> For the complete documentation index, see [llms.txt](https://browsr-documentation.gitbook.io/browsr-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://browsr-documentation.gitbook.io/browsr-documentation/introducing-browsr..md).

# Introducing Browsr.

**Browsr** is a multimodal, agentic LLM interface architected for frictionless interaction with structured and unstructured blockchain data across EVM chains and L1s. \
\
Leveraging NLP, Semantic Search, and Machine Code Parsing (MCP), it enables autonomous access to on-chain state, ABI surfaces, runtime traces, and exfiltrated off-chain signals (e.g., breached credentials, CVEs).

<figure><img src="/files/uvchfUx3UWfSrIrFsUKP" alt=""><figcaption><p><strong>Watch autonomous agents work their magic using Browsr.</strong></p></figcaption></figure>

The protocol leverages real-time ML inference and smart contract introspection to offer a unified search substrate—capable of converting smart contract metadata, event logs, and low-level hex traces into semantically-relevant, query able representations for trading, security, and monitoring.\
\
**Website:** browsr.ai/