superlocalmemory 3.4.17 → 3.4.19

package/docs/compliance.md

@@ -1,191 +0,0 @@
-# Compliance
-> SuperLocalMemory V3 Documentation
-> https://superlocalmemory.com | Part of Qualixar
-
-SuperLocalMemory is designed for organizations that need to meet data protection and privacy regulations. Mode A satisfies the strictest requirements by keeping all data local.
-
----
-
-## EU AI Act
-
-The EU AI Act (Regulation 2024/1689) establishes requirements for AI systems operating in the European Union.
-
-### Mode A: Full Compliance by Architecture
-
-In Mode A, SuperLocalMemory operates as a local data retrieval system with zero cloud dependency:
-
-| Requirement | How Mode A satisfies it |
-|-------------|------------------------|
-| **Data sovereignty** | All data stored and processed locally. Nothing leaves the device. |
-| **Right to erasure** | `slm forget` deletes data from the local database. No cloud logs exist to purge. |
-| **Transparency** | The retrieval pipeline is fully auditable. No black-box AI decisions. |
-| **Risk classification** | A local retrieval system with no autonomous decision-making qualifies as minimal risk. |
-
-### Mode B: Full Compliance
-
-Mode B uses a local LLM (Ollama). Data never leaves the device. Same compliance posture as Mode A.
-
-### Mode C: Shared Responsibility
-
-Mode C sends recall queries to a cloud LLM provider. In this mode:
-
-- **Your data** (stored memories) remains local
-- **Queries** are sent to the cloud provider
-- The cloud provider's compliance posture applies to those queries
-- A Data Processing Agreement (DPA) with your provider is recommended
-
-## GDPR
-
-The General Data Protection Regulation applies to personal data of EU residents.
-
-### Right to Erasure (Article 17)
-
-```bash
-# Delete specific memories
-slm forget "John's phone number"
-slm forget --id 42
-
-# Delete all memories before a date
-slm forget --before "2025-01-01"
-
-# Delete an entire profile
-slm profile delete client-eu
-```
-
-Deletion is permanent. In Mode A, there are no cloud copies to worry about.
-
-### Data Portability (Article 20)
-
-```bash
-# Export all memories for a profile
-slm profile export work > work-data.json
-
-# The export is standard JSON — readable by any system
-```
-
-### Data Minimization (Article 5)
-
-The entropy gate in the ingestion pipeline filters out redundant and low-value information automatically. Only memories with sufficient information value are stored.
-
-### Purpose Limitation
-
-Profiles enforce purpose limitation. Client A's data is stored in Client A's profile and is never accessible from another profile.
-
-## Retention Policies
-
-Named retention policies automate data lifecycle management.
-
-### Built-in policies
-
-| Policy | Retention period | Use case |
-|--------|:----------------:|----------|
-| `indefinite` | Forever | Default. No automatic deletion. |
-| `gdpr-30d` | 30 days | GDPR-compliant short retention |
-| `hipaa-7y` | 7 years | HIPAA medical records requirement |
-
-### Apply a policy
-
-```bash
-slm retention set gdpr-30d
-```
-
-This applies to the active profile. Memories older than the retention period are automatically archived and then deleted.
-
-### Custom policies
-
-```bash
-slm retention set custom --days 90
-```
-
-### Per-profile policies
-
-Different profiles can have different policies:
-
-```bash
-slm profile switch client-eu
-slm retention set gdpr-30d
-
-slm profile switch internal
-slm retention set indefinite
-```
-
-## Access Control
-
-SuperLocalMemory uses Attribute-Based Access Control (ABAC) per profile.
-
-- Each profile is an isolated access boundary
-- No cross-profile data access is possible
-- Profile switching requires the `slm profile switch` command
-- The audit trail logs all profile switches
-
-## Audit Trail
-
-Every memory operation is logged in a tamper-evident hash chain.
-
-### View the audit trail
-
-```bash
-slm audit                    # Recent entries
-slm audit --limit 100        # Last 100 entries
-slm audit --action store     # Only store operations
-slm audit --action delete    # Only delete operations
-```
-
-### Verify integrity
-
-```bash
-slm audit --verify
-```
-
-This checks the hash chain for tampering. Each entry contains a hash of the previous entry, creating a blockchain-like chain. Any modification to a past entry breaks the chain and is detected.
-
-### What gets logged
-
-| Action | What is recorded |
-|--------|-----------------|
-| `store` | Memory ID, timestamp, profile, content hash |
-| `recall` | Query, timestamp, profile, result count |
-| `delete` | Memory ID, timestamp, profile, reason |
-| `profile_switch` | From profile, to profile, timestamp |
-| `mode_change` | From mode, to mode, timestamp |
-| `migration` | Source version, target version, timestamp |
-
-## HIPAA
-
-For healthcare applications:
-
-1. Use Mode A (zero cloud) to ensure PHI never leaves the device
-2. Apply the `hipaa-7y` retention policy
-3. Use per-patient or per-case profiles for isolation
-4. Enable audit trail verification for compliance audits
-
-```bash
-slm profile create patient-12345
-slm profile switch patient-12345
-slm retention set hipaa-7y
-```
-
-## SOC 2
-
-SuperLocalMemory supports SOC 2 requirements through:
-
-- **Access controls:** Profile-based isolation with ABAC
-- **Audit logging:** Hash-chained, tamper-evident audit trail
-- **Data encryption:** SQLite database can be encrypted at rest using OS-level encryption (FileVault, BitLocker, LUKS)
-- **Change management:** All configuration changes are logged
-
-## Compliance Checklist
-
-| Requirement | Mode A | Mode B | Mode C |
-|-------------|:------:|:------:|:------:|
-| Data stays on device | Yes | Yes | Partial (queries sent to cloud) |
-| No cloud dependency | Yes | Yes | No |
-| Right to erasure | Yes | Yes | Yes (local); cloud logs depend on provider |
-| Audit trail | Yes | Yes | Yes |
-| Retention policies | Yes | Yes | Yes |
-| Profile isolation | Yes | Yes | Yes |
-| Tamper detection | Yes | Yes | Yes |
-
----
-
-*SuperLocalMemory V3 — Copyright 2026 Varun Pratap Bhardwaj. Elastic License 2.0. Part of Qualixar.*

package/docs/configuration.md

@@ -1,182 +0,0 @@
-# Configuration
-> SuperLocalMemory V3 Documentation
-> https://superlocalmemory.com | Part of Qualixar
-
-Control how SuperLocalMemory stores, retrieves, and processes your memories.
-
----
-
-## Three Operating Modes
-
-SuperLocalMemory runs in one of three modes. You pick the trade-off between privacy and power.
-
-| Mode | What it does | Needs API key? | Data leaves your machine? |
-|------|-------------|:--------------:|:-------------------------:|
-| **A: Zero-Cloud** | Math-based retrieval. No LLM calls. | No | Never |
-| **B: Local LLM** | Mode A + a local LLM via Ollama. | No | Never |
-| **C: Cloud LLM** | Mode B + a cloud LLM for maximum recall quality. | Yes | Yes (queries only) |
-
-### Check your current mode
-
-```bash
-slm mode
-```
-
-### Switch modes
-
-```bash
-slm mode a    # Zero-cloud (default)
-slm mode b    # Local LLM
-slm mode c    # Cloud LLM
-```
-
-Switching modes takes effect immediately. No data is lost.
-
-### Mode A: Zero-Cloud (Default)
-
-All operations run locally. Retrieval uses four channels (semantic similarity, keyword search, entity graph, and temporal context) combined with mathematical scoring. No network calls.
-
-Best for: privacy-sensitive work, air-gapped environments, EU AI Act compliance.
-
-### Mode B: Local LLM
-
-Everything from Mode A, plus a local LLM (via Ollama) that improves recall by understanding query intent and reranking results.
-
-**Setup:**
-
-```bash
-# Install Ollama (if not already installed)
-brew install ollama          # macOS
-curl -fsSL https://ollama.com/install.sh | sh  # Linux
-
-# Pull a model
-ollama pull llama3.2
-
-# Switch to Mode B
-slm mode b
-```
-
-Best for: developers who want better recall without sending data to the cloud.
-
-### Mode C: Cloud LLM
-
-Everything from Mode B, plus a cloud LLM for cross-encoder reranking and agentic multi-round retrieval. Highest recall quality.
-
-**Setup:**
-
-```bash
-slm mode c
-slm provider set openai
-```
-
-You will be prompted for your API key (stored locally in your config file, never transmitted except to the provider you choose).
-
-Best for: maximum recall quality when privacy constraints allow cloud calls.
-
-## Provider Configuration
-
-Mode C supports multiple LLM providers.
-
-### Set your provider
-
-```bash
-slm provider           # Show current provider
-slm provider set       # Interactive provider selector
-```
-
-### Supported providers
-
-| Provider | Command | Env variable |
-|----------|---------|-------------|
-| OpenAI | `slm provider set openai` | `OPENAI_API_KEY` |
-| Anthropic | `slm provider set anthropic` | `ANTHROPIC_API_KEY` |
-| Azure OpenAI | `slm provider set azure` | `AZURE_OPENAI_API_KEY` |
-| Ollama (local) | `slm provider set ollama` | None needed |
-| OpenRouter | `slm provider set openrouter` | `OPENROUTER_API_KEY` |
-
-### Set API keys
-
-You can set keys interactively or via environment variables:
-
-```bash
-# Interactive (stored in config file)
-slm provider set openai
-# Prompts: Enter your OpenAI API key: sk-...
-
-# Via environment variable (takes precedence)
-export OPENAI_API_KEY="sk-..."
-```
-
-## Config File
-
-All settings live in:
-
-```
-~/.superlocalmemory/config.json
-```
-
-### Example config
-
-```json
-{
-  "mode": "a",
-  "profile": "default",
-  "provider": {
-    "name": "openai",
-    "model": "gpt-4o-mini",
-    "api_key_env": "OPENAI_API_KEY"
-  },
-  "auto_capture": true,
-  "auto_recall": true,
-  "embedding_model": "all-MiniLM-L6-v2",
-  "max_recall_results": 10,
-  "retention": {
-    "default_policy": "indefinite"
-  }
-}
-```
-
-### Key settings
-
-| Setting | Default | Description |
-|---------|---------|-------------|
-| `mode` | `"a"` | Operating mode: `a`, `b`, or `c` |
-| `profile` | `"default"` | Active memory profile |
-| `auto_capture` | `true` | Automatically store decisions and context |
-| `auto_recall` | `true` | Automatically inject relevant memories |
-| `embedding_model` | `"all-MiniLM-L6-v2"` | Sentence transformer for semantic search |
-| `max_recall_results` | `10` | Maximum memories returned per query |
-
-## Environment Variables
-
-These override config file settings when set:
-
-| Variable | Purpose |
-|----------|---------|
-| `SLM_MODE` | Override operating mode |
-| `SLM_PROFILE` | Override active profile |
-| `SLM_DATA_DIR` | Override data directory (default: `~/.superlocalmemory/`) |
-| `OPENAI_API_KEY` | OpenAI API key for Mode C |
-| `ANTHROPIC_API_KEY` | Anthropic API key for Mode C |
-| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key for Mode C |
-| `OPENROUTER_API_KEY` | OpenRouter API key for Mode C |
-
-## Database Location
-
-All data is stored locally in:
-
-```
-~/.superlocalmemory/memory.db    # SQLite database
-~/.superlocalmemory/config.json  # Configuration
-~/.superlocalmemory/backups/     # Automatic backups
-```
-
-To use a custom location:
-
-```bash
-export SLM_DATA_DIR="/path/to/your/data"
-```
-
----
-
-*SuperLocalMemory V3 — Copyright 2026 Varun Pratap Bhardwaj. Elastic License 2.0. Part of Qualixar.*

package/docs/getting-started.md

@@ -1,102 +0,0 @@
-# Getting Started
-> SuperLocalMemory V3 Documentation
-> https://superlocalmemory.com | Part of Qualixar
-
-Get your AI's memory system running in under 5 minutes. **V3.1: Now with Active Memory — your memory learns from your usage and gets smarter over time, at zero token cost.**
-
----
-
-## Prerequisites
-
-- **Node.js** 18 or later
-- **Python** 3.10 or later (installed automatically on most systems)
-- An AI coding tool (Claude Code, Cursor, VS Code, Windsurf, or any MCP-compatible IDE)
-
-## Install
-
-```bash
-npm install -g superlocalmemory
-```
-
-This installs the `slm` command globally.
-
-## Run the Setup Wizard
-
-```bash
-slm setup
-```
-
-The wizard walks you through three choices:
-
-1. **Pick your mode**
-   - **Mode A** (default) — Zero cloud. All memory stays on your machine. No API key needed.
-   - **Mode B** — Local LLM. Uses Ollama on your machine for smarter recall.
-   - **Mode C** — Cloud LLM. Uses OpenAI, Anthropic, or another provider for maximum power.
-
-2. **Connect your IDE** — The wizard detects installed IDEs and configures them automatically.
-
-3. **Verify installation** — A quick self-test confirms everything works.
-
-> **Tip:** Start with Mode A. You can switch to B or C anytime with `slm mode b` or `slm mode c`.
-
-## Store Your First Memory
-
-```bash
-slm remember "The project uses PostgreSQL 16 on port 5433, not the default 5432"
-```
-
-You should see:
-
-```
-Stored memory #1 (Mode A, profile: default)
-```
-
-## Recall a Memory
-
-```bash
-slm recall "what database port do we use"
-```
-
-Output:
-
-```
-[1] The project uses PostgreSQL 16 on port 5433, not the default 5432
-    Score: 0.94 | Stored: 2 minutes ago | Profile: default
-```
-
-## Check System Status
-
-```bash
-slm status
-```
-
-This shows:
-
-- Current mode (A, B, or C)
-- Active profile
-- Total memories stored
-- Database location
-- Health of math layers (Fisher, Sheaf, Langevin)
-
-## How It Works With Your IDE
-
-Once connected, SuperLocalMemory works automatically:
-
-- **Auto-recall** — When your AI assistant responds, relevant memories are injected as context. No manual queries needed.
-- **Auto-capture** — Decisions, bug fixes, architecture choices, and preferences are stored as you work. No manual tagging needed.
-
-You can still use `slm remember` and `slm recall` from the terminal whenever you want explicit control.
-
-## Next Steps
-
-| What you want to do | Guide |
-|---------------------|-------|
-| Set up a specific IDE | [IDE Setup](ide-setup.md) |
-| Switch modes or providers | [Configuration](configuration.md) |
-| Learn all CLI commands | [CLI Reference](cli-reference.md) |
-| Migrate from V2 | [Migration from V2](migration-from-v2.md) |
-| Understand how it works | [Architecture](architecture.md) |
-
----
-
-*SuperLocalMemory V3 — Copyright 2026 Varun Pratap Bhardwaj. Elastic License 2.0. Part of Qualixar.*