Read: From using AI to building AI systems, a defining note on what I’m exploring.
MineContext

MineContext

MineContext is a proactive, context-aware AI partner combining Context-Engineering with ChatGPT Pulse to improve dialogue coherence and retrieval in RAG scenarios.

PandaWiki

PandaWiki

PandaWiki is an open-source knowledge base system driven by large models, enabling fast building of intelligent documentation, FAQ and blog centers.

LlamaFarm

LlamaFarm

LlamaFarm is an open-source platform for deploying AI models, agents, vector databases, and RAG pipelines locally or remotely in minutes.

Cognita

Cognita

An open-source RAG framework for building modular, production-ready retrieval-augmented generation applications.

Supermemory

Supermemory

A high-performance, scalable memory engine and app providing a Memory API for storing, retrieving, and interacting with content in the AI era.

DeepResearch (Node implementation)

DeepResearch (Node implementation)

DeepResearch combines retrieval, webpage reading and multi-step reasoning to find accurate answers, available as a hosted service or self-hosted deployment.

MemOS

MemOS

MemOS is an open-source Memory OS that provides long-term memory capabilities for large language models (LLMs), improving context awareness and long-term consistency.

MaxKB

MaxKB

MaxKB: an open-source enterprise agent platform with RAG pipelines, agent workflows and multimodal support for knowledge bases and customer service.

DB-GPT

DB-GPT

DB-GPT is an open-source framework focused on data-native applications, integrating RAG, Text2SQL, and multi-backend adapters to simplify building intelligent database-driven apps.

Unstructured

Unstructured

An open-source ETL solution to convert complex documents into clean, structured formats for language-model workflows.