Attribution

August 8, 2026 · View on GitHub

SuperLocalMemory

SuperLocalMemory is part of the Qualixar research initiative — advancing agent development through research.

Creator

Varun Pratap Bhardwaj — Solution Architect & Original Creator

  • GitHub: @varun369
  • ORCID: 0009-0002-8726-4289

License

This software is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). See LICENSE for full terms.

Output Attribution

All tool outputs carry provenance metadata:

Generated by SuperLocalMemory | Part of Qualixar

Outputs may include:

  • Layer 1 (Visible): Human-readable attribution in reports and exports.
  • Layer 2 (Cryptographic): SHA-256 content hash and signature in the _qualixar metadata block.
  • Layer 3 (Steganographic): Invisible zero-width character watermark in text outputs.

Verification

Output provenance can be verified programmatically:

from qualixar_attribution import QualixarSigner
is_valid = QualixarSigner.verify(signed_output)

Research Papers

SuperLocalMemory is backed by three public research preprints (arXiv preprints):

  1. Paper 1 — Trust & Behavioral Foundations (arXiv:2603.02240) Bayesian trust defense, behavioral pattern mining, OWASP-aligned memory poisoning protection.

  2. Paper 2 — Information-Geometric Foundations (arXiv:2603.14588) Fisher-Rao geodesic distance, cellular sheaf cohomology, Riemannian Langevin lifecycle dynamics.

  3. Paper 3 — The Living Brain (arXiv:2604.04514) FRQAD mixed-precision metric, Ebbinghaus adaptive forgetting, five candidate producers plus entity-graph enhancement, memory parameterization, trust-weighted forgetting.

Research Initiative

Qualixar is a research initiative for AI agent development tools by Varun Pratap Bhardwaj. SuperLocalMemory is one of several research initiatives under the Qualixar umbrella.

Third-Party Acknowledgments

SuperLocalMemory uses the following open-source libraries:

  • scikit-learn (BSD-3-Clause) — TF-IDF vectorization and similarity search
  • SQLite (Public Domain) — Local database storage
  • NumPy (BSD-3-Clause) — Numerical operations
  • SciPy (BSD-3-Clause) — Numerical optimization (used by vCache MLE logistic refit)

See pyproject.toml for the full dependency list.

Optimize Module — Research Citations (v3.6)

The Optimize module (LLD-03 / LLD-04) builds on cited public research. The Implementer verified each arXiv ID against arxiv.org before citation.

ComponentSourceLicense / Note
vCache (per-item learned thresholds, online MLE)arXiv:2502.03771 (ICLR 2026, Berkeley/TUM)Eq. 9 (sigmoid), Eq. 10 (BCE MLE), Eq. 11 (confidence-band τ̂), Algorithm 2, Theorem 4.1 (≥1-δ correctness guarantee)
CacheAttack (86% response hijack, 90.6% agentic)arXiv:2601.23088Threat model. The 90.6% figure is [UNVERIFIED — body-only, RA-18]; the 86% figure is verified from the abstract.
SAFE-CACHE (centroid-based adversarial defense)Nature Scientific Reports 2026[CITATION-NEEDED-ONLINE — exact paper verified, but exact defense figures are body-only.] Defense reduced attack success from 52.77% to 14.27% per the paper.
ContextCache (multi-turn context-aware keys)arXiv:2506.22791§3 — context-aware cache keys prevent false reuse across semantically overlapping but conversationally distinct turns.
LLMLingua-2 (prose compression)arXiv:2403.12968 (Microsoft Research)MIT license. Models: microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank (default) and microsoft/llmlingua-2-xlm-roberta-large-meetingbank. Off by default, opt-in via compress_prose=True + compress_mode="aggressive". Originals always stored in CCR before lossy compression — reversible via slm_ccr_retrieve.
LongLLMLingua (RAG compression)arXiv:2310.06839Not used in Phase 3. Documented for Phase 4 RAG integration.

Two fabricated arXiv IDs were caught and fixed during the LLD-10 audit: 2501.05064 and 2404.12693 (both previously wrong vCache labels). The verified ID is arXiv:2502.03771.

If you see an arXiv ID in the Optimize module not listed above, treat it as suspect.