#66 · Primary category: LLM Application Frameworks
langroid
Harness LLMs with Multi-Agent Programming
Project last updated:08/29/26
GitHub Stars
4.1K
Forks
395
Contributors
31
License
MIT
Why we included this project
Langroid is a Python framework for coordinating several LLM-backed agents, built by researchers at CMU and UW-Madison. You define agents, attach optional pieces like an LLM, vector store, or function-calling tools, and let them tackle tasks by exchanging messages with one another. Its authors deliberately left LangChain out of the picture, and it works with any model behind an OpenAI-compatible API, so local servers such as Ollama are fair game. That appeals to teams wanting direct control over multi-agent conversations and RAG-style document chat without adopting a heavier ecosystem. The repo documents real production deployments, and its examples for local-LLM extraction and structured data pulling offer a quick way to test the waters before committing.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform