Automate competitive research, market analysis, and topic summaries. OE Runtime lets you run a Perplexity-powered research agent locally — searches the web, synthesises findings, and delivers structured reports automatically.
Create a file called agent.yaml inside a web-search/ directory:
name: Research Agent description: Search the web and summarise findings with citations instructions: | You are a research agent. Use web search to find current, accurate information. Always cite your sources and provide concise, well-structured summaries. Complete all steps fully before writing your report. steps: - name: Search content: | Run 3 separate web searches on the following topics: 1. Latest AI agent frameworks released in 2025 2. Enterprise AI automation adoption trends 2025 3. Top open-source LLM tools for business automation For each search, note the top 3 results: title, source, URL, and a one-sentence summary. - name: Synthesise Findings content: | From the 9 sources gathered: - Identify the top 5 themes that appear across multiple sources - Note any conflicting information or differing perspectives - Select the 5 most credible and relevant sources to cite in the final report - name: Report content: | Produce a structured research summary: Key Findings: [3-5 bullet points covering the main insights] Trends: [Top themes identified across sources] Sources: [Numbered list: title, publication, URL for each cited source] Recommendations: [2-3 actionable recommendations based on the research] connectors: - connection_name: Perplexity connection_type: perplexity
Create oe-config.json in the same directory:
{
"llm": {
"provider": "openai",
"model": "gpt-4o",
"apiKey": "YOUR_OPENAI_API_KEY"
},
"server": {
"enabled": false,
"port": 3333,
"apiKey": "your-secret-api-key"
},
"connectors": [
{
"connection_name": "Perplexity",
"connection_type": "perplexity",
"apiKey": "YOUR_PERPLEXITY_API_KEY"
}
]
}Get your Perplexity API key from perplexity.ai/settings/api. The agent uses Perplexity for real-time web search and your LLM for synthesis and report writing.
# Run the agent oe-runtime-win.exe web-search/agent.yaml --config web-search/oe-config.json
# Make executable (first time only) chmod +x oe-runtime-macos # Run the agent oe-runtime-macos web-search/agent.yaml --config web-search/oe-config.json
# Make executable (first time only) chmod +x oe-runtime-linux # Run the agent oe-runtime-linux web-search/agent.yaml --config web-search/oe-config.json
macOS Gatekeeper: On first run, macOS may block the binary. Go to System Settings → Privacy & Security → click "Allow Anyway" next to oe-runtime-macos.
Add --serve to start OE Runtime as an HTTP server on port 3333:
oe-runtime-win.exe --serve --config web-search/oe-config.json
Then send a request:
curl -X POST http://localhost:3333/run \
-H "Content-Type: application/json" \
-d '{"yaml": "web-search/agent.yaml", "params": {}}'Or import the Postman collection (download above) to test all endpoints visually.
Download OE Runtime and run any AI agent locally or as a server — no cloud required.
Get OE Runtime →