Agents

Production agents with knowledge bases, research pipelines, multimodal processing, and integrations.

Agents that do real work. Each example demonstrates knowledge retrieval, multi-tool orchestration, structured output, or multimodal processing.

1from kern.agent import Agent
2from kern.models.openai import OpenAIResponses
3from kern.tools.yfinance import YFinanceTools
4
5agent = Agent(
6    model=OpenAIResponses(id="gpt-5.2"),
7    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True)],
8    instructions=["Use tables to display data"],
9    markdown=True,
10)
11
12agent.print_response("What's the outlook for NVDA?", stream=True)

Knowledge & RAG

Agents that search, retrieve, and reason over knowledge bases.

Kern Assist

Documentation assistant with hybrid search and source attribution.

Deep Knowledge

Iterative RAG that breaks complex queries into sub-queries.

Research & Analysis

Multi-tool agents for competitive intelligence and due diligence.

Competitor Analysis

Five-phase intelligence with Firecrawl and reasoning tools.

magnifying-glass

Research Agent

Journalism workflow with fact-checking across sources.

Startup Analyst

ScrapeGraph toolkit for investment due diligence.

Multimodal

Agents that process audio, video, and generate speech.

Speech to Text

Structured transcription with timestamps and speakers.

YouTube Agent

Video analysis with timestamped topic segmentation.

Integrations

Agents connecting to external platforms and protocols.

Social Media Agent

X/Twitter sentiment analysis and engagement metrics.

Web Extraction

Firecrawl to Pydantic structured output.

Translation Agent

Multi-step translation with emotion detection and TTS.

Airbnb MCP

Model Context Protocol integration with reasoning.