sirchmunk 0.0.3

Sirchmunk: From raw data to self-evolving real-time intelligence.

Sirchmunk: Raw data to self-evolving intelligence, real-time.

Quick Start · Key Features · MCP Server · Web UI · How it Works · FAQ

🇨🇳 中文

🔍 Agentic Search  •  🧠 Knowledge Clustering  •  📊 Monte Carlo Evidence Sampling
⚡ Indexless Retrieval  •  🔄 Self-Evolving Knowledge Base  •  💬 Real-time Chat

---

🌰 Why “Sirchmunk”？

Intelligence pipelines built upon vector-based retrieval can be rigid and brittle. They rely on static vector embeddings that are expensive to compute, blind to real-time changes, and detached from the raw context. We introduce Sirchmunk to usher in a more agile paradigm, where data is no longer treated as a snapshot, and insights can evolve together with the data.

---

✨ Key Features

1. Embedding-Free: Data in its Purest Form

Sirchmunk works directly with raw data -- bypassing the heavy overhead of squeezing your rich files into fixed-dimensional vectors.

• Instant Search: Eliminating complex pre-processing pipelines in hours long indexing; just drop your files and search immediately.
• Full Fidelity: Zero information loss —- stay true to your data without vector approximation.

2. Self-Evolving: A Living Index

Data is a stream, not a snapshot. Sirchmunk is dynamic by design, while vector DB can become obsolete the moment your data changes.

• Context-Aware: Evolves in real-time with your data context.
• LLM-Powered Autonomy: Designed for Agents that perceive data as it lives, utilizing token-efficient reasoning that triggers LLM inference only when necessary to maximize intelligence while minimizing cost.

3. Intelligence at Scale: Real-Time & Massive

Sirchmunk bridges massive local repositories and the web with high-scale throughput and real-time awareness.
It serves as a unified intelligent hub for AI agents, delivering deep insights across vast datasets at the speed of thought.

---

Traditional RAG vs. Sirchmunk

Dimension	Traditional RAG	✨Sirchmunk
💰 Setup Cost	High Overhead (VectorDB, GraphDB, Complex Document Parser...)	✅ Zero Infrastructure Direct-to-data retrieval without vector silos
🕒 Data Freshness	Stale (Batch Re-indexing)	✅ Instant & Dynamic Self-evolving index that reflects live changes
📈 Scalability	Linear Cost Growth	✅ Extremely low RAM/CPU consumption Native Elastic Support, efficiently handles large-scale datasets
🎯 Accuracy	Approximate Vector Matches	✅ Deterministic & Contextual Hybrid logic ensuring semantic precision
⚙️ Workflow	Complex ETL Pipelines	✅ Drop-and-Search Zero-config integration for rapid deployment

---

Demonstration

Access files directly to start chatting

---

🎉 News

• 🚀 Feb 5, 2026: Release v0.0.2 — MCP Support, CLI Commands & Knowledge Persistence!

  • MCP Integration: Full Model Context Protocol support, works seamlessly with Claude Desktop and Cursor IDE.
  • CLI Commands: New sirchmunk CLI with init, serve, search, web, and mcp commands.
  • KnowledgeCluster Persistence: DuckDB-powered storage with Parquet export for efficient knowledge management.
  • Knowledge Reuse: Semantic similarity-based cluster retrieval for faster searches via embedding vectors.

• 🎉🎉 Jan 22, 2026: Introducing Sirchmunk: Initial Release v0.0.1 Now Available!

---

🚀 Quick Start

Prerequisites

• Python 3.10+
• LLM API Key (OpenAI-compatible endpoint, local or remote)
• Node.js 18+ (Optional, for web interface)

Installation

# Create virtual environment (recommended)
conda create -n sirchmunk python=3.13 -y && conda activate sirchmunk 

pip install sirchmunk

# Or via UV:
uv pip install sirchmunk

# Alternatively, install from source:
git clone https://github.com/modelscope/sirchmunk.git && cd sirchmunk
pip install -e .

Python SDK Usage

import asyncio

from sirchmunk import AgenticSearch
from sirchmunk.llm import OpenAIChat

llm = OpenAIChat(
        api_key="your-api-key",
        base_url="your-base-url",   # e.g., https://api.openai.com/v1
        model="your-model-name"     # e.g., gpt-4o
    )

async def main():
    
    searcher = AgenticSearch(llm=llm)
    
    result: str = await searcher.search(
        query="How does transformer attention work?",
        paths=["/path/to/documents"],
    )
    
    print(result)

asyncio.run(main())

⚠️ Notes:

• Upon initialization, AgenticSearch automatically checks if ripgrep-all and ripgrep are installed. If they are missing, it will attempt to install them automatically. If the automatic installation fails, please install them manually.
  • References: https://github.com/BurntSushi/ripgrep | https://github.com/phiresky/ripgrep-all
• Replace "your-api-key", "your-base-url", "your-model-name" and /path/to/documents with your actual values.

Command Line Interface

Sirchmunk provides a powerful CLI for server management and search operations.

Installation

pip install "sirchmunk[web]"

# or install via UV
uv pip install "sirchmunk[web]"

Initialize

# Initialize Sirchmunk with default settings (Default work path: `~/.sirchmunk/`)
sirchmunk init

# Alternatively, initialize with custom work path
sirchmunk init --work-path /path/to/workspace

Start Server

# Start backend API server only
sirchmunk serve

# Custom host and port
sirchmunk serve --host 0.0.0.0 --port 8000

Search

# Search in current directory
sirchmunk search "How does authentication work?"

# Search in specific paths
sirchmunk search "find all API endpoints" ./src ./docs

# Quick filename search
sirchmunk search "config" --mode FILENAME_ONLY

# Output as JSON
sirchmunk search "database schema" --output json

# Use API server (requires running server)
sirchmunk search "query" --api --api-url http://localhost:8584

Available Commands

Command	Description
sirchmunk init	Initialize working directory, .env, and MCP config
sirchmunk serve	Start the backend API server
sirchmunk search	Perform search queries
sirchmunk web init	Build WebUI frontend (requires Node.js 18+)
sirchmunk web serve	Start API + WebUI (single port)
sirchmunk web serve --dev	Start API + Next.js dev server (hot-reload)
sirchmunk mcp serve	Start the MCP server (stdio/HTTP)
sirchmunk mcp version	Show MCP version information
sirchmunk version	Show version information

---

🔌 MCP Server

Sirchmunk provides a Model Context Protocol (MCP) server that exposes its intelligent search capabilities as MCP tools. This enables seamless integration with AI assistants like Claude Desktop and Cursor IDE.

Quick Start

# Install with MCP support
pip install sirchmunk[mcp]

# Initialize (generates .env and mcp_config.json)
sirchmunk init

# Edit ~/.sirchmunk/.env with your LLM API key

# Test with MCP Inspector
npx @modelcontextprotocol/inspector sirchmunk mcp serve

mcp_config.json Configuration

After running sirchmunk init, a ~/.sirchmunk/mcp_config.json file is generated. Copy it to your MCP client configuration directory.

Example:

{
  "mcpServers": {
    "sirchmunk": {
      "command": "sirchmunk",
      "args": ["mcp", "serve"],
      "env": {
        "SIRCHMUNK_SEARCH_PATHS": "/path/to/your_docs,/another/path"
      }
    }
  }
}

Parameter	Description
command	The command to start the MCP server. Use full path (e.g. /path/to/venv/bin/sirchmunk) if running in a virtual environment.
args	Command arguments. ["mcp", "serve"] starts the MCP server in stdio mode.
env.SIRCHMUNK_SEARCH_PATHS	Default document search directories (comma-separated). Supports both English , and Chinese ， as delimiters. When set, these paths are used as default if no paths parameter is provided during tool invocation.

Tip: MCP Inspector is a great way to test the integration before connecting to your AI assistant. In MCP Inspector: Connect → Tools → List Tools → sirchmunk_search → Input parameters (query and paths, e.g. ["/path/to/your_docs"]) → Run Tool.

Features

• Multi-Mode Search: DEEP mode for comprehensive analysis, FILENAME_ONLY for fast file discovery
• Knowledge Cluster Management: Automatic extraction, storage, and reuse of knowledge
• Standard MCP Protocol: Works with stdio and Streamable HTTP transports

📖 For detailed documentation, see Sirchmunk MCP README.

---

🖥️ Web UI

The web UI is built for fast, transparent workflows: chat, knowledge analytics, and system monitoring in one place.

_{Home — Chat with streaming logs, file-based RAG, and session management.}

_{Monitor — System health, chat activity, knowledge analytics, and LLM usage.}

Option 1: Single-Port Mode (Recommended)

Build the frontend once, then serve everything from a single port — no Node.js needed at runtime.

# Build WebUI frontend (requires Node.js 18+ at build time)
sirchmunk web init

# Start server with embedded WebUI
sirchmunk web serve

Access: http://localhost:8584 (API + WebUI on the same port)

Option 2: Development Mode

For frontend development with hot-reload:

# Start backend + Next.js dev server
sirchmunk web serve --dev

Access:

• Frontend (hot-reload): http://localhost:8585
• Backend APIs: http://localhost:8584/docs

Option 3: Legacy Script

# Start frontend and backend via script
python scripts/start_web.py 

# Stop all services
python scripts/stop_web.py

Configuration:

• Access Settings → Envrionment Variables to configure LLM API, and other parameters.

---

🏗️ How it Works

Sirchmunk Framework

Core Components

Component	Description
AgenticSearch	Search orchestrator with LLM-enhanced retrieval capabilities
KnowledgeBase	Transforms raw results into structured knowledge clusters with evidences
EvidenceProcessor	Evidence processing based on the MonteCarlo Importance Sampling
GrepRetriever	High-performance indexless file search with parallel processing
OpenAIChat	Unified LLM interface supporting streaming and usage tracking
MonitorTracker	Real-time system and application metrics collection

Monte Carlo Evidence Sampling

Traditional retrieval systems read entire documents or rely on fixed-size chunks, leading to either wasted tokens or lost context. Sirchmunk takes a fundamentally different approach inspired by Monte Carlo methods — treating evidence extraction as a sampling problem rather than a parsing problem.

_{Monte Carlo Evidence Sampling — A three-phase exploration-exploitation strategy for extracting relevant evidence from large documents.}

The algorithm operates in three phases:

1. Phase 1 — Cast the Net (Exploration): Fuzzy anchor matching combined with stratified random sampling. The system identifies seed regions of potential relevance while maintaining broad coverage through randomized probing — ensuring no high-value region is missed.

2. Phase 2 — Focus (Exploitation): Gaussian importance sampling centered around high-scoring seeds from Phase 1. The sampling density concentrates on the most promising regions, extracting surrounding context and scoring each snippet for relevance.

3. Phase 3 — Synthesize: The top-K scored snippets are passed to the LLM, which synthesizes them into a coherent Region of Interest (ROI) summary with a confidence flag — enabling the pipeline to decide whether evidence is sufficient or a ReAct agent should be invoked for deeper exploration.

Key properties:

• Document-agnostic: The same algorithm works equally well on a 2-page memo and a 500-page technical manual — no document-specific chunking heuristics needed.
• Token-efficient: Only the most relevant regions are sent to the LLM, dramatically reducing token consumption compared to full-document approaches.
• Exploration-exploitation balance: Random exploration prevents tunnel vision, while importance sampling ensures depth where it matters most.

Self-Evolving Knowledge Clusters

Sirchmunk does not discard search results after answering a query. Instead, every search produces a KnowledgeCluster — a structured, reusable knowledge unit that grows smarter over time. This is what makes the system self-evolving.

What is a KnowledgeCluster?

A KnowledgeCluster is a richly annotated object that captures the full cognitive output of a single search cycle:

Field	Purpose
Evidences	Source-linked snippets extracted via Monte Carlo sampling, each with file path, summary, and raw text
Content	LLM-synthesized markdown with structured analysis and references
Patterns	3–5 distilled design principles or mechanisms identified from the evidence
Confidence	A consensus score [0, 1] indicating the reliability of the cluster
Queries	Historical queries that contributed to or reused this cluster (FIFO, max 5)
Hotness	Activity score reflecting query frequency and recency
Embedding	384-dim vector derived from accumulated queries, enabling semantic retrieval

Lifecycle: From Creation to Evolution

 ┌─────── New Query ───────┐
 │                          ▼
 │     ┌──────────────────────────────┐
 │     │  Phase 0: Semantic Reuse     │──── Match found ──→ Return cached cluster
 │     │  (cosine similarity ≥ 0.85)  │                     + update hotness/queries/embedding
 │     └──────────┬───────────────────┘
 │           No match
 │                ▼
 │     ┌──────────────────────────────┐
 │     │  Phase 1–3: Full Search      │
 │     │  (keywords → retrieval →     │
 │     │   Monte Carlo → LLM synth)   │
 │     └──────────┬───────────────────┘
 │                ▼
 │     ┌──────────────────────────────┐
 │     │  Build New Cluster           │
 │     │  Deterministic ID: C{sha256} │
 │     └──────────┬───────────────────┘
 │                ▼
 │     ┌──────────────────────────────┐
 │     │  Phase 5: Persist            │
 │     │  Embed queries → DuckDB →    │
 │     │  Parquet (atomic sync)       │
 └─────└──────────────────────────────┘

1. Reuse Check (Phase 0): Before any retrieval, the query is embedded and compared against all stored clusters via cosine similarity. If a high-confidence match is found, the existing cluster is returned instantly — saving LLM tokens and search time entirely.

2. Creation (Phase 1–3): When no reuse match is found, the full pipeline runs: keyword extraction, file retrieval, Monte Carlo evidence sampling, and LLM synthesis produce a new KnowledgeCluster.

3. Persistence (Phase 5): The cluster is stored in an in-memory DuckDB table and periodically flushed to Parquet files. Atomic writes and mtime-based reload ensure multi-process safety.

4. Evolution on Reuse: Each time a cluster is reused, the system:

   • Appends the new query to the cluster's query history (FIFO, max 5)
   • Increases hotness (+0.1, capped at 1.0)
   • Recomputes the embedding from the updated query set — broadening the cluster's semantic catchment area
   • Updates version and timestamp

Key Properties

• Zero-cost acceleration: Repeated or semantically similar queries are answered from cached clusters without any LLM inference, making subsequent searches near-instantaneous.
• Query-driven embeddings: Cluster embeddings are derived from queries rather than content, ensuring that retrieval aligns with how users actually ask questions — not how documents are written.
• Semantic broadening: As diverse queries reuse the same cluster, its embedding drifts to cover a wider semantic neighborhood, naturally improving recall for related future queries.
• Lightweight persistence: DuckDB in-memory + Parquet on disk — no external database infrastructure required. Background daemon sync with configurable flush intervals keeps overhead minimal.

---

Data Storage

All persistent data is stored in the configured SIRCHMUNK_WORK_PATH (default: ~/.sirchmunk/):

{SIRCHMUNK_WORK_PATH}/
  ├── .cache/
    ├── history/              # Chat session history (DuckDB)
    │   └── chat_history.db
    ├── knowledge/            # Knowledge clusters (Parquet)
    │   └── knowledge_clusters.parquet
    └── settings/             # User settings (DuckDB)
        └── settings.db

---

🔗 HTTP Client Access (Search API)

When the server is running (sirchmunk serve or sirchmunk web serve), the Search API is accessible via any HTTP client.

API Endpoints

Method	Endpoint	Description
POST	/api/v1/search	Execute a search query
GET	/api/v1/search/status	Check server and LLM configuration status

Interactive Docs: http://localhost:8584/docs (Swagger UI)

cURL Examples

# Basic search (DEEP mode)
curl -X POST http://localhost:8584/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "How does authentication work?",
    "paths": ["/path/to/project"],
    "mode": "DEEP"
  }'

# Filename search (fast, no LLM required)
curl -X POST http://localhost:8584/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "config",
    "paths": ["/path/to/project"],
    "mode": "FILENAME_ONLY"
  }'

# Full parameters
curl -X POST http://localhost:8584/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "database connection pooling",
    "paths": ["/path/to/project/src"],
    "mode": "DEEP",
    "max_depth": 10,
    "top_k_files": 20,
    "keyword_levels": 3,
    "include_patterns": ["*.py", "*.java"],
    "exclude_patterns": ["*test*", "*__pycache__*"],
    "return_cluster": true
  }'

# Check server status
curl http://localhost:8584/api/v1/search/status

Python Client Examples

Using requests:

import requests

response = requests.post(
    "http://localhost:8584/api/v1/search",
    json={
        "query": "How does authentication work?",
        "paths": ["/path/to/project"],
        "mode": "DEEP"
    },
    timeout=300  # DEEP mode may take a while
)

data = response.json()
if data["success"]:
    print(data["data"]["result"])

Using httpx (async):

import httpx
import asyncio

async def search():
    async with httpx.AsyncClient(timeout=300) as client:
        resp = await client.post(
            "http://localhost:8584/api/v1/search",
            json={
                "query": "find all API endpoints",
                "paths": ["/path/to/project"],
                "mode": "DEEP"
            }
        )
        data = resp.json()
        print(data["data"]["result"])

asyncio.run(search())

JavaScript Client Example

const response = await fetch("http://localhost:8584/api/v1/search", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    query: "How does authentication work?",
    paths: ["/path/to/project"],
    mode: "DEEP"
  })
});

const data = await response.json();
if (data.success) {
  console.log(data.data.result);
}

Request Parameters

Parameter	Type	Default	Description
query	string	required	Search query or question
paths	string[]	required	Directories or files to search (min 1)
mode	string	"DEEP"	DEEP or FILENAME_ONLY
max_depth	int	null	Maximum directory depth
top_k_files	int	null	Number of top files to return
keyword_levels	int	null	Keyword granularity levels
include_patterns	string[]	null	File glob patterns to include
exclude_patterns	string[]	null	File glob patterns to exclude
return_cluster	bool	false	Return full KnowledgeCluster object

Note: FILENAME_ONLY mode does not require an LLM API key. DEEP mode requires a configured LLM.

---

❓ FAQ

How is this different from traditional RAG systems?

Sirchmunk takes an indexless approach:

1. No pre-indexing: Direct file search without vector database setup
2. Self-evolving: Knowledge clusters evolve based on search patterns
3. Multi-level retrieval: Adaptive keyword granularity for better recall
4. Evidence-based: Monte Carlo sampling for precise content extraction

What LLM providers are supported?

Any OpenAI-compatible API endpoint, including (but not limited too):

• OpenAI (GPT-4, GPT-4o, GPT-3.5)
• Local models served via Ollama, llama.cpp, vLLM, SGLang etc.
• Claude via API proxy

How do I add documents to search?

Simply specify the path in your search query:

result = await searcher.search(
    query="Your question",
    paths=["/path/to/folder", "/path/to/file.pdf"]
)

No pre-processing or indexing required!

Where are knowledge clusters stored?

Knowledge clusters are persisted in Parquet format at:

{SIRCHMUNK_WORK_PATH}/.cache/knowledge/knowledge_clusters.parquet

You can query them using DuckDB or the KnowledgeManager API.

How do I monitor LLM token usage?

1. Web Dashboard: Visit the Monitor page for real-time statistics
2. API: GET /api/v1/monitor/llm returns usage metrics
3. Code: Access searcher.llm_usages after search completion

---

📋 Roadmap

• Text-retrieval from raw files
• Knowledge structuring & persistence
• Real-time chat with RAG
• Web UI support
• Web search integration
• Multi-modal support (images, videos)
• Distributed search across nodes
• Knowledge visualization and deep analytics
• More file type support

---

🤝 Contributing

We welcome contributions !

---

📄 License

This project is licensed under the Apache License 2.0.

---

ModelScope · ⭐ Star us · 🐛 Report a bug · 💬 Discussions

✨ Sirchmunk: Raw data to self-evolving intelligence, real-time.

❤️ Thanks for Visiting ✨ Sirchmunk !