Multi-agent CrewAI engineering team with per-role LLMs#1410
Open
yousefattaff wants to merge 2 commits into
Open
Multi-agent CrewAI engineering team with per-role LLMs#1410yousefattaff wants to merge 2 commits into
yousefattaff wants to merge 2 commits into
Conversation
A multi-agent software engineering team with per-role LLM config, 4 different Groq models, Docker code execution, and LangSmith observability. Built for week 3 of Ed Donner's AI Agentic Engineering course.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
An end-to-end multi-agent software engineering team built with CrewAI, using only free-tier models from Groq (4 different models, separate rate limit pools), with custom Docker code execution and LangFuse observability.
What it does Takes a natural-language requirements spec, then runs a sequential 4-agent pipeline: Engineering Lead produces a design document → Backend Engineer writes the Python module → Frontend Engineer builds a Gradio UI → QA Engineer writes and runs unit tests. All output goes to ./output/. Entire pipeline traced in LangFuse.
Labs covered
Lab 3 (Week 3): @crewbase class, 4 agents with per-role config, Process.sequential, task chaining via context, output_file
Custom tool: DockerCodeExecutor — replaces CrewAI's buggy built-in Code Interpreter, builds and runs code in Docker containers
Multi-provider LLM routing: LiteLLM with 4 different Groq models, each in a separate rate limit pool
Post-processing: strips tags and markdown from generated files using ast.parse() validation