Skip to content

cmudrc/design-research-agents

Repository files navigation

design-research-agents

CI Coverage Examples Passing Public API In Examples Docs

Important

Current monthly release: The April Alignment
Due: April 1, 2026
Tracks: March 2026 work

design-research-agents is a modular framework for prototyping and researching engineering design AI agents. It features shared runtime contracts, workflow orchestration, and pluggable LLM backends for quick iteration.

Overview

This library centers on a small set of composable pieces you can run, inspect, and test:

  • Two primary entry points: DirectLLMCall and MultiStepAgent (direct, json, and code modes)
  • A tool runtime built around Toolbox, with callable, script, and MCP-backed tool configs
  • Prebuilt orchestration patterns for plan/execute, debate, propose/critic, routing, beam search, RAG, blackboard, and conversations
  • Hosted and local LLM clients, plus ModelSelector for backend-selection policies
  • Tracing, structured ExecutionResult outputs, and runnable examples aimed at repeatable experiments
  • A workflow runtime with explicit step primitives for model calls, tool calls, delegation, loops, and memory

A Super Basic Agent

from design_research_agents import LlamaCppServerLLMClient, MultiStepAgent

with LlamaCppServerLLMClient() as llm_client:
    agent = MultiStepAgent(mode="direct", llm_client=llm_client, max_steps=3)
    result = agent.run(
        prompt="Suggest two design goals for a field-repairable drone battery latch.",
    )

print(result.final_output)

Quickstart

Requires Python 3.12+. Reproducible release installs target Python 3.12 (see .python-version).

python -m venv .venv
source .venv/bin/activate
make dev
make test
PYTHONPATH=src python3 examples/patterns/plan_execute.py

For frozen installs, optional extras, and release maintenance, see Dependencies and Extras.

Examples

Start with examples/README.md for runnable examples grouped by agents, clients, workflows, patterns, model selection, and tools.

Docs

See the documentation site for the full guide set, including quickstart, backend setup, workflows, patterns, and API reference.

Build docs locally with make docs.

Contributing

Contribution guidelines now live in CONTRIBUTING.md.

About

A flexible, modular framework for researching AI agents that design

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Packages