Welcome! Type "help" for available commands.

microsoft/TypeAgent: Sample code that explores an architecture for...

~/bookmarks

/**/

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

github.comSaved October 19, 20256 min

AI Agent Research Project

Summary

TypeAgent is a Microsoft research project exploring an architecture for a personal agent that combines LLMs with traditional software. It introduces Structured RAG for precise conversational memory and the AMP system for natural information flow between actions and memories.

Highlights

Introduces Structured RAG, a new indexing and query approach that substantially outperforms Classic RAG for recalling past conversation details
Proposes three core principles: distill models into logical structures, use structure to control information density, and use structure to enable collaboration
The AMP architecture enables actions and memories to flow together naturally, so past actions become parameters for future ones
Authored by Guido van Rossum (Python creator) and Steve Lucco (TypeScript creator), giving it notable pedigree in the programming language community
Aims to map user requests to actions at much lower cost and latency than current systems by distilling LLMs into logical systems

auto-generated

Preview of GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

Guido van Rossum & Steve Lucco · via GitHub

Context

Audience

AI researchers and developers working on LLM-based agent systems, particularly those interested in agent memory architectures and structured prompting approaches

DomainAI Agents and Language Models

FormatOpen source code repository with documentation

AccessFree, open source on GitHub

Personal Notes

I got to meet Guido van Rossum and Steve Lucco (Python and Typescript founders, respectively) at the PyBay 2025 conference yesterday and we chatted about TypeAgent and structured RAG.

Topics

GitHub Natural Language Interfaces Structured Prompting Personal Agents Language Models

View on GitHub All Bookmarks

Structured RAGAMP (Action Memory Planning)Tree of ThoughtClassic RAGPersonal AgentsStructured Prompting

William's Bookmark Library

/**/

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

github.comSaved October 19, 20256 min

AI Agent Research Project

Summary

Highlights

Introduces Structured RAG, a new indexing and query approach that substantially outperforms Classic RAG for recalling past conversation details
Proposes three core principles: distill models into logical structures, use structure to control information density, and use structure to enable collaboration
The AMP architecture enables actions and memories to flow together naturally, so past actions become parameters for future ones
Authored by Guido van Rossum (Python creator) and Steve Lucco (TypeScript creator), giving it notable pedigree in the programming language community
Aims to map user requests to actions at much lower cost and latency than current systems by distilling LLMs into logical systems

auto-generated

Guido van Rossum & Steve Lucco · via GitHub

Context

Audience

AI researchers and developers working on LLM-based agent systems, particularly those interested in agent memory architectures and structured prompting approaches

DomainAI Agents and Language Models

FormatOpen source code repository with documentation

AccessFree, open source on GitHub

Personal Notes

I got to meet Guido van Rossum and Steve Lucco (Python and Typescript founders, respectively) at the PyBay 2025 conference yesterday and we chatted about TypeAgent and structured RAG.

Topics

GitHub Natural Language Interfaces Structured Prompting Personal Agents Language Models

View on GitHub All Bookmarks

Structured RAGAMP (Action Memory Planning)Tree of ThoughtClassic RAGPersonal AgentsStructured Prompting

~/bookmarks

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

Summary

Highlights

Context

Personal Notes

Topics

Related

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

Summary

Highlights

Context

Personal Notes

Topics

Related

~/bookmarks

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

Summary

Highlights

Context

Personal Notes

Topics

Related

Discover Similar Content

GitHub - openai/openai-agents-js: A lightweight, powerful framework for multi-agent workflows and voice agents

GitHub - g023/g023_agentic_chat: g023’s Agentic Chat

GitHub - NirDiamant/GenAI_Agents: This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.

Discover Similar Content

GitHub - microsoft/TypeAgent: Sample code that explores an architecture for using language models to build a personal agent that can work with application agents.

Summary

Highlights

Context

Personal Notes

Topics

Related

Discover Similar Content

GitHub - openai/openai-agents-js: A lightweight, powerful framework for multi-agent workflows and voice agents

GitHub - g023/g023_agentic_chat: g023’s Agentic Chat

GitHub - NirDiamant/GenAI_Agents: This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.