research-report-agents

HamsikaRaj/research-report-agents

★ 0 stars Python AI/LLM Updated 12d ago

Three-agent research system on the OpenAI Agents SDK — Planner/Executor/Reviewer with typed handoffs, a custom MCP server, function tools, input/output guardrails, token-streaming (CLI + SSE), tracing, and an LLM-judge eval harness with a pytest regression gate.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "research-report-agen": {
      "command": "uvx",
      "args": [
        "research-report-agents"
      ]
    }
  }
}

Or install with pip: pip install research-report-agents

README Excerpt

A multi-agent system built on the OpenAI Agents SDK. It takes a research question, breaks it into steps, gathers evidence with tools and a Model Context Protocol (MCP) server, and returns a validated, structured answer. I built it to get hands-on experience with the OpenAI Agents SDK, the Responses API, and MCP, porting a research

Topics

ai-agentsevaluationfastapiguardrailsllmmcpmodel-context-protocolmulti-agentopenaiopenai-agents-sdkpython

research-report-agents

Quick Install

README Excerpt

Topics

Related AI/LLM Servers