Aura Openclaw

# Aura for OpenClaw

Persistent memory and instant knowledge retrieval for your OpenClaw agent. Compile 60+ file formats into queryable `.aura` archives and give your agent a 3-tier memory that survives sessions, compaction, and restarts.

> **Memory OS v2.1** (`auralith-aura>=0.2.2`): Enhanced with temporal decay scoring, noise filtering, deduplication, bloom filters, SimHash fuzzy matching, and tiered priority scoring — zero RAM overhead.

## Setup

```bash
pip install auralith-aura
```

For full document support (PDFs, DOCX, etc.):
```bash
pip install 'aura-core[all]'
```

## What It Looks Like

### Learn an entire codebase

```
You: Learn my project in ~/repos/api-service
Agent: 🔥 Compiling ~/repos/api-service...
       ✅ Compiled 847 files → api-service.aura
       Indexed: Python (312), TypeScript (201), YAML (44), Markdown (73), JSON (217)

You: How does the auth middleware handle token refresh?
Agent: Based on src/middleware/auth.ts (lines 45-89), the auth middleware
       intercepts expired JWTs by checking the `exp` claim. When expired,
       it calls `refreshTokenService.rotate()` which issues a new access
       token and sets it via the `X-Refreshed-Token` response header.
       The original request is then replayed with the new token.
```

### Compile legal docs with PII masking

```
You: Learn everything in ~/legal but mask any personal info
Agent: 🔥 Compiling with PII masking enabled...
       ✅ Compiled → legal.aura
       Masked: 23 emails, 8 phone numbers, 4 SSNs

You: What are the termination conditions in the Series A agreement?
Agent: Per series_a_term_sheet.pdf, Section 7.2 — the agreement may be
       terminated by either party with 30 days written notice if:
       (a) material breach remains uncured after 15 business days,
       (b) insolvency or bankruptcy filing, or
       (c) failure to meet the minimum revenue threshold in Schedule B...
```

### Remember facts across sessions...

<p align="center">
  <img src="https://raw.githubusercontent.com/Auralith-Inc/aura-core/main/logo.png" alt="Aura" width="100">
</p>

# 🔥 Aura for OpenClaw

**Persistent memory and instant knowledge retrieval for your OpenClaw agent.**

<p align="center">
  <a href="https://pypi.org/project/auralith-aura/"><img src="https://badge.fury.io/py/auralith-aura.svg" alt="PyPI"></a>
  <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License: Apache 2.0"></a>
</p>

---

## Why Aura?

OpenClaw agents are powerful, but memory is hard. Context compaction can silently drop facts. MEMORY.md doesn't scale. Sessions start fresh.

**Aura gives your agent a real memory system:**

- ✅ **Memories persist across sessions** — facts, preferences, and decisions survive restarts
- ✅ **No context window pollution** — memory lives outside the prompt, retrieved on demand
- ✅ **Scales to thousands of documents** — compiled into indexed `.aura` archives, not flat markdown
- ✅ **Instant writes, zero blocking** — sub-millisecond write-ahead log means your agent is never waiting
- ✅ **Compile any file format** — PDFs, DOCX, code, spreadsheets, emails — 60+ formats into one queryable archive

All processing happens **locally on your machine**. Your data stays on your hardware.

---

## 3-Tier Memory OS

Aura organizes agent memory into three purpose-built tiers:

| Tier | What It Stores | Lifecycle |
|------|---------------|-----------|
| **`/pad`** | Working notes, scratch space, in-progress thinking | Transient — cleared between sessions |
| **`/episodic`** | Session transcripts, conversation history, decisions made | Auto-archived — retained for reference |
| **`/fact`** | Verified facts, user preferences, learned rules | Persistent — survives indefinitely |

> **Memory OS v2.1** (`auralith-aura>=0.2.2`): Enhanced with temporal decay scoring, noise filtering, deduplication, b...