vektor-slipstream 1.4.4 → 2.0.0

package/README.md

@@ -1,306 +1,67 @@
-# vektor-slipstream
-
-Hardware-accelerated persistent memory for AI agents. Local-first. No cloud. One-time payment.
-
-[![npm](https://img.shields.io/npm/v/vektor-slipstream)](https://www.npmjs.com/package/vektor-slipstream)
-[![downloads](https://img.shields.io/npm/dw/vektor-slipstream)](https://www.npmjs.com/package/vektor-slipstream)
-[![license](https://img.shields.io/badge/license-Commercial-blue)](https://vektormemory.com/product#pricing)
-
-## Install
-
-```bash
-npm install vektor-slipstream
-npx vektor setup
-```
-
-## Quick Start
-
-```js
-const { createMemory } = require('vektor-slipstream');
-
-const memory = await createMemory({
-  agentId:    'my-agent',
-  licenceKey: process.env.VEKTOR_LICENCE_KEY,
-});
-
-// Store a memory
-await memory.remember('User prefers TypeScript over JavaScript');
-
-// Recall by semantic similarity — avg 8ms, fully local
-const results = await memory.recall('coding preferences', 5);
-// → [{ content, score, id }]
-
-// Traverse the graph
-const graph = await memory.graph('TypeScript', { hops: 2 });
-
-// What changed in 7 days?
-const delta = await memory.delta('project decisions', 7);
-
-// Morning briefing
-const brief = await memory.briefing();
-```
-
----
-
-## CLI Chat — Persistent Memory Terminal
-
-Chat with any LLM with full memory across every session. Zero configuration.
-
-```bash
-npx vektor chat                          # start chat (auto-detects Ollama)
-npx vektor chat --provider claude        # use Anthropic Claude
-npx vektor chat --provider groq --model llama-3.3-70b-versatile
-npx vektor chat --provider gemini
-npx vektor chat --provider openai
-```
-
-### Providers
-
-| Provider | Details |
-|---|---|
-| `ollama` | Default — free, local, no API key. Auto-detects best installed model. |
-| `claude` | Anthropic Claude — set `ANTHROPIC_API_KEY` |
-| `openai` | OpenAI GPT — set `OPENAI_API_KEY` |
-| `groq` | Groq LLaMA — set `GROQ_API_KEY` (free tier available) |
-| `gemini` | Google Gemini — set `GEMINI_API_KEY` |
-
-Set a permanent default:
-```bash
-# Windows
-$env:VEKTOR_PROVIDER = "claude"
-
-# macOS/Linux
-export VEKTOR_PROVIDER=claude
-```
-
-### In-chat commands
-
-Type `/` to see available commands with autocomplete. Tab to select, arrow keys to navigate.
-
-| Command | Action |
-|---|---|
-| `/recall <query>` | Search MAGMA memory mid-conversation |
-| `/stats` | Show memory node count, edges, pinned |
-| `/briefing` | Generate memory briefing inline |
-| `/exit` | Exit chat (Ctrl+C also works) |
-
-### One-liner commands
-
-```bash
-# Store a fact
-npx vektor remember "I prefer TypeScript over JavaScript"
-npx vektor remember "deadline is Friday" --importance 5
-
-# Pipe support
-cat meeting-notes.txt | npx vektor remember
-
-# One-shot recall + LLM answer
-npx vektor ask "what stack am I using?"
-npx vektor ask "what did we decide about the database?"
-
-# Autonomous goal executor
-npx vektor agent "summarise everything I know about project Alpha"
-npx vektor agent "research AI memory tools" --steps 15 --provider groq
-```
-
-### Ollama auto-detection
-
-VEKTOR queries `http://localhost:11434/api/tags` and picks the best available model:
-`qwen3` → `qwen2` → `llama` → `mistral` → first available.
-
-Override:
-```bash
-$env:OLLAMA_MODEL = "qwen3.5:4b"
-export OLLAMA_MODEL=qwen3.5:4b
-```
-
----
-
-## All CLI Commands
-
-```bash
-npx vektor setup      # First-run wizard — licence, hardware, integrations
-npx vektor activate   # Activate licence key on this machine
-npx vektor test       # Test memory engine with progress bar
-npx vektor status     # System health check
-npx vektor mcp        # Start Claude Desktop MCP server
-npx vektor rem        # Run REM dream cycle
-npx vektor chat       # Persistent memory chat (all LLMs)
-npx vektor remember   # Store a fact
-npx vektor ask        # Query memory + LLM answer
-npx vektor agent      # Autonomous goal executor
-npx vektor help       # All commands
-```
-
----
-
-## Claude Desktop Extension (DXT)
-
-Install the `.dxt` extension for zero-config memory in every Claude Desktop session.
-
-**Install:** drag `vektor-slipstream.dxt` onto the Claude Desktop Extensions page.
-
-Once installed, Claude automatically:
-- Recalls relevant context at session start
-- Stores facts and decisions during conversation
-- Summarises at session end
-
-All 28 tools are available in Claude Desktop — no configuration needed beyond your licence key.
-
-**User config fields:**
-
-| Field | Purpose |
-|---|---|
-| `licence_key` | Your Polar licence key (required) |
-| `db_path` | Memory DB path (defaults to `~/vektor-slipstream-memory.db`) |
-| `project_path` | Default path for `cloak_cortex` project scanning (optional) |
-
-Download the latest `.dxt` from [vektormemory.com/docs/dxt](https://vektormemory.com/docs/dxt).
-
----
-
-## MCP Tools — All 28
-
-### Memory Tools
-
-| Tool | Function |
-|---|---|
-| `vektor_recall` | Semantic search across MAGMA graph |
-| `vektor_store` | Store memory with importance score |
-| `vektor_graph` | Traverse associative memory graph |
-| `vektor_delta` | See what changed on a topic over time |
-| `vektor_briefing` | Generate morning briefing from recent memories |
-
-### CLOAK Core
-
-| Tool | Function |
-|---|---|
-| `cloak_fetch` | Stealth headless browser fetch via Playwright |
-| `cloak_fetch_smart` | Checks `llms.txt` first, falls back to stealth browser |
-| `cloak_render` | Full CSS/DOM layout sensor |
-| `cloak_diff` | Semantic diff of URL since last fetch |
-| `cloak_diff_text` | Structural diff between two text blobs |
-| `cloak_passport` | AES-256-GCM credential vault (get/set/delete/list) |
-| `tokens_saved` | Token efficiency ROI calculator |
-
-### Identity Tools
-
-| Tool | Function |
-|---|---|
-| `cloak_identity_create` | Create persistent browser fingerprint identity |
-| `cloak_identity_use` | Apply saved identity to a fetch call |
-| `cloak_identity_list` | List all saved identities with trust summary |
-
-### Behaviour Tools
-
-| Tool | Function |
-|---|---|
-| `cloak_inject_behaviour` | Human mouse/scroll injection for reCAPTCHA/Cloudflare bypass |
-| `cloak_behaviour_stats` | List available patterns and categories |
-| `cloak_load_pattern` | Load custom recorded behaviour pattern |
-| `cloak_pattern_stats` | Self-improving pattern store tier breakdown |
-| `cloak_pattern_list` | List patterns with scores and tier |
-| `cloak_pattern_prune` | Remove stale/low-scoring patterns |
-| `cloak_pattern_seed` | Seed store with built-in patterns |
-
-### CAPTCHA Tools
-
-| Tool | Function |
-|---|---|
-| `cloak_detect_captcha` | Detect CAPTCHA type and sitekey |
-| `cloak_solve_captcha` | Solve via vision AI (Claude/GPT-4o/2captcha) |
-
-### Compression & Cortex Tools
-
-| Tool | Function |
-|---|---|
-| `turbo_quant_compress` | PolarQuant vector compression (~75% smaller) |
-| `turbo_quant_stats` | Compression ratio and savings stats |
-| `cloak_cortex` | Scan project directory into MAGMA entity graph |
-| `cloak_cortex_anatomy` | Get cached file anatomy without rescanning |
-
----
-
-## Claude Code Setup
-
-Add to `.claude/settings.json` in your project:
-
-```json
-{
-  "mcpServers": {
-    "vektor": {
-      "command": "node",
-      "args": ["/path/to/node_modules/vektor-slipstream/index.js"],
-      "env": {
-        "VEKTOR_LICENCE_KEY": "your-licence-key",
-        "CLOAK_PROJECT_PATH": "/path/to/your/project"
-      }
-    }
-  }
-}
-```
-
-All 28 tools are available in Claude Code via this config.
-
----
-
-## What's Included
-
-### Memory Core (MAGMA)
-
-- 4-layer associative graph — semantic, causal, temporal, entity
-- AUDN curation loop — zero contradictions, zero duplicates
-- REM dream cycle — up to 50:1 compression
-- Sub-20ms recall — HNSW index, local SQLite
-- Local ONNX embeddings — $0 embedding cost, no API key required
-
-### Integrations
-
-- **Claude Desktop** — DXT extension, 28 tools, auto-memory system prompt
-- **Claude Code** — MCP server, all 28 tools
-- **CLI** — `chat`, `remember`, `ask`, `agent` commands
-- **LangChain** — v1 + v2 adapter included
-- **OpenAI Agents SDK** — drop-in integration
-- **Gemini · Groq · Ollama** — provider agnostic
-
----
-
-## Performance
-
-| Metric | Value |
-|---|---|
-| Recall latency | ~8ms avg (local SQLite) |
-| Embedding cost | $0 — fully local ONNX |
-| Embedding latency | ~10ms GPU / ~25ms CPU |
-| First run | ~2 min (downloads ~25MB model once) |
-| Subsequent boots | <100ms |
-
-## Hardware Auto-Detection
-
-Zero config. VEKTOR detects and uses the best available accelerator:
-
-- **NVIDIA CUDA** — GPU acceleration
-- **Apple Silicon** — CoreML
-- **CPU** — optimised fallback, works everywhere
-
----
-
-## Licence
-
-Commercial licence. One-time payment of $159. Activates on up to 3 machines.
-Manage at [polar.sh](https://polar.sh).
-
-Purchase: [vektormemory.com/product#pricing](https://vektormemory.com/product#pricing)  
-Docs: [vektormemory.com/docs](https://vektormemory.com/docs)  
-Support: hello@vektormemory.com
-
----
-
-## Research
-
-Built on peer-reviewed research:
-
-- [MAGMA (arxiv:2601.03236)](https://arxiv.org/abs/2601.03236) — Multi-Graph Agentic Memory Architecture
-- [EverMemOS (arxiv:2601.02163)](https://arxiv.org/abs/2601.02163) — Self-Organizing Memory OS
-- [HippoRAG (arxiv:2405.14831)](https://arxiv.org/abs/2405.14831) — Neurobiologically Inspired Long-Term Memory (NeurIPS 2024)
-- [Mem0 (arxiv:2504.19413)](https://arxiv.org/abs/2504.19413) — Production-Ready Agent Memory
+# vektor-slipstream
+
+Hardware-accelerated persistent memory for AI agents. Local-first. No cloud. One-time payment.
+
+[![license](https://img.shields.io/badge/license-Commercial-blue)](https://vektormemory.com/product)
+[![website](https://img.shields.io/badge/website-vektormemory.com-black)](https://vektormemory.com)
+
+---
+
+## ⚠️ This package is a directory listing only
+
+**The SDK is not distributed via npm.**
+
+Purchase and download directly from:
+
+### 👉 [vektormemory.com/product](https://vektormemory.com/product)
+
+---
+
+## What is VEKTOR Slipstream?
+
+Persistent memory for AI agents — local, fast, private.
+
+- **MAGMA graph** — 4-layer associative memory (semantic · causal · temporal · entity)
+- **Sub-8ms recall** — HNSW index, local SQLite, no API calls
+- **42 MCP tools** — plug directly into Claude Desktop or Claude Code
+- **Zero cloud** — ONNX embeddings run 100% on your hardware
+- **One-time payment** — $159, activates on up to 3 machines
+
+---
+
+## Integrations
+
+- Claude Desktop (DXT extension, auto-memory)
+- Claude Code (MCP server)
+- CLI — `chat`, `remember`, `ask`, `agent`
+- LangChain, OpenAI Agents SDK, Gemini, Groq, Ollama
+
+---
+
+## Performance
+
+| Metric | Value |
+|---|---|
+| Recall latency | ~8ms avg (local SQLite) |
+| Embedding cost | $0 — fully local ONNX |
+| First run | ~2 min (downloads ~25MB model once) |
+| Subsequent boots | <100ms |
+
+---
+
+## Get Started
+
+1. Purchase at **[vektormemory.com/product](https://vektormemory.com/product)**
+2. Download the SDK from your licence dashboard
+3. Follow the setup guide at **[vektormemory.com/docs](https://vektormemory.com/docs)**
+
+---
+
+## Links
+
+| | |
+|---|---|
+| **Purchase** | [vektormemory.com/product](https://vektormemory.com/product) |
+| **Docs** | [vektormemory.com/docs](https://vektormemory.com/docs) |
+| **Research** | [vektormemory.com/research](https://vektormemory.com/research) |
+| **Support** | hello@vektormemory.com |

package/package.json

@@ -1,146 +1,14 @@
-{
-  "name": "vektor-slipstream",
-  "version": "1.4.4",
-  "description": "Hardware-accelerated persistent memory for AI agents. Local-first, zero cloud dependency, $0 embedding cost.",
-  "main": "slipstream-core-extended.js",
-  "types": "./types/index.d.ts",
-  "bin": {
-    "vektor": "vektor-cli.js"
-  },
-  "exports": {
-    ".": {
-      "types": "./types/index.d.ts",
-      "default": "./slipstream-core-extended.js"
-    },
-    "./cloak": "./cloak-index.js",
-    "./cloak-warmup": "./cloak-warmup.js",
-    "./db": "./slipstream-db.js",
-    "./embedder": "./slipstream-embedder.js",
-    "./cloak-behaviour": "./cloak-behaviour.js",
-    "./cloak-pattern-store": "./cloak-pattern-store.js",
-    "./cloak-recorder-auto": "./cloak-recorder-auto.js",
-    "./cloak-recorder-snippet": "./cloak-recorder-snippet.js",
-    "./cloak-turbo-quant": "./cloak-turbo-quant.js",
-    "./cloak/cortex": "./cortex.js",
-    "./cloak/axon": "./axon.js",
-    "./cloak/cerebellum": "./cerebellum.js",
-    "./cloak/token": "./token.js",
-    "./cloak/mcp": "./index.js",
-    "./boot": "./boot-patch.js",
-    "./errors": "./errors.js",
-    "./entity-resolver": "./entity-resolver.js"
-  },
-  "keywords": [
-    "ai",
-    "memory",
-    "agent",
-    "vector",
-    "sqlite",
-    "embeddings",
-    "langchain",
-    "openai",
-    "anthropic",
-    "claude",
-    "mcp",
-    "rag",
-    "persistent-memory",
-    "local-ai",
-    "onnx",
-    "mistral",
-    "cloak",
-    "ai-agent-memory",
-    "local-first",
-    "knowledge-graph",
-    "agentic-ai",
-    "llm-memory",
-    "vector-store",
-    "associative-memory",
-    "groq",
-    "ollama",
-    "gemini"
-  ],
-  "author": "VEKTOR Memory <hello@vektormemory.com>",
-  "license": "SEE LICENSE IN LICENSE",
-  "homepage": "https://vektormemory.com",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/Vektor-Memory/Vektor-memory.git"
-  },
-  "engines": {
-    "node": ">=18.0.0"
-  },
-  "dependencies": {
-    "better-sqlite3": "^12.8.0",
-    "onnxruntime-node": "^1.17.3",
-    "vektor-slipstream": "^1.4.4"
-  },
-  "optionalDependencies": {
-    "@anthropic-ai/sdk": "^0.82.0",
-    "@xenova/transformers": "^2.17.2",
-    "blessed": "^0.1.81",
-    "blessed-contrib": "^4.11.0",
-    "playwright": "^1.44.0",
-    "sqlite-vec-darwin-arm64": "^0.1.6",
-    "sqlite-vec-linux-x64": "^0.1.6",
-    "sqlite-vec-windows-x64": "^0.1.6"
-  },
-  "files": [
-    "slipstream-core.js",
-    "slipstream-db.js",
-    "slipstream-embedder.js",
-    "detect-hardware.js",
-    "vektor-licence.js",
-    "vektor-licence-prompt.js",
-    "vektor-cli.js",
-    "vektor-setup.js",
-    "vektor-banner-loader.js",
-    "vektor-tui.js",
-    "boot-screen.html",
-    "cloak-core.js",
-    "cloak-index.js",
-    "cloak-identity.js",
-    "cloak-captcha.js",
-    "cloak-llms.js",
-    "cloak-turbo-quant.js",
-    "cloak-warmup.js",
-    "cloak-behaviour.js",
-    "cloak-recorder-snippet.js",
-    "cloak-pattern-store.js",
-    "cloak-recorder-auto.js",
-    "sovereign.js",
-    "visualize.js",
-    "TENETS.md",
-    "README.md",
-    "CHANGELOG.md",
-    "LICENSE",
-    "cortex.js",
-    "axon.js",
-    "cerebellum.js",
-    "token.js",
-    "index.js",
-    "errors.js",
-    "forget.js",
-    "pin.js",
-    "briefing.js",
-    "inspect.js",
-    "audn-log.js",
-    "namespace.js",
-    "export-import.js",
-    "migrate-137.js",
-    "entity-resolver.js",
-    "models/model_quantized.onnx",
-    "models/vocab.json",
-    "types/index.d.ts",
-    "examples/",
-    "mistral/",
-    "vektor-slipstream.dxt",
-    "boot-patch.js",
-    "slipstream-core-extended.js"
-  ],
-  "publishConfig": {
-    "access": "public"
-  },
-  "devDependencies": {
-    "javascript-obfuscator": "^5.4.1"
-  }
-}
+{
+  "name": "vektor-slipstream",
+  "version": "2.0.0",
+  "description": "Hardware-accelerated persistent memory for AI agents. Purchase and download at vektormemory.com",
+  "keywords": ["memory", "ai", "agents", "mcp", "llm", "claude", "persistent-memory"],
+  "homepage": "https://vektormemory.com",
+  "bugs": { "url": "mailto:hello@vektormemory.com" },
+  "license": "SEE LICENSE IN https://vektormemory.com/product",
+  "author": "Vektor Memory <hello@vektormemory.com> (https://vektormemory.com)",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/Vektor-Memory/Vektor-memory"
+  }
+}

package/CHANGELOG.md

@@ -1,139 +0,0 @@
-# VEKTOR v1.3.7 — Changelog
-
-Released: 2026-04-05
-
-## New features
-
-### memory.forget(id)
-Hard-deletes a memory and cascades to all graph edges. Throws if memory is pinned — must unpin first.
-```js
-await memory.forget('mem_abc123');
-// → { deleted: true, edgesRemoved: 4 }
-```
-
-### memory.forgetWhere(query, opts)
-Semantic bulk-delete. Preview with `dryRun: true` before committing.
-```js
-await memory.forgetWhere('Project Atlas', { dryRun: true });
-await memory.forgetWhere('Project Atlas', { minScore: 0.9, limit: 5 });
-```
-
-### memory.pin(id) / memory.unpin(id) / memory.listPinned()
-Mark memories as permanent — REM cycle will never compress or delete them.
-```js
-const { id } = await memory.remember('User is allergic to peanuts');
-await memory.pin(id);
-await memory.listPinned(); // → all pinned memories
-```
-
-### memory.inspect()
-Full diagnostic snapshot — no more raw SQLite queries to debug state.
-```js
-const state = memory.inspect();
-state.counts       // → { memories: 247, pinned: 3, edges: 7180 }
-state.rem          // → { totalDreams: 11, compressionRatio: '0.06' }
-state.graph.topNodes  // → 5 most-connected memories
-```
-
-### memory.auditLog(opts) / memory.auditStats()
-Full AUDN decision history. Nothing disappears silently.
-```js
-memory.auditLog({ action: 'DELETE', since: '7d' });
-// → [{ action, memory_id, content, reason, similarity, ran_at }]
-```
-
-### memory.briefing({ since }) — scoped date filtering
-```js
-await memory.briefing({ since: '7d' });
-await memory.briefing({ since: '12h', minImportance: 0.7 });
-await memory.briefing({ since: '2026-01-01', raw: true });
-```
-
-### memory.export() / memory.import()
-Full graph serialisation with checksum integrity.
-```js
-const bundle = memory.export();
-fs.writeFileSync('backup.vektor.json', JSON.stringify(bundle));
-
-memory.import(bundle);
-// → { imported: 244, skipped: 3, edgesAdded: 7100 }
-
-memory.import(bundle, { dryRun: true });    // preview
-memory.import(bundle, { mode: 'replace' }); // wipe and restore
-```
-
-### Namespace support
-Scope all reads/writes to prevent project bleed.
-```js
-const memory = await createMemory({ agentId: 'my-agent', namespace: 'project-atlas' });
-memory.listNamespaces();
-// → [{ namespace: 'project-atlas', memories: 18 }, ...]
-```
-
-### TypeScript types
-Full `.d.ts` declarations for all public API methods. No more flying blind in your IDE.
-Add to `tsconfig.json`: `"types": ["vektor-slipstream"]`
-
-### Structured error codes
-Replace string catch blocks with reliable `VektorError.code` switching.
-```js
-import { VektorError, ERR } from 'vektor-slipstream/errors';
-
-try {
-  await memory.remember(...)
-} catch (e) {
-  if (e instanceof VektorError) {
-    switch (e.code) {
-      case ERR.LICENCE_INVALID: // handle
-      case ERR.EMBED_FAILED:    // retry
-    }
-  }
-}
-```
-
-## Schema changes
-Run `npx vektor migrate` after updating, or migration runs automatically on startup.
-
-New columns:
-- `memories.pinned` INTEGER DEFAULT 0
-- `memories.namespace` TEXT DEFAULT 'default'
-- `memories.updated_at` INTEGER
-
-New tables:
-- `audn_log` — AUDN decision audit trail
-- `rem_log` — REM cycle run history (if not already present)
-- `vektor_meta` — schema version tracking
-
-## Bug fixes
-- REM cycle now skips pinned memories (previously could compress critical facts)
-- AUDN deletions now logged before execution (previously silent)
-- briefing() no longer returns stale summary when no memories exist in window
-
-## Breaking changes
-None. All new methods are additive. Existing code works unchanged.
-Migration is backward-compatible — new columns have safe defaults.
-
-## Gemini security review fixes (round 1 — applied)
-- `briefing.js` — pinned memory query now has LIMIT 50 (context bomb prevention)
-- `briefing.js` — `parseSince()` guards against `Date.now()` ms being passed as unix seconds
-- `forget.js` — `forgetWhere()` selective error catching — infra errors re-thrown, only expected skips swallowed
-- `namespace.js` — O(N) JS delete loop replaced with bulk SQL subquery (2 statements vs N*2)
-- `inspect.js` — all `SUM()` aggregations wrapped in `IFNULL(..., 0)` — no more `null` in charts
-- `migrate-137.js` — `PRAGMA table_info()` replaces brittle error-message string matching
-
-## Gemini security review fixes (round 2 — applied)
-- `export-import.js` — Fix 1: `IN (...memIds)` placeholders replaced with SQL subqueries — no more 32,766 param limit crash on large exports
-- `export-import.js` — Fix 2: O(N) loop in `replace` mode replaced with bulk subquery deletes
-- `export-import.js` — Fix 3: checksum now hashes full memories payload — content/importance tampering now detectable
-- `export-import.js` — Fix 4: dangling edge guard — edges only inserted if both source and target exist in destination (`WHERE EXISTS`)
-- `export-import.js` — `edgesSkipped` added to import return value with console.warn for partial imports
-
-## Gemini security review fixes (round 3 — applied)
-- `forget.js` — pinned edge orphan guard: blocks deleting a memory that shares
-  a graph edge with a pinned memory — prevents silent MAGMA traversal corruption
-- `namespace.js` — SQLITE_BUSY retry loop: 3 attempts × 100ms using
-  `Atomics.wait` (correct sync sleep for better-sqlite3) before propagating error
-- `export-import.js` — confirmed: empty bundle guard (line 103) already sits
-  before checksum computation (line 107) — correct order, no change needed
-
-## Total fixes across 3 Gemini review rounds: 13