How I built a Multi-Agent system from scratch

Discover how to build a multi-agent system with context enhancement, shrinking, and unique tool result handling for effective agent collaboration and dynamic context management.

Python OpenAI API ChromaDB MCP tree-sitter

Overview

A multi-agent AI system with three context control mechanisms I discovered while building it: context enhancement, context shrinking, and unique tool result handling. The demo shows agents collaborating while these mechanisms silently manage context across handoffs.

Links

https://github.com/saigontechnology/AgentCrew
AgentCrew is a multi-agent AI system supporting multi-models and MCP.

Tech stack

Python

Python: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.

Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .

https://python.org

View projects
OpenAI API

OpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.

The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.

https://platform.openai.com/

View projects
ChromaDB

ChromaDB is the open-source vector database built for LLM applications, providing simple, fast semantic search via embedding management.

ChromaDB is your go-to open-source embedding database for building advanced LLM applications, specifically Retrieval-Augmented Generation (RAG) systems. It simplifies the storage, indexing, and querying of vector embeddings and their metadata, enabling fast Approximate Nearest Neighbor (ANN) similarity search. Developers appreciate its lightweight design: it runs in-memory, persistently using SQLite 3, or in client/server mode, offering robust Python and JavaScript SDKs. With over 5M+ monthly downloads and deep integration with tools like LangChain and LlamaIndex, Chroma is a proven, developer-friendly component for your AI stack.

https://www.trychroma.com

View projects
MCP

MCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.

The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .

https://modelcontextprotocol.io/

View projects
tree-sitter

An incremental parsing library that builds concrete syntax trees and updates them efficiently during live editing.

Tree-sitter generates robust syntax trees using a C-based runtime and language-specific grammars. It supports over 40 languages (including Rust, JavaScript, and Python) to power features like syntax highlighting and code navigation in Neovim and GitHub. The engine handles syntax errors gracefully and re-parses modified code in O(log n) time. This efficiency ensures immediate feedback without blocking the main editor thread.

https://tree-sitter.github.io/tree-sitter/

View projects

How I built a Multi-Agent system from scratch

Related talks