qualixar/superlocalmemory

Why SuperLocalMemory?

Agent-memory systems make different storage, model-provider, and deployment trade-offs. SuperLocalMemory starts with a local runtime and makes provider-backed enrichment, cloud backup, connectors, and proxy use explicit choices.

SuperLocalMemory V3 combines conventional dense and lexical retrieval with graph, temporal, associative, and Fisher-informed scoring. The default local runtime does not require Docker, a separately operated graph database, or an API key.

Published benchmark evidence carried into V3.7: the architecture evaluated in the V3 paper remains the foundation of this release. The figures below keep their original LoCoMo protocol, answer-construction, model, and sample scope; they are not a claim of a newly rerun 3.7 package benchmark.

How SLM fits beside other memory systems

Different products solve different boundaries. SLM is for developers who want one local-first operating control plane—not only an SDK, managed context API, or agent runtime. It combines dated evidence, graph-aware retrieval, cache and compression controls, trusted-peer Mesh, and MCP/CLI/hooks/dashboard/IDE surfaces in one install.

See the source-linked market comparison for current primary sources and protocol-scoped benchmark evidence. A LoCoMo percentage is comparable only when the dataset scope, answer model, judge, retrieval stack, and release artifact match.

The V3.7 capability architecture

SuperLocalMemory is one local control plane for persistent agent context. It is not just a vector store: the same runtime can accept evidence, build and govern memory, retrieve bounded evidence for an agent, and expose cache, compression, and peer-coordination controls through a CLI, MCP, dashboard, and supported IDE integrations.

Architecture boundary: SQLite + sqlite-vec remain canonical; CozoDB and LanceDB are parity-gated projections; Mesh coordinates trusted peers rather than replicating a distributed memory database; connectors are opt-in.

Memory boundaries: profiles isolate workspaces by default. Every memory is personal, shared with named profile readers, or global; cross-profile recall is default-deny and must be explicitly enabled. This scoped sharing is local authorization, not SLM Mesh synchronization. See shared-memory.md.

 IDEs, agents, scripts, connectors, and humans
             │  CLI · MCP (HTTP/stdio) · hooks · dashboard
             ▼
 ┌────────────────────────── SLM CONTROL PLANE ──────────────────────────┐
 │  1. Admission       identity, scope, idempotency, raw evidence         │
 │  2. Queryable core  SQLite facts + FTS durable receipt                  │
 │  3. Enrichment      facts, entities, scenes, time, provenance, graph   │
 │  4. Memory brain    feedback, patterns, rewards, consolidation          │
 │  5. Retrieval       semantic · BM25 · temporal · Hopfield · activation │
 │  6. Context safety  policy, trust, provenance, redaction, budgets      │
 │  7. Operations      lifecycle, audit, cache/compress, mesh, backups    │
 └───────────────────────────────────────────────────────────────────────┘
             │
             ▼
 SQLite + sqlite-vec canonical store  ──► optional graph/vector projections

The seven stages are an execution model, not a promise that every optional enricher or retrieval channel runs for every request. The receipt, trace, and health surfaces expose the stages actually completed by the installed runtime.

What the dashboard exposes

slm dashboard opens a local operational view of the same control plane:

Dashboard visibility is not a substitute for runtime proof: use slm doctor, slm health, slm trace, and the relevant CLI/MCP operation to validate a deployment.

Watch the product walkthrough

Watch the SuperLocalMemory demo on YouTube — a five-minute walkthrough of installation, setup, recall, cache, and compression. The video shows a product walkthrough; use the commands and release notes in this README as the current release contract.

Published LoCoMo evidence carried into V3.7

The V3 paper evaluates the architecture carried into V3.7. Every figure below is protocol-scoped, so a reader can distinguish local retrieval, answer construction, and cloud-assisted evaluation rather than treating unlike runs as one score.

Published category results: Mode A Retrieval scored 72.0% single-hop, 70.3% multi-hop, 80.0% temporal, and 85.0% open-domain. Mode C scored 64.0% single-hop, 100.0% multi-hop, and 86.0% open-domain on its 81-question Conv-30 scope (no temporal category was reported for that run). Across six LoCoMo conversations, the paper reports 71.7% with the information-geometric layers versus 58.9% without them: +12.7pp.

See arXiv:2603.14588 and the official LoCoMo paper for the full protocol, ablation table, and limitations. These are published V3 architecture results carried into V3.7—not a substitute for a newly rerun release-artifact benchmark.

Related MCP server: dakera-mcp

Quick Start

# Primary path 1 — npm global CLI (Node 18+)
# Creates a package-owned virtual environment. It does not modify system Python.
npm install -g superlocalmemory
slm setup       # Choose mode (A/B/C)
slm doctor      # Verify everything is working

# Primary path 2 — Python CLI + SDK in an activated virtual environment
python3 -m venv .venv
source .venv/bin/activate  # Windows PowerShell: .venv\Scripts\Activate.ps1
python -m pip install superlocalmemory
slm setup
slm doctor

# First use
slm remember "Alice works at Google as a Staff Engineer" --json
slm recall "What does Alice do?"
slm status

The default daemon write commits raw evidence plus a relational/FTS projection and returns a durable receipt in queryable state. Enrichment then advances the same operation through enriching to complete, or records a retryable failed state. Use slm remember "..." --sync when the caller must wait for all declared derivation and projector stages. JSON output includes the opaque operation_id, current materialization_state, and fact IDs.

# Wrap your agent — starts proxy + sets environment + launches agent
slm wrap claude
# Your first repeat prompt → CACHE HIT → $0.00
# See savings: slm optimize savings --since 1

Upgrading: use the owner of the installation: npm update -g superlocalmemory or, while the Python virtual environment is active, python -m pip install --upgrade superlocalmemory. Then run slm restart && slm doctor. Repository-clone users use the matching upgrade action in scripts/install.sh or scripts/install.ps1. Installers never move or delete memory data.

Three Pillars

Memory

Current recall has five candidate producers—dense semantic, BM25 lexical, temporal, Hopfield associative, and spreading activation—followed by fusion, optional reranking, and entity-graph score enhancement. The entity graph does not create an independent candidate in the current implementation. Core memory is SQLite-backed. SQLite and sqlite-vec remain the canonical source of truth. The packaged Scale Engine can maintain CozoDB graph and LanceDB vector projections, and it remains outside active retrieval paths until slm db scale prepare, verify, and promote prove parity against the canonical store. This makes the capability available on a fresh installation without silently migrating an existing user's data.

Canonical ingestion is a durable state machine: raw → queryable → enriching → complete, with failed retaining raw evidence, error details, attempt count, and retry timing. SQLite relational facts and FTS are the queryable checkpoint; optional ANN/vector projectors are verified before complete is granted.

Recalled text is treated as untrusted evidence. Hooks, MCP session_init, CLI session context, and chat use one bounded renderer that redacts recognized secrets, neutralizes forged boundary markers, and attaches provenance. Trusted IDE instruction files contain only the static SLM protocol; fresh memory is retrieved at runtime rather than copied into those files.

Score Contract v2: relevance_score is query-relative relevance; ranking_score is internal ranking utility; memory_confidence belongs to the stored assertion; and trust_score is an evidence-policy signal. Legacy score and confidence remain aliases for one compatibility release. V3.7 is explicitly uncalibrated: calibration_status is uncalibrated and answer_confidence is null. See the retrieval score contract.

The retrieval/lifecycle implementation includes three mathematical layers that can run without a cloud LLM:

1. Fisher-informed scoring — dense candidate generation uses cosine similarity; Fisher-derived terms can modify later scoring when their state is available.

2. Sheaf Cohomology for Consistency — algebraic topology detects contradictions via coboundary norms on the knowledge graph.

3. Riemannian Langevin Lifecycle — memory positions evolve on the Poincare ball; neglected memories self-archive, no hardcoded thresholds.

Auto-capture hooks are installed explicitly with slm hooks install (Claude Code) or slm hooks install --agent codex (Codex). Hook latency and capture quality must be evaluated for the target client and workload; V3.7 publishes no universal p99 claim.

Multi-scope memory (v3.6.15, opt-in): keep memories personal (default), shared with named profiles, or global across the machine. Off by default — recall only ever returns your own facts until you turn sharing on, per call or in config. See docs/shared-memory.md.

Multilingual models: configure an OpenAI-compatible embedding endpoint such as Ollama, vLLM, LiteLLM, bge-m3, multilingual-e5, or Qwen3-Embedding. Language coverage and retrieval quality depend on the selected model and should be evaluated for the deployment corpus.

Cache + Compress

One engine, three ways in — choose the surface that fits your setup:

The hard constraint: The primary Claude conversation turn cannot be cached without a proxy. The MCP/skill path caches results you explicitly route through SLM (tool outputs, file reads, sub-model calls) — without a proxy the main conversation turn is not intercepted.

How to choose:

• Metered API (pay-per-token), want every call cached → Proxy (A)

• Pro/Max/Team subscription or any plan where you won't run a proxy → MCP tools (B) or Skill (C)

• Zero configuration → Skill (C): install once, auto-compresses CLAUDE.md and large outputs

• Agent-controlled caching of repeated file reads → MCP tools (B)

Cache: exact-match SQLite lookup is the stable cache path. Semantic cache controls are experimental until release-linked precision, invalidation, and tenant-isolation evidence exists. A cache hit can avoid a provider request, but actual cost and latency savings depend on the intercepted surface and provider.

Compress: safe mode uses conservative normalization and preserves JSON and code; measured reduction varies by content and can be zero. Aggressive prose compression is opt-in and lossy. CCR can retain an original for later byte-exact retrieval when reversible storage is enabled.

Savings dashboard: slm optimize savings --since 7 — live USD/INR/tokens saved. Hot-reload config, fail-open.

Mesh

Mesh provides authenticated coordination messages between configured peers, with an offline queue and optional mDNS discovery (SLM_MESH_DISCOVERY=on). It is not a replicated or conflict-resolving distributed-memory database.

# Machine A (broker)
export SLM_MESH_HOST=192.168.1.100
export SLM_MESH_SHARED_SECRET=my-secret-key
slm init

# Machine B (client)
export SLM_MESH_PEER_URL=http://192.168.1.100:8765
export SLM_MESH_SHARED_SECRET=my-secret-key
slm init

8 mesh MCP tools: mesh_peers, mesh_send, mesh_broadcast, mesh_project, mesh_inbox, mesh_pending, mesh_state, mesh_lock.

Full docs: docs/multi-machine.md · docs/distributed-deployment.md

Install Paths

After any install path: slm setup → slm doctor → slm warmup (optional, pre-downloads ~500MB embedding model).

MCP + Profiles

SLM supports two MCP transports:

HTTP (recommended, v3.6.7+):

{ "mcpServers": { "superlocalmemory": { "type": "http", "url": "http://127.0.0.1:8765/mcp/" } } }

Or: claude mcp add --transport http superlocalmemory http://127.0.0.1:8765/mcp/

stdio (universal fallback):

{ "mcpServers": { "superlocalmemory": { "command": "slm", "args": ["mcp"] } } }

MCP Profiles (WP-01)

Control tool surface via SLM_MCP_PROFILE:

Precedence: ALL > TOOLS > PROFILE > default

export SLM_MCP_PROFILE=full   # or core / code / mesh / power / whole
slm mcp

For a predictable small surface, set core explicitly. Leaving the variable unset retains the compatibility default, whose mesh tools follow the local mesh setting. The former count-suffixed names (core14, code20, mesh8, full38, power50, whole81) remain temporary aliases and emit a migration warning. Unknown names stop startup instead of silently selecting another tool set.

Per-IDE configs available for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Gemini CLI, JetBrains, Zed, and more (15 configs in ide/configs/). See docs/ide-setup.md.

Claude Code Plugin

Install directly in Claude Code — no system-level npm/pip needed. This is how you get the skills, agents, hooks, commands, and rules (the MCP server is bootstrapped automatically). It is a two-step flow — add the marketplace once, then install:

# 1. Add the Qualixar marketplace (one-time — the repo IS the marketplace)
/plugin marketplace add qualixar/superlocalmemory

# 2. Install the plugin
/plugin install superlocalmemory@qualixar

• Self-bootstraps a Python venv, installs all deps in an isolated SLM_DATA_DIR

• Registers the 14-tool core MCP surface (core14 profile by default)

• Ships the SLM skills / agents / hooks / commands / rules

• Additive — does not replace an existing SLM install

• slm connect claude-code detects an existing plugin install and links them

Plugin vs Python/npm: python -m pip install superlocalmemory inside an activated virtual environment, or npm i -g superlocalmemory, give you the slm CLI + the MCP server (the tools). The skills/agents/hooks/ commands come only through the plugin above. Use the plugin for Claude Code; use pip/npm for the CLI or other IDEs.

To update later: /plugin marketplace update qualixar then /plugin install superlocalmemory@qualixar.

Codex add-on

For Codex, install the SLM-owned skills, two focused subagents, and four lifecycle hooks explicitly:

slm codex install

This adds only SLM-owned files under ~/.agents/skills, ~/.codex/agents, and ~/.codex/hooks.json; it does not replace another agent's hooks or rewrite ~/.codex/config.toml. Codex requires review and trust for new command hooks: open /hooks after installation. MCP wiring remains a separate explicit step:

slm connect codex

slm connect codex semantically merges the superlocalmemory MCP server into ~/.codex/config.toml, preserving unrelated configuration keys and writing atomically. TOML serializers can normalize whitespace and comments, so it is not a byte-preserving operation; use it only when you want the MCP server configured. Check the result with slm codex status; undo SLM-owned add-ons with slm codex remove.

Privacy controls and operating modes

slm mode a   # Zero-cloud (default)
slm mode b   # Local Ollama
slm mode c   # Cloud LLM

Mode A can run core memory operations without sending memory content to a cloud model provider. This does not disable optional connectors, cloud backup, proxy providers, dependency acquisition, or model downloads; review configuration and network policy for the deployment.

SuperLocalMemory provides local storage, export/erasure commands, provenance, policy, and audit features that can support a compliance program. The software is not a legal certification, and compliance depends on the use case, operator, configuration, and surrounding systems.

Available controls include local export and erasure commands, hash-chained audit records, provenance tracking, and ABAC policy enforcement. Verify their behavior and retention boundaries for your deployment; see docs/compliance.md.

Advanced

Web dashboard:

slm dashboard    # Opens at http://localhost:8765

The dashboard includes Dashboard, Brain, Knowledge Graph, Memories, Health, Operations, Entity Explorer, Skill Evolution, Mesh Peers, Settings, and Optimize workspaces. Features are populated only when their corresponding runtime capability is enabled and healthy.

Release history:

Research Papers

SuperLocalMemory is backed by three published research papers (arXiv preprints + Zenodo DOIs). These are preprints — not conference-accepted or journal-published yet.

Paper 3: The Living Brain (V3.3)

SuperLocalMemory V3.3: The Living Brain — Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems Varun Pratap Bhardwaj (2026) arXiv:2604.04514 · Zenodo DOI: 10.5281/zenodo.19435120

Paper 2: Information-Geometric Foundations (V3)

SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory Varun Pratap Bhardwaj (2026) arXiv:2603.14588 · Zenodo DOI: 10.5281/zenodo.19038659

Paper 1: Trust & Behavioral Foundations (V2)

SuperLocalMemory: A Structured Local Memory Architecture for Persistent AI Agent Context Varun Pratap Bhardwaj (2026) arXiv:2603.02240 · Zenodo DOI: 10.5281/zenodo.18709670

Cite This Work

@article{bhardwaj2026slmv33,
  title={SuperLocalMemory V3.3: The Living Brain — Biologically-Inspired
         Forgetting, Cognitive Quantization, and Multi-Channel Retrieval
         for Zero-LLM Agent Memory Systems},
  author={Bhardwaj, Varun Pratap},
  journal={arXiv preprint arXiv:2604.04514},
  year={2026},
  url={https://arxiv.org/abs/2604.04514}
}

@article{bhardwaj2026slmv3,
  title={Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory},
  author={Bhardwaj, Varun Pratap},
  journal={arXiv preprint arXiv:2603.14588},
  year={2026}
}

@article{bhardwaj2026slm,
  title={A Structured Local Memory Architecture for Persistent AI Agent Context},
  author={Bhardwaj, Varun Pratap},
  journal={arXiv preprint arXiv:2603.02240},
  year={2026}
}

Support / License / Qualixar

See CONTRIBUTING.md for guidelines. Wiki for detailed documentation.

GNU Affero General Public License v3.0 (AGPL-3.0). See LICENSE.

For commercial licensing (closed-source, proprietary, or hosted use), see COMMERCIAL-LICENSE.md or contact varun.pratap.bhardwaj@gmail.com.

Copyright (c) 2026 Varun Pratap Bhardwaj / Qualixar.

Part of Qualixar · Author: Varun Pratap Bhardwaj

Acknowledgments

• Everything Claude Code (ECC) — SLM's skill observation patterns were inspired by ECC's continuous learning architecture. SLM supports direct ingestion of ECC observations via slm ingest --source ecc. We recommend ECC for Claude Code users who want the deepest learning experience alongside SLM.

• HKUDS/OpenSpace — The skill evolution research in SLM draws from the EvoSkills co-evolutionary verification concepts (arXiv:2604.01687). We adopted their 3-trigger evolution system and anti-loop guard patterns.

Qualixar AI Agent Reliability Platform

Qualixar is building the open-source infrastructure for AI agent reliability engineering. Seven products, one coherent platform:

Local-first architecture. Deployment-specific privacy and compliance controls.

Start here → qualixar.com · All papers on Qualixar HuggingFace

Star This Project

If this project solves a real problem for you, please star the repo — it helps other developers discover Qualixar and signals that the AI agent reliability community is growing.

The live Star History chart is intentionally not embedded: its upstream service timed out during release validation. The link above is the stable, direct way to star and follow the repository.