SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Varun Pratap Bhardwaj

cs.AIApr 6, 2026

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Authors: Varun Pratap Bhardwaj

Organizations: Independent Researcher, Solution Architect India

Abstract

AI coding agents operate in a paradox: they possess vast parametric knowledge yet cannot remember a conversation from an hour ago. Existing memory systems store text in vector databases with single-channel retrieval, require cloud LLMs for core operations, and implement none of the cognitive processes that make human memory effective. We present SuperLocalMemory V3.3 ("The Living Brain"), a local-first agent memory system implementing the full cognitive memory taxonomy with mathematical lifecycle dynamics. Building on the information-geometric foundations of V3.2 (arXiv:2603.14588), we introduce five contributions: (1) Fisher-Rao Quantization-Aware Distance (FRQAD) -- a new metric on the Gaussian statistical manifold achieving 100% precision at preferring high-fidelity embeddings over quantized ones (vs 85.6% for cosine), with zero prior art; (2) Ebbinghaus Adaptive Forgetting with lifecycle-aware quantization -- the first mathematical forgetting curve in local agent memory coupled to progressive embedding compression, achieving 6.7x discriminative power; (3) 7-channel cognitive retrieval spanning semantic, keyword, entity graph, temporal, spreading activation, consolidation, and Hopfield associative channels, achieving 70.4% on LoCoMo in zero-LLM Mode A; (4) memory parameterization implementing Long-Term Implicit memory via soft prompts; (5) zero-friction auto-cognitive pipeline automating the complete memory lifecycle. On LoCoMo, V3.3 achieves 70.4% in Mode A (zero-LLM), with +23.8pp on multi-hop and +12.7pp on adversarial. V3.2 achieved 74.8% Mode A and 87.7% Mode C; the 4.4pp gap reflects a deliberate architectural trade-off. SLM V3.3 is open source under the Elastic License 2.0, runs entirely on CPU, with over 5,000 monthly downloads.

Figures & tables

System	Local	Ch.	Forget	Quant	Param	Auto	Trust	LoCoMo
Mem0 [ 17 ]	No	1	No	No	No	No	No	64.2%
Letta [ 20 ]	No	1	No	No	No	Partial	No	$\sim$ 83%
Zep v3	No	3	No	No	No	No	No	85.2%
LangMem	No	1	No	No	No	No	No	—
SLM V3.2 [ 8 ]	Yes	4	No	No	No	Yes	Yes	74.8%
SLM V3.3	Yes	7	Yes	Yes	Yes	Yes	Yes	70.4%

Table 1: Comparison of open-source agent memory systems. SLM V3.3 is the only system implementing all capabilities.

Figure 1: SLM V3.3 system architecture. The Interface Layer provides 60 MCP tools, a CLI with daemon serve mode (32

\times

cold-start speedup), a 17-tab web dashboard, and auto-cognitive hooks for Claude Code. The Engine Layer implements 7-channel cognitive retrieval, Ebbinghaus lifecycle management with EAP precision scheduling, FRQAD/TurboQuant quantization ( C1 ), soft prompt generation ( C4 ), and a code knowledge graph module. The Storage Layer uses local SQLite databases with sqlite-vec for vector operations. Orange blocks indicate novel contributions.

Operation	V3.2	V3.3 (daemon)	Speedup
slm recall (cold)	19s	0.6s	32 $\times$
slm recall (warm)	1s	0.6s	1.7 $\times$
slm remember (async)	0.3s	0.1s	3 $\times$
MCP recall (cold)	23s	$\sim$ 1s	23 $\times$

Table 2: Daemon serve mode performance impact.

#	Channel	Source	Retrieves	Weight
1	Semantic	sqlite-vec KNN (float[768])	Meaning-similar	1.2
2	BM25	FTS5 keyword index	Exact term matches	1.0
3	Entity Graph	Knowledge graph traversal	Entity-connected	1.0
4	Temporal	Bi-temporal timestamps	Recently relevant	1.0
5	Spreading Activation	Energy propagation	Causally-connected	1.0
6	Consolidation	CCQ gist blocks	Compressed knowledge	0.8

Table 3: Seven-channel retrieval architecture.

Method	Prefers f32	Percentage
Cosine similarity	16,127 / 18,840	85.6%
Fisher-Rao (standard)	13,316 / 18,840	70.7%
FRQAD (ours)	18,840 / 18,840	100.0%

Table 4: Mixed-precision preference: percentage of query-fact pairs where f32 is preferred over 4-bit.

Figure 2: Mixed-precision preference: percentage of 18,840 query-fact pairs where the f32 embedding is correctly preferred over the 4-bit quantized version. FRQAD achieves perfect precision (100%) by accounting for quantization uncertainty via variance inflation on the Fisher-Rao geodesic.

Metric	Value
Baseline recall@10 (all float32)	1.000
Mixed recall@10 mean	0.680
4-bit cosine fidelity	0.994
2-bit cosine fidelity	0.801

Table 5: TurboQuant mixed-precision recall.

Component	RSS
Main process (MCP/CLI, no torch)	63.3 MB
Embedding worker subprocess	1,058.9 MB
Total system footprint	1,122.2 MB
Engine init time	1.75s
torch in main process	False
Worker auto-kill (2 min idle)	Yes

Table 6: Wall-clock memory usage (Mode A, sentence-transformers subprocess).

Group	Mean R	Avg S	EAP Tier	Half-life
Hot (20 facts)	0.345	11.28	polar4 (4-bit)	7.8h
Warm (50 facts)	0.165	6.67	polar2 (2-bit)	4.6h
Cold (100 facts)	0.000	1.69	deleted	1.2h

Table 7: Ebbinghaus forgetting dynamics at day 30 (measured 12h after last access).

Figure 3: Ebbinghaus retention curves over 30 simulated days. Hot facts (daily access) converge toward the polar4 tier (

R\approx 0.35

). Warm facts (every 3 days) show a characteristic cyclic pattern. Cold facts decay immediately below the forget threshold. Dotted lines indicate EAP precision tier boundaries.

Category	V3.3 Baseline	V3.3 R3	Paper 2
single-hop	60.5%	65.1% (+4.6pp)	$\sim$ 80%
multi-hop	25.4%	49.2% (+23.8pp)	$\sim$ 60%
temporal	38.5%	53.8% (+15.3pp)	$\sim$ 60%
open-domain	86.8%	82.5% ( $-$ 4.3pp)	85.0%
adversarial	63.4%	76.1% (+12.7pp)	$\sim$ 70%
Overall	62.8%	70.4%	74.8%

Table 8: LoCoMo Mode A results: V3.3 (Round 3, best of 5 rounds) vs. V3.2 retrieval baseline and Paper 2 reported score.

Figure 4: LoCoMo per-category comparison. V3.3 R3 surpasses Paper 2 on adversarial (+6.1pp) and substantially closes the multi-hop gap (+23.8pp from baseline). The single-hop regression (

-

14.9pp vs Paper 2) reflects 7-channel fusion complexity.

System	LoCoMo	Cloud?	Capabilities
Zep v3	85.2%	Yes	Bi-temporal KG, triple-modality
Letta v2	$\sim$ 83%	Yes	LLM-managed memory
SLM V3.2 Mode C	87.7%	Yes	4-channel, Fisher-Rao
SLM V3.2 Mode A	74.8%	No	4-channel, Fisher-Rao
SLM V3.3 Mode A	70.4%	No	7-ch, forget, quant, trust, param
Mem0	64.2%	Yes	Vector + graph overlay

Table 9: Comparison with open-source agent memory systems on LoCoMo (zero-cloud where applicable).

Agent Memory

Agent memory lets AI systems retain, update, and use facts, experiences, and skills across sessions and long-horizon tasks.

See all 191 papers

Mar 15, 2026

SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory

Persistent memory is a central capability for AI agents, yet the mathematical foundations of memory retrieval, lifecycle management, and consistency remain unexplored. Current systems employ cosine similarity for retrieval, heuristic decay for salience, and provide no formal contradiction detection. We establish information-geometric foundations through three contributions. First, a retrieval metric derived from the Fisher information structure of diagonal Gaussian families, satisfying Riemannian metric axioms, invariant under sufficient statistics, and computable in O(d) time. Second, memory lifecycle formulated as Riemannian Langevin dynamics with proven existence and uniqueness of the stationary distribution via the Fokker-Planck equation, replacing hand-tuned decay with principled convergence guarantees. Third, a cellular sheaf model where non-trivial first cohomology classes correspond precisely to irreconcilable contradictions across memory contexts. On the LoCoMo benchmark, the mathematical layers yield +12.7 percentage points over engineering baselines across six conversations, reaching +19.9 pp on the most challenging dialogues. A four-channel retrieval architecture achieves 75% accuracy without cloud dependency. Cloud-augmented results reach 87.7%. A zero-LLM configuration satisfies EU AI Act data sovereignty requirements by architectural design. To our knowledge, this is the first work establishing information-geometric, sheaf-theoretic, and stochastic-dynamical foundations for AI agent memory systems.

Varun Pratap Bhardwaj

Independent Researcher, Solution Architect India

Agent Memory Agent Memory Management Information Geometry

Ask PDF

Apr 18, 2026

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstructured embedding vectors, retrieving information through semantic similarity. This paradigm fails to capture the associative structure of human memory, wherein related experiences progressively strengthen interconnections through repeated co-activation. Inspired by cognitive neuroscience, we identify three mechanisms central to biological memory: association, consolidation, and spreading activation, which remain largely absent in current research. To bridge this gap, we propose HeLa-Mem, a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics. HeLa-Mem employs a dual-level organization: (1) an episodic memory graph that evolves through co-activation patterns, and (2) a semantic memory store populated via Hebbian Distillation, wherein a Reflective Agent identifies densely connected memory hubs and distills them into structured, reusable semantic knowledge. This dual-path design leverages both semantic similarity and learned associations, mirroring the episodic-semantic distinction in human cognition. Experiments on LoCoMo demonstrate superior performance across four question categories while using significantly fewer context tokens. Code is available on GitHub: https://github.com/ReinerBRO/HeLa-Mem

Jinchang Zhu, Jindong Li, Cheng Zhang +2

The Hong Kong University of Science and Technology (Guangzhou) · Jilin University · The Chinese University of Hong Kong

Memorization in Language Models Hebbian Learning LLM Agent Memory Persistent Memory for Language Models Graph-Based Agent Memory Long-Term Conversational Memory+1

Ask PDF

Sep 25, 2026

HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents

Text-based memory and context compression support reuse of past interactions. Resizing continuous memory changes the input to a frozen LLM, coupling capacity allocation with readout. We propose Hard-Origin Adaptively Softened Memory (HasMem). Frozen hard-prompt embeddings provide a verifiable initial state. A controller adjusts memory widths, a Writer re-encodes resized entries, and Reader and Global provide readout adaptation and cross-turn state. On all

535

questions in a reconstruction probe derived from the Multi-Session Chat (MSC) development split, the main configuration achieves lexical F1 of

95.3

(

+4.4

percentage points) at

93.6\%

of the hard reference's framed memory positions. With approximately matched per-question target body budgets, six configurations at mean per-entry retention around

0.83

0.91

exceed rule-based re-encoding by

8.0

23.6

exact-match (EM) percentage points. With fixed model parameters and rule target width ratio

0.75

, Global's EM gain passes a user-level exact paired test with Bonferroni correction over eight comparisons. On all

500

LongMemEval-S questions, local lexical F1 rises from the hard reference's

3.4

8.9

, and answer negative log-likelihood (NLL) falls from

12.257

5.274

. F1 gains accompany lower EM on both evaluations.

Zihong He, Junxiao Shen, Chen Liang +1

The Hong Kong University of Science and Technology (Guangzhou) · University of Bristol · The Hong Kong University of Science and Technology

Memory Management for LLM Agents Long-Term Conversational Memory Agent Memory Management Memory-Augmented Language Model Agents

Ask PDF

Abstract

Agent Memory

Explore similar work

SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents