InfoMesh

Fully Decentralized P2P Search Engine for LLMs
No credit card. No API key. No usage cap. Forever free.

Quick Start • Why InfoMesh • Features • What's New • Architecture • Security • Credits • Contributing • Docs

infomesh peer add /ip4/<IP>/tcp/4001/p2p/<PEER_ID>
infomesh peer test

💡 Why InfoMesh?

The Problem

Every AI assistant needs real-time web access — but that access is gated behind expensive, proprietary search APIs:

This creates a paywall barrier for independent AI developers, open-source assistants, and researchers. Small projects and local LLMs simply cannot afford real-time web search.

The Solution

I started building AI agents and quickly hit a wall: there was no free web search API. Every provider wanted a credit card, a billing account, or a monthly subscription — just to let an AI agent look something up on the web. That felt wrong.

So I built InfoMesh — a decentralized search engine where the community is the infrastructure:

• No central server — every participant is both a crawler and a search node.
• No per-query cost — contribute crawling, earn search credits. The more you give, the more you can search.
• No vendor lock-in — standard MCP protocol integration, works offline with your local index.
• No data harvesting — search queries never leave your node. There is no central entity to collect them.

InfoMesh does not compete with existing commercial search providers. Those companies serve human search at massive scale with ads-based monetization. InfoMesh provides minimal, sufficient search capabilities for AI assistants — for free, via MCP — democratizing real-time web access without per-query billing.

I just wanted my AI agent to search the web without reaching for my wallet. If you've felt the same way, InfoMesh is for you.

🆓 Free. Every Interface. No Exceptions.

No API keys. No billing accounts. No usage caps. No rate limits per dollar. You run a node, you contribute to the network, and search is free — forever.

InfoMesh vs Other Web Search MCP Servers

Looking for a free web search MCP server? Here's how InfoMesh compares to common alternatives:

InfoMesh is the only web search MCP server that is fully decentralized, works offline, requires no API key, and lets you crawl and index your own content — all for free.

🔐 Safe by Design — The Most Secure Search Engine You Can Run

Most search engines ask you to trust them. InfoMesh asks you to trust math.

There is no central server that collects your queries. There is no company that stores your search history. There is no database of user behavior waiting to be breached. Your data never leaves your machine unless you choose to share it.

Contribute to the network → earn credits → search for free, forever, with no limits.

That's the entire deal. No catch.

Why InfoMesh Is Enterprise-Grade Secure

Unified Trust Score

Every peer earns a continuously updated trust score based on behavior, not identity:

Trust = 0.15 × uptime  +  0.25 × contribution  +  0.40 × audit_pass_rate  +  0.20 × summary_quality

Compliance Built In

Bottom line: InfoMesh doesn't ask you to trust a company. It uses cryptography, audits, and game theory to make cheating harder than playing fair. Your queries are private, your data stays local, and your search is free — no strings attached.

🚀 Quick Start

Install & Run (Two Steps — No Git Required)

All you need is a Linux terminal (Ubuntu, Debian, etc.). No prior Python or developer experience required.

Step 1 — Install uv (Python package manager, one-time setup):

curl -LsSf https://astral.sh/uv/install.sh | sh

After this finishes, close and reopen your terminal (or run source ~/.bashrc). This ensures the uv and uvx commands are available.

Step 2 — Run InfoMesh:

uvx infomesh status

uvx automatically downloads and runs InfoMesh — no git clone, no pip install, no virtual environments. On the first run it may take a few seconds to download; subsequent runs are instant.

Try It Out

# Crawl a webpage and index it
uvx infomesh crawl https://docs.python.org/3/library/asyncio.html

# Search your local index
uvx infomesh search "asyncio"

# View the node dashboard (works over SSH too)
uvx infomesh dashboard --text

Install Permanently (Optional)

If you use InfoMesh regularly, install it as a persistent tool so you don't need the uvx prefix:

uv tool install infomesh

# Now run directly:
infomesh status
infomesh crawl https://example.com
infomesh search "example"
infomesh dashboard --text

Connect to Your AI Assistant (MCP)

Add InfoMesh as an MCP server in VS Code (Copilot), Claude Desktop, Cursor, or Windsurf — no API key needed:

{
  "mcpServers": {
    "infomesh": {
      "command": "uvx",
      "args": ["infomesh", "mcp"]
    }
  }
}

Your AI assistant can now search the web for free via MCP.

From Source (Contributors / Developers)

If you want to contribute code or run from source:

System Prerequisites

The P2P optional dependency (libp2p) includes C extensions (fastecdsa, coincurve, pynacl) that require native build tools. These are only needed if you install with pip install 'infomesh[p2p]'.

Linux (Debian / Ubuntu):

sudo apt-get update && sudo apt-get install -y build-essential python3-dev libgmp-dev

macOS:

brew install gmp
# Xcode Command Line Tools are usually pre-installed

Windows: Use WSL2 (recommended) or install Visual Studio Build Tools + GMP.

Note: These system packages are only required for the p2p optional dependency. The base install (uv sync) does not need them.

Clone & Run

# Clone and install with dev dependencies
git clone https://github.com/dotnetpower/infomesh.git
cd infomesh
uv sync

# Start InfoMesh with the TUI dashboard
uv run infomesh start

# Or run headless (servers / CI)
uv run infomesh start --no-dashboard

Docker

docker build -t infomesh .
docker run -d --name infomesh \
  -p 4001:4001 -p 8080:8080 \
  -v infomesh-data:/data \
  infomesh

Verify It Works

# Search your local index
uvx infomesh search "python asyncio tutorial"

# Check node status
uvx infomesh status

# Crawl a specific URL on demand
uvx infomesh crawl https://docs.python.org/3/

# Export your index as a portable snapshot
uvx infomesh index export backup.zst

Examples

Ready-to-run Python scripts are available in the examples/ directory:

# Local search
uv run python examples/basic_search.py "python tutorial"

# Crawl → index → search pipeline
uv run python examples/crawl_and_search.py https://docs.python.org/3/

# Programmatic MCP client
uv run python examples/mcp_client.py "async programming"

See examples/README.md for the full list.

✨ Features

Core Capabilities

MCP Integration — Free Web Search for AI Assistants

Most commercial search APIs charge per query or require a paid subscription. InfoMesh exposes 15 MCP tools completely free — no API key, no billing:

Configure in VS Code / Copilot / Claude Desktop / Cursor

{
  "mcpServers": {
    "infomesh": {
      "command": "uvx",
      "args": ["infomesh", "mcp"]
    }
  }
}

Optional Add-ons

# Vector search with ChromaDB + sentence-transformers
uv sync --extra vector

# Local LLM summarization via Ollama
uv sync --extra llm

� What's New in v0.2.0

v0.2.0 adds 100+ features across search intelligence, RAG support, security, observability, and developer experience. Here are the highlights:

Search Intelligence

RAG & Answer Extraction

Crawler Enhancements

Security & API

Developer Experience

See CHANGELOG.md for the complete list of changes.

�🏗️ Architecture

Tech Stack

Search Flow (Target Latency: ~1 second)

🔒 Security & Trust

InfoMesh is designed with a zero-trust assumption — every peer is potentially adversarial. The system provides multiple layers of defense:

Content Integrity

Network Security

Key Management

• Ed25519 key pairs stored in ~/.infomesh/keys/
• Key rotation: infomesh keys rotate — generates new key pair, publishes dual-signed revocation record to DHT
• Peer identity derived from public key hash (consistent with libp2p PeerId)

Unified Trust Score

Every peer has a continuously updated trust score:

Trust = 0.15 × uptime  +  0.25 × contribution  +  0.40 × audit_pass_rate  +  0.20 × summary_quality

🏢 Enterprise Readiness

InfoMesh is designed for production use, not just experimentation:

Split Deployment (DMZ / Private Network)

Enterprise environments can separate crawlers from indexers across network zones:

┌─────────── DMZ ──────────────┐       ┌──────── Private Network ────────┐
│                              │       │                                 │
│  infomesh --role crawler ──────────────▶  infomesh --role search      │
│  (crawls the public web)     │  P2P  │  (indexes + serves queries)    │
│                              │ auth  │                                 │
│  infomesh --role crawler ──────────────▶  infomesh --role search      │
│                              │       │                                 │
└──────────────────────────────┘       └─────────────────────────────────┘

Three node roles:

Configuration example (~/.infomesh/config.toml):

# DMZ Crawler node
[node]
role = "crawler"
listen_address = "0.0.0.0"

[network]
index_submit_peers = ["/ip4/10.0.0.1/tcp/4001", "/ip4/10.0.0.2/tcp/4001"]

# Private Search/Index node
[node]
role = "search"
listen_address = "10.0.0.1"

[network]
peer_acl = ["QmCrawler1PeerId...", "QmCrawler2PeerId..."]

CLI usage:

# Start as DMZ crawler
infomesh start --role crawler --seeds tech-docs

# Start as private indexer
infomesh start --role search --no-dashboard

Operational

• Resource Governor — CPU, memory, disk I/O, and bandwidth limits with 4 preset profiles (minimal, balanced, contributor, dedicated). Dynamic throttling based on real-time system load
• Pre-flight Checks — Disk space and network connectivity verified before startup
• Load Guard — QPM (queries per minute) + concurrency limiting to prevent node overload
• WAL Mode SQLite — Safe concurrent reads during dashboard refresh without locking crawl writes
• Structured Logging — All library code uses structlog with machine-parseable output
• Docker Support — Production-ready Dockerfile with volume mounts for persistent data

Configurable

• TOML Configuration (~/.infomesh/config.toml) with environment variable overrides (INFOMESH_CRAWL_MAX_CONCURRENT=20)
• Value Validation — All config values clamped to safe ranges with structured warnings
• Dashboard Settings — All configuration editable via the TUI Settings tab (no file editing required)
• Energy-aware Scheduling — LLM-heavy tasks preferentially scheduled during configured off-peak hours (1.5× credit multiplier)

Compliance

• robots.txt strictly enforced — respects all crawl directives
• DMCA Takedown — Signed takedown requests propagated via DHT; nodes comply within 24 hours
• GDPR — Distributed deletion records for personal data; right-to-be-forgotten support
• Content Attribution — AI-generated summaries labeled with content_hash + source URL
• Paywall Detection — fetch_page() detects and respects paywalled content
• Terms of Use — Clear TERMS_OF_USE.md covering crawler behavior and data handling

Scale

• Designed for thousands of nodes with Kademlia DHT routing
• 3-layer deduplication prevents index bloat (URL normalization → SHA-256 exact → SimHash near-duplicate)
• zstd-compressed snapshots for efficient index sharing between nodes
• Common Crawl data import for bootstrapping large indexes

💰 Earning Credits

Credits are the incentive mechanism that keeps the network healthy. They are tracked locally per node — no blockchain, no central ledger.

How Credits Work

Credits Earned = Σ (Weight × Quantity × TimeMultiplier)

Earning Actions

Time Multiplier

• Base actions: Always 1.0×
• LLM actions during off-peak hours (configurable, default 23:00–07:00): 1.5×
• Off-peak scheduling is energy-conscious — the network preferentially routes batch LLM work to nodes currently in off-peak

Search Cost

Fairness Guarantees

• Non-LLM nodes are never starved: A node doing only crawling at 10 pages/hr earns 100 searches/hr at worst tier
• LLM earnings capped: LLM-related credits never exceed ~60% of total — LLM is a network bonus, not a participation requirement
• Uptime rewards: 0.5 credits/hr just for keeping your node online, regardless of hardware
• Search is never blocked: Even with zero credits, you can still search — see Zero-Dollar Debt below

💳 Zero-Dollar Debt — No Credit Card, No Real Money

What happens when your credits run out? You keep searching.

InfoMesh doesn't cut you off. There's no paywall, no "please enter your credit card," no upgrade button. Instead, there's a simple, human-friendly recovery path:

Credits ran out
     │
     ▼
┌─────────────────────────────────────┐
│  🟢 Grace Period (72 hours)         │
│  Search works normally.             │
│  Balance goes negative — no penalty.│
└──────────────┬──────────────────────┘
               │ 72h passed, still negative?
               ▼
┌─────────────────────────────────────┐
│  🟡 Debt Mode                       │
│  Search continues at 2× cost.      │
│  Debt accumulates.                  │
└──────────────┬──────────────────────┘
               │ Earn credits → balance > 0
               ▼
┌─────────────────────────────────────┐
│  🟢 Back to Normal                  │
│  Debt cleared. Grace reset.         │
│  Full speed ahead.                  │
└─────────────────────────────────────┘

The key principle: Debt in InfoMesh is measured in credits, not money. You recover by contributing, not by paying. Run your node, crawl some pages, keep the network alive — and your debt disappears naturally.

No credit card. No dollars. No subscription. No "trial expired" popup. Just run your node, and you're back.

🤝 Contributing

We welcome contributions of all kinds — code, documentation, bug reports, feature ideas, and seed URL lists.

Getting Started

# Clone and install
git clone https://github.com/dotnetpower/infomesh.git
cd infomesh
uv sync --dev

# Run the test suite (1,307 tests)
uv run pytest

# Run linter + formatter
uv run ruff check infomesh/ tests/
uv run ruff format .

# Run type checker
uv run mypy infomesh/

Ways to Contribute

Code Style

• Formatter: ruff format (black-compatible, 88 char lines)
• Linter: ruff with E, F, I, UP, B, SIM rules
• Type hints: Required on all public functions
• Docstrings: Required on all public classes and functions
• Tests: Every PR should include tests for new functionality
• No print() in library code — use structlog

Pull Request Workflow

1. Fork the repository
2. Create a feature branch: git checkout -b feat/my-feature
3. Write code + tests
4. Run uv run pytest && uv run ruff check .
5. Submit a PR — you earn 1,000 – 100,000 credits per merged PR!

See CONTRIBUTING.md for the full guide.

📖 Documentation

Detailed documentation is available in the docs/ directory:

📌 Documentation is also available in Korean (한국어).

📊 Project Stats

🗺️ Roadmap

All core phases are complete. Current focus is on community growth and production hardening.

What's Next

• 🌍 Public bootstrap nodes — community-maintained seed nodes across multiple Azure regions

  ✅ Active: Bootstrap nodes are live in US East and US East 2. Your node connects automatically via bootstrap/nodes.json. No manual configuration needed.

• 🎭 JS rendering — Playwright-based SPA crawling for JS-heavy sites
• 📱 Web dashboard — optional browser UI alongside the TUI
• 🔍 Semantic search fusion — BM25 + vector hybrid ranking with RRF
• 🌐 Multi-language stemming — language-specific tokenization and stemming

⚖️ Legal

• robots.txt: Strictly enforced. Sites that prohibit crawling are never crawled.
• Copyright: Full text stored as cache only; search results return snippets with source attribution.
• DMCA: Signed takedown requests propagated via DHT. All nodes must comply within 24 hours.
• GDPR: Distributed deletion records. Nodes can exclude pages with personal data.
• AI Summaries: Labeled as AI-generated, linked to source via content_hash, original URL always provided.
• Terms of Use: See TERMS_OF_USE.md for full terms.

🙏 Acknowledgements

InfoMesh stands on the shoulders of excellent open-source projects:

httpx • trafilatura • libp2p • SQLite • ChromaDB • Textual • FastAPI • mcp-python-sdk • uv • structlog • zstandard

MIT License — Copyright 2026 InfoMesh Contributors

If you find InfoMesh useful, consider ⭐ starring the repo — it helps others discover the project.