100+

File formats
searched instantly

Zero

Pre-indexing
required

6

Integration surfaces
SKILL · MCP · REST · WS · CLI · Web

Key Features

An agentic search engine that goes beyond traditional RAG — embedding-free, self-evolving, and token-efficient.

Embedding-Free Retrieval

Work directly with raw data — no vector database, no pre-indexing, no ETL pipeline. Drop your files and search immediately with full source fidelity.

Self-Evolving Knowledge

Every search produces a reusable KnowledgeCluster. Clusters merge, broaden, and form meta-communities over time — the system literally gets smarter as you use it.

LENS: Latent Evidence Exploration

Budgeted evidence localization over a query-conditioned latent evidence space. The LENS framework locates source-grounded evidence from raw dynamic documents under explicit cost constraints.

Multi-Path DEEP Retrieval

Parallel lexical, entity, directory, structural, and topic-graph retrieval routes fused by confidence-weighted RRF — with soft route-collapse for high-confidence single-file lookups.

Large Corpus Robustness

Bounded per-file and per-query retrieval cost: tiered rg-first scan, adapter whitelist, file-size cap, per-file match limits, and hard token budgets keep huge corpora fast.

Multi-Surface Integration

MCP protocol, OpenClaw skill, REST API, WebSocket real-time chat, CLI, and a modern Web UI with knowledge graph visualization — all built in.

Start Searching with Sirchmunk

Drop your files and search instantly — no vector database, no pre-indexing, no complex setup. Get self-evolving intelligence from your raw data in real time.
Quick Start Guide