v0.4.0 — Open Source (MIT)
Structuredknowledge,
nottextsoup.

Feed it a question. Get back scored claims,entity graphs, and asynthesized report — using your own LLM.

Research ▋

$pip install behive
View on GitHub
behive research "NVIDIA GPU market 2026" --scale 30
BeHive CLI Demo — animated terminal showing research pipeline with bee flight physics, honeycomb progress bars, and knowledge graph output
0

API Sources

0K

Claims Extracted

0.0

Avg Quality

0K

Entities Mapped

⬡ MCP Native⬡ 64 APIs⬡ Knowledge Graph⬡ Quality Scoring⬡ Self-Hosted⬡ MIT License⬡ SSE Streaming⬡ BYOK LLM⬡ PostgreSQL⬡ Docker Compose⬡ 53K Claims⬡ 127K Entities⬡ MCP Native⬡ 64 APIs⬡ Knowledge Graph⬡ Quality Scoring⬡ Self-Hosted⬡ MIT License⬡ SSE Streaming⬡ BYOK LLM⬡ PostgreSQL⬡ Docker Compose⬡ 53K Claims⬡ 127K Entities⬡ MCP Native⬡ 64 APIs⬡ Knowledge Graph⬡ Quality Scoring⬡ Self-Hosted⬡ MIT License⬡ SSE Streaming⬡ BYOK LLM⬡ PostgreSQL⬡ Docker Compose⬡ 53K Claims⬡ 127K Entities
⬢ MCP Native⬢ 64 APIs⬢ Knowledge Graph⬢ Quality Scoring⬢ Self-Hosted⬢ MIT License⬢ SSE Streaming⬢ BYOK LLM⬢ PostgreSQL⬢ Docker Compose⬢ 53K Claims⬢ 127K Entities⬢ MCP Native⬢ 64 APIs⬢ Knowledge Graph⬢ Quality Scoring⬢ Self-Hosted⬢ MIT License⬢ SSE Streaming⬢ BYOK LLM⬢ PostgreSQL⬢ Docker Compose⬢ 53K Claims⬢ 127K Entities⬢ MCP Native⬢ 64 APIs⬢ Knowledge Graph⬢ Quality Scoring⬢ Self-Hosted⬢ MIT License⬢ SSE Streaming⬢ BYOK LLM⬢ PostgreSQL⬢ Docker Compose⬢ 53K Claims⬢ 127K Entities

The Problem

You ask AI to research a topic.
It gives you confident-soundingtext soup.

✗

Without BeHive

"Based on my training data, NVIDIA's GPU market shows promising growth with several key factors driving demand..."

No sourcesNo structureStale data
✓

With BeHive

[0.94] NVIDIA H200 production at 500K units/month as of Q2 2026

[0.91] Data center GPU revenue $35.1B in FY2026 Q2, 87% YoY

[0.88] Blackwell GB200 yield rate: 92% at TSMC CoWoS-L

290 claims234 sources8 min

How It Works

Swarm intelligence.
Not prompt engineering.

01
🐝Step 01

Scout

Queen decomposes your question into research axes. Generates 60+ search queries across 64 APIs. Plans the mission.

02
⬡Step 02

Harvest

Stealth drones fetch 1000+ URLs through a multi-layer evasion stack. Rotates backends: Chromium, SearXNG, Brave, Serper, Tavily.

03
⚗️Step 03

Extract

Your LLM extracts claims from raw content. Every fact scored 0.0–1.0 on specificity, density, uniqueness, verifiability, structure.

04
🧬Step 04

Deduplicate

Jaccard similarity at 0.60 threshold merges duplicate facts from different sources. No inflation. Only unique intelligence.

05
📊Step 05

Synthesize

Your LLM weaves verified claims into a structured report. Every statement mapped to a scored source. Zero hallucination.

06
🕸️Step 06

Graph

Entities and relationships stored in PostgreSQL. Knowledge compounds across missions. Research builds on research.

Benchmarks

Real results. No cherry-picking.

Depth 3 (standard). Self-hosted PostgreSQL. Your LLM key.

TopicClaimsQuality
NVIDIA GPU market 20262900.797
OpenAI GPT-5 capabilities5740.789
EU AI Act enforcement2670.759
Meta Llama 4 architecture5680.821
SpaceX Starship progress4120.804

Honest scoring. No sigmoid rescaling. No artificial inflation.Weighted average of specificity, density, uniqueness, verifiability, and structure.

Integrations

Works with your existing stack.

🤖

Claude Desktop

MCP (zero-code)

Add one URL to config. Claude calls BeHive natively.

⌨️

Cursor / Windsurf

MCP

Research from your IDE. No context switching.

⚡

n8n

Community Node

Drag-and-drop BeHive into automation workflows.

🏛️

Hermes Agent

MCP + Skill

Deep research with autonomous agents.

🦞

OpenClaw

Skill

ClawHub-ready skill for OpenClaw agents.

🔌

Any MCP Client

Streamable HTTP

Standard MCP protocol. Any client works.

MCP Configuration (works everywhere)

{
  "mcpServers": {
    "behive": {
      "url": "http://localhost:8090/mcp",
      "transport": "streamable-http"
    }
  }
}

Self-Hosting

Three commands. Your infrastructure.

Docker Compose. PostgreSQL + API + MCP. Zero config.

bash
$ git clone https://github.com/qa10devteam/behive.git
$ cp .env.example .env  # add your API key
$ docker compose up -d

✓ API ready at localhost:8091
✓ MCP server at localhost:8090
✓ PostgreSQL running

Comparison

Why not just use Perplexity?

BeHiveTavilyPerplexity
Per-claim scoring✅——
Knowledge graph✅——
MCP native✅——
BYOK (any LLM)✅——
64 API sources✅—~
Self-hosted✅——
SSE streaming✅——
Cross-session KG✅——
PriceFree$29/mo$20/mo+

Start researching.

One command. Infinite knowledge.

$pip install behive