By qualixar
Provides local-first persistent memory for AI agents with reversible context compression, KV caching, and codebase graph intelligence to reduce token usage and retain cross-session facts, decisions, and code structure.
Advises the main agent on using SuperLocalMemory well — when to call session_init, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.
Applies SuperLocalMemory's context-optimization rules — reversible compression of large tool output and KV-caching of repeated reads/searches — to stretch the context window with no proxy. Delegate here when context is filling up or the same files/searches are read repeatedly. Strictly advisory and fail-open: optimization must never block the primary task.
KV cache for repeated reads — call slm_cache_get(key) first; on a miss do the expensive operation then slm_cache_set(key, value, ttl_seconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read more than once in a session.
Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slm_compress(content, mode, reversible, ttl_seconds) to shrink content; if the result is lossy a ccr_id is returned so you can call slm_retrieve(ccr_id) later to recover the exact original; always fail-open (ok:false → continue with the original).
Index and query a codebase as a structural graph — build the code graph, trace blast radius of a change, find callers/callees/inheritors, semantic code search by meaning, assemble PR review context, and detect what changed since last index. Use when the user asks how code connects, what breaks if X changes, what calls a function, what a class inherits from, how to navigate an unfamiliar codebase, or to understand risk before editing.
Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.
Capture durable facts, decisions, constraints, and gotchas into SuperLocalMemory. Use when the user says "remember that", "save this decision", "note this constraint", or when a session produces a conclusion worth persisting across sessions. Always recall first to avoid duplicates.
Admin access level
Server config contains admin-level keywords
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Cache. Compress. Remember. Three surfaces — proxy, MCP tools, or skill. Every setup covered.
To the best of our knowledge, the only zero-cloud agent memory that beats Mem0's zero-LLM score on LoCoMo. Mode A: 74.8% vs Mem0 64.2% — no GPU, no API key, on CPU.
v3.6.14 — Plugin-native. Profile-aware. Distributed-ready.
Proxy: slm wrap claude · MCP: add slm_compress to your config · Skill: zero-config
3 published research papers (arXiv preprints + Zenodo-archived) · arXiv:2603.02240 · arXiv:2603.14588 · arXiv:2604.04514
Every hosted AI memory platform — Mem0 Cloud, Zep Cloud, Letta Cloud, EverMemOS Cloud — sends your data to cloud LLMs by default. Self-hosted variants exist but require Docker, a separate graph DB, or Ollama config, and most default to OpenAI until you flip env vars. After August 2, 2026, any of those cloud paths becomes a compliance question under the EU AI Act.
SuperLocalMemory V3 uses mathematics instead of cloud compute — differential geometry, algebraic topology, and stochastic analysis replace the work other systems need LLMs to do. Local-first out of the box. No Docker. No graph DB. No API keys. CPU-only.
Benchmark results (evaluated on LoCoMo, the standard long-conversation memory benchmark, published April 2026):
| System | Score | Config | Cloud LLM required? | Open Source | Source |
|---|---|---|---|---|---|
| EverMemOS | 93.05% | Cloud (proprietary) | Yes | Core only | evermind.ai (Feb 2026) |
| Hindsight (LoComo10) | 92.0% | Cloud | Yes | No | benchmarks.hindsight.vectorize.io (Apr 2026) |
| Mem0 (token-efficient) | 91.6% | Hybrid (Cohere/OpenAI) | Yes | Partial | mem0.ai blog (Apr 16 2026) |
| SLM V3 Mode C | 87.7% | Local + optional LLM | Optional (Ollama OK) | Yes (AGPL-3.0) | In-house, arXiv:2603.14588 |
| Zep v3 Cloud | 85.2% | Cloud | Yes | Community deprecated | getzep.com |
| SLM V3 Mode A | 74.8% | Local, CPU-only, zero-LLM | No | Yes (AGPL-3.0) | In-house, arXiv:2603.14588 |
| Mem0 (zero-retrieval-LLM) | 64.2% | Local baseline | No | Partial | Mem0 paper, zero-LLM row |
npx claudepluginhub qualixar/superlocalmemory --plugin superlocalmemoryDeja Vu memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows using the Deja Vu Platform MCP server.
Reflex-based memory system for AI agents — stores experiences as interconnected neurons and recalls them through spreading activation, mimicking how the human brain works.
Memory → Evaluation → Credential → Access Control for AI agents. Persistent memory with W3C Verifiable Credentials, capability-based access control, drift detection, and FSRS-6 spaced repetition.
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
Local-first persistent memory for Claude Code — 101 MCP tools, hybrid search (FTS5 + vector + MMR), bitemporal contradictions, GDPR primitives, chatlog auto-capture, multi-agent handoffs.
Persistent memory for Claude Code — memories survive across sessions, projects, and machines