Metadata-Version: 2.4
Name: pdm-memory
Version: 0.2.4
Summary: Pressure-Driven Memory (PDM) — persistent, resonance-based memory for AI apps.
Author: Westfield Innovations LLC
License: Elastic License 2.0 (ELv2)
        =========================
        
        Copyright (c) 2026 Westfield Innovations LLC
        
        Core software modification and redistribution of altered versions are
        prohibited without a commercial license from Westfield Innovations LLC.
        Extensions via defined plugin interfaces (e.g., BaseStorage) are permitted.
        
        Patent Pending — U.S. App. No. 19/739,419 | 63/953,563 | 63/953,842
        
        The software in this repository is licensed under the Elastic License 2.0
        (the text of which follows), subject to the additional Westfield Innovations
        LLC restrictions stated above. Free use is permitted "as-shipped". Unauthorized
        modification, forking, or redistribution of altered core logic is prohibited
        without a separate commercial license from Westfield Innovations LLC.
        
        --------------------------------------------------------------------------
        Elastic License 2.0
        --------------------------------------------------------------------------
        
        ## Acceptance
        
        By using the software, you agree to all of the terms and conditions below.
        
        ## Copyright License
        
        The licensor grants you a non-exclusive, royalty-free, worldwide,
        non-sublicensable, non-transferable license to use, copy, distribute, make
        available, and prepare derivative works of the software, in each case subject
        to the limitations and conditions below.
        
        ## Limitations
        
        You may not provide the software to third parties as a hosted or managed
        service, where the service provides users with access to any substantial set
        of the features or functionality of the software.
        
        You may not move, change, disable, or circumvent the license key functionality
        in the software, and you may not remove or obscure any functionality in the
        software that is protected by the license key.
        
        You may not alter, remove, or obscure any licensing, copyright, or other
        notices of the licensor in the software. Any use of the licensor's trademarks
        is subject to applicable law.
        
        ## Patents
        
        The licensor grants you a license, under any patent claims the licensor can
        license, or becomes able to license, to make, have made, use, sell, offer for
        sale, import and have imported the software, in each case subject to the
        limitations and conditions in this license. This license does not cover any
        patent claims that you cause to be infringed by modifications or additions to
        the software. If you or your company make any written claim that the software
        infringes or contributes to infringement of any patent, your patent license
        for the software granted under these terms ends immediately. If your company
        makes such a claim, your patent license ends immediately for work on behalf of
        your company.
        
        ## Notices
        
        You must ensure that anyone who gets a copy of any part of the software from
        you also gets a copy of these terms.
        
        If you modify the software, you must include in any modified copies of the
        software prominent notices stating that you have modified the software.
        
        ## No Other Rights
        
        These terms do not imply any licenses other than those expressly granted in
        these terms.
        
        ## Termination
        
        If you use the software in violation of these terms, such use is not licensed,
        and your licenses will automatically terminate. If the licensor provides you
        with a notice of your violation, and you cease all violation of this license
        no later than 30 days after you receive that notice, your licenses will be
        reinstated retroactively. However, if you violate these terms after such
        reinstatement, any additional violation of these terms will cause your
        licenses to terminate automatically and permanently.
        
        ## No Liability
        
        As far as the law allows, the software comes as is, without any warranty or
        condition, and the licensor will not be liable to you for any damages arising
        out of these terms or the use or nature of the software, under any kind of
        legal claim.
        
        ## Definitions
        
        The **licensor** is the entity offering these terms, and the **software** is
        the software the licensor makes available under these terms, including any
        portion of it.
        
        **you** refers to the individual or entity agreeing to these terms.
        
        **your company** is any legal entity, sole proprietorship, or other kind of
        organization that you work for, plus all organizations that have control over,
        are under the control of, or are under common control with that organization.
        **control** means ownership of substantially all the assets of an entity, or
        the power to direct its management and policies by vote, contract, or
        otherwise. Control can be direct or indirect.
        
        **your licenses** are all the licenses granted to you for the software under
        these terms.
        
        **use** means anything you do with the software requiring one of your licenses.
        
        **trademark** means trademarks, service marks, and similar rights.
        
Project-URL: Homepage, https://azus.ai
Project-URL: Documentation, https://azus.ai/support
Project-URL: Bug Tracker, https://azus.ai/support?tab=bugs
Project-URL: Source, https://github.com/westfield-innovations/pdm-memory
Project-URL: Repository, https://github.com/westfield-innovations/pdm-memory
Keywords: ai,memory,llm,rag,pressure-driven,persistent-memory
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: Other/Proprietary License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: httpx>=0.27
Provides-Extra: openai
Requires-Dist: openai>=1.0; extra == "openai"
Requires-Dist: tiktoken>=0.7; extra == "openai"
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.25; extra == "anthropic"
Provides-Extra: gemini
Requires-Dist: google-genai>=0.1.0; extra == "gemini"
Provides-Extra: ollama
Requires-Dist: ollama>=0.2.0; extra == "ollama"
Provides-Extra: groq
Requires-Dist: groq>=0.9.0; extra == "groq"
Provides-Extra: all
Requires-Dist: openai>=1.0; extra == "all"
Requires-Dist: tiktoken>=0.7; extra == "all"
Requires-Dist: anthropic>=0.25; extra == "all"
Requires-Dist: google-genai>=0.1.0; extra == "all"
Requires-Dist: ollama>=0.2.0; extra == "all"
Requires-Dist: groq>=0.9.0; extra == "all"
Provides-Extra: ui
Requires-Dist: fastapi>=0.110; extra == "ui"
Requires-Dist: uvicorn[standard]>=0.27; extra == "ui"
Provides-Extra: postgres
Requires-Dist: psycopg[binary]>=3.1; extra == "postgres"
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-cov>=5.0; extra == "dev"
Requires-Dist: respx>=0.21; extra == "dev"
Requires-Dist: openai>=1.0; extra == "dev"
Requires-Dist: anthropic>=0.25; extra == "dev"
Requires-Dist: tiktoken>=0.7; extra == "dev"
Requires-Dist: google-genai>=0.1.0; extra == "dev"
Requires-Dist: ollama>=0.2.0; extra == "dev"
Requires-Dist: groq>=0.9.0; extra == "dev"
Requires-Dist: fastapi>=0.110; extra == "dev"
Requires-Dist: uvicorn[standard]>=0.27; extra == "dev"
Dynamic: license-file

# PDM — Memory for AI Apps That Works Like Memory

[![PyPI](https://img.shields.io/pypi/v/pdm-memory)](https://pypi.org/project/pdm-memory/)
[![Python](https://img.shields.io/pypi/pyversions/pdm-memory)](https://pypi.org/project/pdm-memory/)
[![License: Proprietary](https://img.shields.io/badge/License-Proprietary%20ELv2-blue)](LICENSE)
[![Documentation](https://img.shields.io/badge/Docs-azus.ai%2Fsupport-blue)](https://azus.ai/support)

Your LLM forgets everything between conversations. The standard fix — stuff a vector database into the context window — is expensive, slow, and retrieves **what matches words, not what matters**.

**PDM stores meaning signatures instead of raw text.** Memories that get used grow stronger. Memories that don't, fade. Retrieval works by resonance: the question itself surfaces what's relevant, instead of a keyword search digging for it.

- 🔑 **Your API key.** Works with your existing Anthropic/OpenAI account.
- 🗄️ **Your storage.** One local file. Your data never leaves your machine. Check the source — there's no phone-home in it.
- 🛡️ **Guarded agents.** Pass a rule as a string — blocks actions that contradict it. No store required. Catches contradicting facts automatically.
- ⚡ **Ten minutes.** `pip install pdm-memory` → three lines → persistent memory.

📖 **Documentation:** [azus.ai/support](https://azus.ai/support)

**Benchmarks vs standard RAG:** PDM wins **7 of 8** metrics — **15×** fewer tokens, **35×** less storage. One loss published. [See full methodology →](https://azus.ai/pdm/benchmarks)

---

## Table of Contents

0. [Documentation](https://azus.ai/support)
1. [Privacy Mode](#-privacy-mode-local-sqlite)
2. [Ecosystem Mode](#-ecosystem-mode-azus-cloud)
3. [LLM Adapters](#-llm-adapters)
4. [Guarded Agents (GAA & Torsion)](#-guarded-agents-gaa--torsion)
5. [Data Ingestion](#-data-ingestion)
6. [Developer Tools](#-developer-tools)
7. [API Reference](#-api-reference)
8. [License](#-license)

---

## 🔒 Privacy Mode (Local SQLite)

Zero setup. No network calls. Your data stays in a single file on your machine.

### Install

```bash
pip install pdm-memory
# With OpenAI support:
pip install "pdm-memory[openai]"
# With Anthropic support:
pip install "pdm-memory[anthropic]"
# Everything:
pip install "pdm-memory[all]"
```

### Quick Start

```python
from pdm_memory import Memory

# One line to start. The .db file is created automatically.
mem = Memory(store="./my_app_memory.db")

# Write: PDM assigns pressure and stores a signature.
mem.save("User prefers metric units and short answers", source="chat",
         tags=["units", "formatting", "preferences"], p_magnitude=85)

# Read: resonance retrieval — surfaces what's relevant, not just what matches.
hits = mem.recall("how should I format the answer?", k=5)

for h in hits:
    print(h.text, h.pressure, h.last_reinforced)

# Reinforce a memory manually (recall() does this automatically).
mem.reinforce(hits[0].id)

# Inspect why a memory surfaced.
report = mem.explain(hits[0].id, query="how should I format the answer?")
print(report.render())

# Decay runs automatically on each recall(). Manual trigger:
counts = mem.decay()
print(f"Decayed: {counts['decayed']}, Deleted: {counts['deleted']}")
```

### Privacy-First Mode

Store only SHA-256 hashes of memory text — the content never touches disk:

```python
mem = Memory(store="./private.db", store_raw=False)
```

---

## ☁️ Ecosystem Mode (AZUS Cloud)

Connect to the **AZUS Companion API** so memories sync across devices and the companion app.

**Cloud endpoint:** default base URL is `https://api.azus.ai` (not the marketing site `https://azus.ai`). Staging: `https://staging.azus.ai`.

CloudDriver expects a Companion build that exposes the PDM SDK routes (list, batch, by-hash / by-idempotency-key, soft-delete). Older deploys still support single-row `ingest` / get / patch / hard delete only.

### Getting your JWT access token

AZUS Cloud uses standard JWT auth. If you already have an AZUS account, sign in and use the returned `access` token as `token="..."`.

If you do not have an account yet, create one here:

- Web signup: [azus.ai/auth/register](https://azus.ai/auth/register)
- API signup: `POST https://api.azus.ai/api/v1/accounts/auth/register/`
- API login: `POST https://api.azus.ai/api/v1/accounts/auth/login/`
- Token refresh: `POST https://api.azus.ai/api/v1/accounts/token/refresh/`

Example registration flow:

```python
import requests

r = requests.post(
    "https://api.azus.ai/api/v1/accounts/auth/register/",
    json={
        "email": "user@example.com",
        "username": "user123",
        "password": "SecurePass123!",
        "profile": {"first_name": "John", "last_name": "Doe"},
    },
)
data = r.json()

access_token = data["tokens"]["access"]
refresh_token = data["tokens"]["refresh"]
```

Use the returned JWTs directly with `Memory(store="cloud", ...)`:

### Connect to the Cloud

```python
from pdm_memory import Memory

mem = Memory(
    store="cloud",
    token="eyJ...",               # AZUS JWT access token
    refresh_token="eyJ...",       # optional — auto-refresh on 401
    cloud_url="https://api.azus.ai",  # optional; this is the default
    user="your_username",         # ownership scope for storage ops
)

# Writes use POST /api/v1/pdm/ingest; dedupe hits the by-hash API when available.
mem.save(
    "User's team is in Kyiv (UTC+3)",
    source="manual",
    tags=["location", "team", "timezone"],
    p_magnitude=70,
    dedupe=True,
)
# Exact-once create on retries: pass idempotency_key=...
hits = mem.recall("what timezone are they in?")

# Batch write (POST /pdm/ingest/batch when supported)
mem.save_many(
    [
        {"text": "Fact A", "tags": ["a", "b", "c"], "p_magnitude": 70, "source": "manual"},
        {"text": "Fact B", "tags": ["a", "b", "c"], "p_magnitude": 70, "source": "manual"},
    ],
    dedupe=False,
)
```

### Soft delete vs hard delete

- `mem.delete(id)` → soft-delete (`is_deleted`) when the API supports it; cloud list/get hide those rows.
- Permanent removal is storage-level `hard_delete` (CloudDriver), not the default Memory facade API.

### Sync Local ↔ Cloud

```python
# Start with a local store
local_mem = Memory(store="./local.db")
local_mem.save("Local preference", tags=["pref", "local", "test"])

# Push local memories to cloud
report = local_mem.sync(
    direction="push",
    token="eyJ...",
    cloud_url="https://api.azus.ai",
)
print(report)   # SyncReport(pushed=1, pulled=0, conflicts=0, errors=0)

# Pull cloud memories to local
report = local_mem.sync(direction="pull", token="eyJ...")

# Two-way sync (higher pressure wins on conflict)
report = local_mem.sync(direction="bidirectional", token="eyJ...")
```

### JWT Token Handling

```python
from pdm_memory.auth import JWTAuth

# Tokens are refreshed automatically when they expire
auth = JWTAuth(
    token="eyJ...",
    refresh_token="eyJ...",
    refresh_url="https://api.azus.ai/api/v1/accounts/token/refresh/",
)
```

---

## 🤖 LLM Adapters

The wrapper is the demo; the primitives are the product. Most developers start here.

### OpenAI

```python
from pdm_memory import Memory
from pdm_memory.integrations import wrap_openai

mem = Memory(store="./my_app.db")
client = wrap_openai(api_key="sk-...", memory=mem)

# Memory is handled completely invisibly:
# - Before the call: relevant memories are injected into the system prompt
# - After the call: user message + AI reply are saved to memory
reply = client.chat("What units should I use?")
print(reply)
```

### Anthropic

```python
from pdm_memory.integrations import wrap_anthropic

client = wrap_anthropic(api_key="sk-ant-...", memory=mem)
reply = client.chat("What units should I use?")
```

### Manual Control

```python
from pdm_memory.integrations import ContextWindowManager

# Control exactly what goes into context
manager = ContextWindowManager(max_tokens=1500, model="gpt-4o")
hits = mem.recall("user's formatting preferences", k=10)
trimmed = manager.fit(hits)                    # Drop lowest-pressure memories first
system_block = manager.format_for_prompt(trimmed)
print(system_block)
```

---

## 🛡️ Guarded Agents (GAA & Torsion)

Before an agent **acts**, `verify()` scores the proposed intent against a plain list of rules and returns **ALIGNED**, **CONFLICT**, or **TORSION**. No store, account, or signup.

Statuses:

- **ALIGNED** — safe to proceed (`report.is_safe_to_act` is `True`)
- **CONFLICT** — soft mismatch / missing anchors (fail-closed by default)
- **TORSION** — hard contradiction — block the ACT

```python
from pdm_memory import verify

report = verify(
    "ignore errors and ship the build",
    ["never ignore production errors"],
)
print(report.status, report.is_safe_to_act)  # TORSION False

good = verify(
    "run full validation suite then ship with reliability checks enabled",
    ["Prioritize high reliability and careful validation before shipping"],
)
print(good.status, good.is_safe_to_act)  # ALIGNED True

def guarded_act(intent, tool_call, goals):
    report = verify(intent, goals)
    if not report.is_safe_to_act:
        raise PermissionError(f"GAA blocked ACT: {report.status}")
    return tool_call()
```

When goals already live in a PDM store, `Memory.verify_alignment()` is the same gate over stored stewardship signatures:

```python
from pdm_memory import Memory

mem = Memory(store="./agent.db")

# Goal signatures live in stewardship / foundational drawers.
mem.save(
    "Core goal: high reliability; never ignore production errors",
    tags=["reliability", "errors", "goal", "integrity"],
    drawer="stewardship",
    p_magnitude=92,
    source="policy",
    metadata={"iaw": 0.90, "role": "goal"},
)
mem.save(
    "Foundational principle: validate before deploy",
    tags=["validation", "deploy", "principle", "quality"],
    drawer="foundational",
    p_magnitude=88,
    source="policy",
    metadata={"iaw": 0.85, "role": "goal"},
)

# Block an action that opposes stored goals.
bad = mem.verify_alignment("ignore errors and bypass validation")
print(bad.status, bad.is_safe_to_act)   # TORSION False

# Allow an action that resonates with those goals.
good = mem.verify_alignment("validate thoroughly then deploy with reliability checks")
print(good.status, good.is_safe_to_act)  # ALIGNED True
```

Catch contradicting facts already in the store:

```python
from datetime import datetime, timezone

mem.save(
    "Project Orion launch date is 2026-08-01",
    tags=["orion", "launch", "deadline", "project"],
    drawer="product",
    p_magnitude=70,
    deadline=datetime(2026, 8, 1, tzinfo=timezone.utc),
    metadata={"cluster_id": "orion-launch"},
)
mem.save(
    "Project Orion launch date is 2026-09-01",
    tags=["orion", "launch", "deadline", "project"],
    drawer="product",
    p_magnitude=72,
    deadline=datetime(2026, 9, 1, tzinfo=timezone.utc),
    metadata={"cluster_id": "orion-launch"},
)

for report in mem.detect_torsion(threshold=0.5):
    print(report.torsion_score, report.conflict_kind, report.explanation)
```

Full walkthroughs: `python -m pdm_memory.examples.standalone_guard`, `python -m pdm_memory.examples.guarded_agent_logic` and `python -m pdm_memory.examples.handling_contradictions`.

---

## 📥 Data Ingestion

### Import Legacy Data

```python
# From a list of dicts
mem.ingest(
    data_source=[
        {"text": "User hates Comic Sans", "importance": 85},
        {"content": "Team deploys on Fridays — bad idea", "labels": "devops,process,risk"},
    ],
    mapping={"text": "compressed_fact", "importance": "p_magnitude"},
)

# From a CSV file (auto-detects common column names)
mem.ingest("./old_chat_logs.csv")

# With progress tracking
def on_progress(processed, total):
    print(f"{processed}/{total} records processed")

mem.ingest("./large_dataset.csv", on_progress=on_progress)
```

### Auto-Generate Signatures with an LLM

```python
import openai
client = openai.OpenAI(api_key="sk-...")

# LLM will compress raw text → compressed_fact + 3 tags + p_magnitude
mem.ingest(
    data_source=["User complains about slow API responses every Monday morning"],
    llm_client=client,
)
```

### Batch Processing (Large Datasets)

```python
# 10,000 records processed in batches of 50, with rate limiting
mem.ingest(
    data_source="./10k_records.csv",
    batch_size=50,
)
```

---

## 🛠️ Developer Tools

### Quick Start (PyPI install)

Everything below works after `pip install pdm-memory` — no repository clone required.

```bash
pip install pdm-memory
python -m pdm_memory.examples.hello_pdm
```

Inline smoke test:

```bash
python -c "
from pdm_memory import Memory
mem = Memory(store='./demo.db')
mem.save('User prefers metric units and short answers', source='demo',
         tags=['units', 'formatting', 'preferences'], p_magnitude=85)
for h in mem.recall('how should I format the answer?', k=3):
    print(h.text, round(h.pressure, 1))
"
```

Other PyPI-shipped tools:

```bash
python -m pdm_memory.bench --quick   # smoke benchmark (5 scenarios)
pdm-cli stats --store ./demo.db      # inspect the store created above
```

### Example walkthroughs (bundled in PyPI)

All scripts below ship inside the wheel — run them with `python -m`:

```bash
pip install pdm-memory
python -m pdm_memory.examples.hello_pdm                 # save / recall / explain
python -m pdm_memory.examples.standalone_guard          # GAA: no store
python -m pdm_memory.examples.guarded_agent_logic       # GAA: store-backed TORSION vs ALIGNED
python -m pdm_memory.examples.handling_contradictions     # detect + reconcile torsion
python -m pdm_memory.examples.temporal_recall_demo        # event_at + deadline (PDM-T)
python -m pdm_memory.examples.industrial_safety_gate      # Oil Field: Auto-Discovery + heal
```

See [`pdm_memory/examples/README.md`](pdm_memory/examples/README.md).

From a source checkout, the wrappers in [`examples/`](examples/) delegate to the same modules:

```bash
pip install .
python examples/hello_pdm.py
```

To run the test suite (contributors):

```bash
pip install ".[dev]"
pytest
```

### The explain Method

```python
report = mem.explain(memory_id, query="how should I format this?")
print(report.render())
```

```
╔══════════════════════════════════════════════════════
║  PDM Memory Explain Report
╠══════════════════════════════════════════════════════
║  ID:              abc12345-...
║  Fact:            User prefers metric units and short answers
║  Tags:            units, formatting, preferences
╠──────────────────────────────────────────────────────
║  Pressure Components:
║    p_magnitude:    80.00
║    V coefficient:  0.8333  (4 retrievals)
║    Decay factor:   0.0231  (1.0d since retrieved, T½=30d)
║    Intent weight:  1.0000
║    Quality:        0.80
║    ─────────────────────────────
║    P_effective:    55.28
╠──────────────────────────────────────────────────────
║  Resonance (TAS coupling):
║    coupling_score:     0.8750
║    tag_overlap:        1.0000
║    domain_match:       1.0000
╚══════════════════════════════════════════════════════
```

### Benchmark Harness

```bash
# Run full benchmark (PDM vs keyword+recency baseline)
python -m pdm_memory.bench

# Quick smoke test (5 scenarios)
python -m pdm_memory.bench --quick

# Save results as JSON
python -m pdm_memory.bench --output results.json
```

### CLI Tool

```bash
# List all memories
pdm-cli list-memories --store ./my_app.db

# Filter by pressure
pdm-cli list-memories --store ./my_app.db --min-pressure 60

# Explain a specific memory
pdm-cli explain abc12345 --store ./my_app.db --query "formatting"

# Trigger a decay pass (dry run first)
pdm-cli decay --store ./my_app.db --dry-run
pdm-cli decay --store ./my_app.db

# Show stats
pdm-cli stats --store ./my_app.db

# Store-free GAA — no .db required
pdm-cli verify "ignore errors and ship" --goal "never ignore production errors"

# List drawers (categories)
pdm-cli drawers --store ./my_app.db

# Sync to cloud
pdm-cli sync --store ./my_app.db --token eyJ... --direction push

# Launch visual dashboard (requires: pip install "pdm-memory[ui]")
pdm-cli ui --store ./my_app.db --port 8080
```

### PDM Explorer (Visual Dashboard)

```bash
pip install "pdm-memory[ui]"
pdm-cli ui --store ./local.db --port 8080
```

Opens `http://localhost:8080` with a D3 force graph:

- **Node size** ∝ live `P_effective` (decay made visible)
- **Edges** = high tag resonance
- **Red glow** = torsion conflict on that signature

API endpoints used by the UI: `GET /api/v1/memory-map`, `GET /api/v1/torsion`.

---

## 📖 API Reference

### `verify(intent_text, goals)`

Store-free Goal-Anchor Alignment. Pass a proposed action and one or more rule strings. Returns `AlignmentReport` (`ALIGNED` / `CONFLICT` / `TORSION`). No SQLite, cloud, or account.

| Arg | Description |
|-----|-------------|
| `intent_text` | Proposed action / intent to validate |
| `goals` | One rule string, or a list of rule strings |
| `torsion_threshold` | Peak torsion that escalates to `TORSION` (default `0.70`) |
| `conflict_threshold` | Soft-mismatch floor for `CONFLICT` (default `0.40`) |

Use `report.is_safe_to_act` (True only when `status == "ALIGNED"`) before triggering ACT.

### `Memory(store, user, token, refresh_token, cloud_url, store_raw)`

| Method | Description |
|--------|-------------|
| `save(text, source, tags, p_magnitude, t_persistence, drawer, regime, deadline, dedupe=True, idempotency_key=None)` | Store a memory (content dedupe and/or idempotency when storage supports it) |
| `save_many(items, dedupe=True)` → `dict` | Batch save; returns `{saved, skipped, errors}` |
| `recall(query, k, min_pressure, search_cost, drawer, reinforce)` → `List[MemoryHit]` | Retrieve top-k relevant memories |
| `verify_alignment(intent_text, min_pressure, k_goals, torsion_threshold)` → `AlignmentReport` | Same GAA gate against goals already stored in Memory |
| `detect_torsion(drawer, threshold)` → `List[TorsionReport]` | Find contradicting facts (Reverse Resonance) |
| `reinforce(memory_id, coupling_score)` | Manually raise a memory's pressure (and V-counters where supported) |
| `delete(memory_id)` → `bool` | Soft-delete when storage supports it |
| `decay(dry_run)` → `dict` | Trigger decay pass (runs automatically on recall) |
| `explain(memory_id, query)` → `ExplainReport` | Show why a memory has its current pressure |
| `list(limit, min_pressure, drawer, cursor_id)` → `MemoryListPage` | Keyset page of memories (storage list API on cloud) |
| `sync(direction, token, cloud_url)` → `SyncReport` | Sync local ↔ cloud |
| `ingest(data_source, mapping, llm_client, batch_size)` → `dict` | Import legacy data |
| `list_drawers()` → `List[DrawerInfo]` | List memory categories |
| `count()` → `int` | Total memory count |
| `close()` | Release storage connections |

### `MemoryHit`

| Field | Description |
|-------|-------------|
| `id` | UUID |
| `text` | Memory content |
| `pressure` | Live P_effective at retrieval time |
| `p_raw` | Stored p_magnitude |
| `intent_tags` | Classification tags |
| `coupling_score` | TAS resonance score (0–1) |
| `last_reinforced` | Last retrieval datetime |

---

## 🔬 How PDM Works

**Pressure** — every memory has a p_magnitude (0–100). Important, frequently-used memories stay strong. Unused ones decay. You control the baseline; the system adjusts dynamically.

**Decay** — computed at recall time based on elapsed days vs. domain-specific half-lives. No scheduler required (Celery-free). Market signals decay in 1 day; core facts persist for a year.

**Retrieval (TAS)** — Threshold-Adjustment Search lowers the pressure threshold based on query uncertainty (search_cost). Then coupling scores rank memories by tag overlap, domain, regime, and pressure proximity. The most resonant memories surface first.

**Validation Coefficient (V)** — Laplace-smoothed accuracy tracker. Memories that prove predictively useful grow stronger; ones that mislead decay faster.

---

## 🏗️ Custom Storage Backend

Implement `BaseStorage` to add your own backend (Postgres, Redis, DynamoDB…):

```python
from pdm_memory.storage.base import BaseStorage

class MyPostgresStorage(BaseStorage):
    def save(self, sig): ...
    def save_batch(self, sigs): ...
    def get(self, memory_id, user): ...
    def get_many(self, ids, user): ...
    def update(self, memory_id, **fields): ...
    def update_batch(self, updates, user): ...
    def delete(self, memory_id, user): ...       # soft-delete when supported
    def hard_delete(self, memory_id, user): ...
    def list(self, user, limit, min_pressure, drawer, cursor_id=None, include_deleted=False): ...
    def list_drawers(self, user): ...
    def find_by_idempotency_key(self, key, user): ...
    def find_by_hash(self, text_hash, user): ...
    def ping(self): ...

mem = Memory.__new__(Memory)
mem._storage = MyPostgresStorage(...)
mem._user = "alice"
mem._engine = RetrievalEngine()
```

---

## 📄 License

Free to use **as-shipped** under a custom [Elastic License 2.0 (ELv2)](LICENSE)
base from **Westfield Innovations LLC**.

- Use the SDK as distributed: yes.
- Modify / fork / redistribute altered **core** logic: **no**, without a
  commercial license from Westfield Innovations LLC.
- Extensions via defined plugin interfaces (e.g. `BaseStorage`): **permitted**.

**Patent Pending** — U.S. App. No. **19/739,419** · **63/953,563** · **63/953,842**.

If this software makes you money, send Carl a birthday card. He collects them.

Built by **Westfield Innovations LLC** · [azus.ai](https://azus.ai) · [getdeepsignals.com](https://getdeepsignals.com)
