workflowstacks
multi-agent

langroid: Build Multi‑Agent LLM Apps Quickly with Python

Create scalable AI agents using langroid’s Python framework—ideal for founders needing chat, retrieval‑augmented generation, or custom LLM workflows. 4.1k+ GitHub stars.
4,113 stars+3★ this week417 forksPythonGuide quality 8/10 · reviewed Oct 9Updated 10/9/2026100% free · open source
What it does

Langroid streamlines AI development by harnessing large language models (LLMs) within multi-agent systems, allowing for more efficient and scalable AI development

When to use it
  • •You're building a complex AI system that requires coordination between multiple agents
  • •You want to leverage the power of LLMs but need a framework to manage their interactions
  • •Your AI project involves multiple tasks or domains that can be addressed by different agents
Ready-to-paste prompt
python example_llm_agent.py --llm-model bert-base-uncased --agent-count 5
Heads up: Ensure you have the necessary dependencies installed, including `transformers` and `torch`, as specified in the `requirements.txt` file, to avoid import errors when running langroid
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/langroid && curl -fsSL https://workflowstacks.com/api/skills/langroid/claude-skill -o ~/.claude/skills/langroid/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How langroid: Build Multi‑Agent LLM Apps Quickly with Python works
Codeflow
Free to inspect

Langroid: Build Multi‑Agent LLM Apps Quickly with Python is mostly documents (179 doc files, 320 small scripts) — something you read, not something you run. You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license.

Size
Mostly documents
179 documents · 320 small scripts · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 2 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Python · Docker
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    langroid/__init__.py
    Inside langroid/ — the main logic begins here
  4. 4
    examples/Langroid_quick_start.ipynb
    A worked example — copy this to get going
What's in each folder
langroid/Core code — the actual logic144 files
plugins/Sub-packages / plugins10 files
examples/Examples you can copy215 files
docs/Documentation133 files
issues/Folder25 files
release-notes/Folder13 files
ai-notes/Folder3 files
.claude-plugin/Plugin manifest — what gets installed1 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
langroid
Language
Python
Category
multi-agent
Published
4/16/2023

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/langroid.svg)](https://workflowstacks.com/skills/langroid?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More multi-agent tools founders pair with this one.

multi-agent★ 110,386
TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework
multi-agent★ 59,496
crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
multi-agent★ 10,701
Orchestrate AI Agents with Omnigent
Swap harnesses without rewriting code with Omnigent, a framework for startup founders. 5.6k+ GitHub stars
multi-agent★ 513
zhikuncode: Self-host AI coding
Get self-hosted AI coding with zhikuncode, ideal for founders needing secure multi-agent collaboration.
multi-agent★ 4,576
Council of High Intelligence: Informed Decisions
Get structured multi-round deliberation for your toughest decisions with Council of High Intelligence, ideal for startup founders, backed by 3.2k+ GitHub stars
multi-agent★ 18
vmux: Control coding agents
Monitor and respond to coding agents from your phone with vmux, for founders using tmux and coding agents.