> ## Documentation Index
> Fetch the complete documentation index at: https://docs.provenlog.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Tamper-evident audit trails for AI agents

ProvenLog captures every AI agent action into a **hash-chained audit trail** — like a blockchain for your agent's behavior. Each event is cryptographically linked to the previous one, making tampering detectable and providing a verifiable record of everything your agent did.

## Why ProvenLog

AI agents call tools, write files, send messages, and make decisions autonomously. When something goes wrong, you need an answer: **what did the agent do, and can you prove it?**

* **Hash chain integrity** — SHA-256 linked events, tamper-evident by design
* **Merkle tree verification** — global integrity proof across all agent chains
* **Verifiable exports** — portable `.plog` evidence packages auditors can verify offline
* **RFC 3161 timestamping** — third-party proof that records existed at a given time
* **PII/PHI redaction** — 17 built-in patterns for emails, SSNs, API keys, credit cards
* **Framework-native** — drop-in integrations for LangChain, CrewAI, OpenAI, Anthropic, AG2, LangGraph
* **Zero-code options** — MCP proxy, OTLP receiver, Claude Code hooks
* **Embedded or server** — local SQLite with no setup, or a server for multi-agent visibility

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get up and running in under 3 minutes with zero code changes.
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install the CLI, Python SDK, or TypeScript SDK.
  </Card>

  <Card title="Python SDK" icon="python" href="/sdks/python">
    Explicit instrumentation with the Python client.
  </Card>

  <Card title="TypeScript SDK" icon="js" href="/sdks/typescript">
    Instrument your TypeScript agents.
  </Card>
</CardGroup>

## Core concepts

<CardGroup cols={2}>
  <Card title="Events" icon="list" href="/concepts/events">
    Understand the ProvenLogEvent schema and action types.
  </Card>

  <Card title="Hash Chains" icon="link" href="/concepts/hash-chains">
    How SHA-256 hash chains provide tamper evidence.
  </Card>

  <Card title="Merkle Trees" icon="sitemap" href="/concepts/merkle-trees">
    Global integrity proofs across all agent chains.
  </Card>

  <Card title="Operating Modes" icon="toggle-on" href="/concepts/operating-modes">
    Embedded (local SQLite) vs Server mode.
  </Card>
</CardGroup>

## Architecture

```
+-------------------------------------------------------------+
|                        Capture Layer                         |
|  plog run  .  provenlog.auto  .  Python SDK  .  TS SDK      |
|  MCP Proxy  .  OTLP  .  Claude Code Hook  .  OpenClaw       |
+-----------------------------+-------------------------------+
                              |
                       +------v------+
                       |   Pipeline   |
                       |  Validate    |
                       |  Redact PII  |
                       |  Hash Chain  |
                       |  Merkle Tree |
                       +------+------+
                              |
                       +------v------+
                       |   Storage    |
                       |   SQLite     |
                       +------+------+
                              |
                 +------------+------------+
                 |            |            |
           +-----v----+ +----v-----+ +----v----+
           |  REST API | |Dashboard | |   CLI   |
           |  /v1/*    | |  React   | |  plog   |
           +----------+ +----------+ +---------+
```