operates as the continuity-runtime branch of the broader Mandale-OS ecosystem.


🧠 Runtime Positioning

XLifelineAI explores continuity-native AI execution where memory, fragments, graph intelligence, and runtime survivability become part of the execution lifecycle itself.

Within the Mandale-OS ecosystem, XLifelineAI represents:

  • continuity-runtime research
  • self-healing execution systems
  • post-failure runtime recovery
  • graph-aware memory continuity
  • AI survivability infrastructure

RUN β†’ FAIL β†’ DETECT β†’ REBUILD β†’ CONTINUE


✨ What is XLifelineAI?

A failure-native AI runtime using:

πŸ‘‰ Deterministic Fragment Graphs (DFG)


🧠 Runtime Model

RUN β†’ FAIL β†’ DETECT β†’ REBUILD β†’ CONTINUE


πŸš€ Quickstart

1. Clone

git clone https://github.com/raajmandale/XLifelineAI.git
cd XLifelineAI


2. Setup environment

python -m venv .venv
.venv\Scripts\activate


3. Install dependencies

pip install -r requirements.txt
pip install -e .


4. Run demo

python examples/resurrection_demo.py


πŸ§ͺ Output

Fragments created: 8
Fragments destroyed: 3
Integrity score: 0.625
Continuity mode: patched


🧠 Fragment Graph

  • partial context
  • connected memory
  • survivable structure

πŸ”— Recovery

  • detect loss
  • analyze graph
  • rebuild missing

βš™οΈ Flow

Graph β†’ Scan β†’ Repair β†’ Continue


♻️ Rebuild


πŸ–₯️ Preview

Simulator
docs/simulator/index.html

Report
docs/demo/resurrection_report.html


πŸ“‚ Structure

xlifeline/
docs/
examples/


πŸ” Core Idea

Traditional
β†’ reset

XLifelineAI
β†’ recover


🧭 Use Cases

  • AI continuity systems
  • long-running agents
  • failure-resilient runtimes
  • memory corruption simulation

πŸ—Ί Roadmap

v0 β€” DFG runtime core
v1 β€” semantic repair
v2 β€” distributed fragments
v3 β€” agent-native runtime


πŸ“Š Status

Research prototype
DFG continuity model validated


πŸ‘€ Author

Raaj Mandale
Systems Architect β€’ Runtime Intelligence β€’ Mandale-OS β€’ QBAIX β€’ XPADI-SGDS

🌐 https://raajmandale.in
πŸ”¬ https://orcid.org/0009-0005-9810-1655
πŸ“š https://openalex.org/A5127026877


πŸ“„ License

MIT License


⭐ Support

If this idea resonates:

⭐ Star the repo
🍴 Fork it
πŸ§ͺ Break it
🧠 Build on top of it


πŸ”₯ Final Thought

AI shouldn’t restart.
It should recover and continue.

About

πŸ€–DFG-based AI Memory Resilience Layer β€” continuity under partial memory destruction

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

Contributors

AltStyle γ«γ‚ˆγ£γ¦ε€‰ζ›γ•γ‚ŒγŸγƒšγƒΌγ‚Έ (->γ‚ͺγƒͺγ‚ΈγƒŠγƒ«) /