oryx1729

https://github.com/morishuz/CoreSQL

https://github.com/morishuz/RadixKit

https://github.com/morishuz/adaptive-frame-extractor

https://sanbox.cloud/blog/always-on-sanbox-computers-for-supabase/

https://sanbox.cloud/blog/building-a-persistent-browser-terminal/

https://github.com/morishuz/delaunay32

Today, we are releasing Hermes Agents running on the Kimi K3 model inside a sandbox. You don’t need a Mac mini to run one!You can connect it to Telegram.The initial setup takes less than 10 minutes. All you need to do is:1. Create a Telegram bot and get the bot token.2. Sign up for Sanbox and connect your preferred model provider’s key.3. Create a Sanbox API key.4. Ask your coding agent, such...

https://sanbox.cloud

Hi HN,We are building Sanbox, a platform for running AI agents in isolated and resumable sandboxes.We use the OpenCode SDK as the harness, support reusable templates, and have a CLI that works with Codex, Claude Code, Cursor, CI, or your terminal. Each sandbox has MicroVM isolation, a persistent filesystem, and live trail of run events. Can also self-host if required for...

I'm building an agent sandbox platform with opinionated customizable templates for general purpose agents using the OpenCode SDK.The idea is to provide a great CLI experience so it's easy to use an AI client like Claude Code or Codex to launch sandboxes, fetch/retrieve data and prompts, review generated outputs, and manage queues for ask-user questions.I also plan to add an AI gateway layer,...

https://www.docker.com/blog/introducing-docker-mcp-catalog-and-toolkit/

https://med-oryx.streamlit.app

I created a simple app to explore how Agents & MCP can help with medical research. It connects to ClinicalTrials.gov, PubMed/PubTator, and MyVariant.info using the BioMCP Server(https://github.com/genomoncology/biomcp), and uses Haystack(https://github.com/deepset-ai/haystack) as the MCP Client.The idea is to let users ask natural-language questions like: - Are there new studies on...

https://r1-demo.deepset.ai

Hey HN,We built a live demo to compare DeepSeek R1 and OpenAI’s o1 model on a simple RAG pipeline using Haystack, our open-source AI framework. Both pipelines use the same retrieval and prompts to ensure a fair comparison.Would love to hear your thoughts -- how do open-weight models stack up against proprietary ones for RAG?blog post + demo link:...

http://graphrag-demo.deepset.ai/query-gen

A common UX challenge with RAG applications is that they often leave users staring at a blank page, unsure of what queries to run to explore a dataset. This can be overwhelming and inefficient.GraphRAG transforms this experience with its entity-based query generation feature. By combining structured data (entities and relationships) with unstructured data (community reports and covariates), it...

https://oryx1729.github.io/gephi-lite/?file=https%3A%2F%2Foryx1729.github.io%2Fgephi-lite%2Fsamples%2Fsummarized_graph.gexf

Hi HN,I've built a demo to query quarterly earnings call transcripts from a select few S&P 100 companies using Microsoft's new GraphRAG framework.One of the key advantages of GraphRAG over traditional vector retrieval methods is its transparency and explainability. Unlike vectors, which are often obscure and not human-readable, the graphs generated by GraphRAG are easily interpretable.In...

https://graphrag-demo.deepset.ai

Hi HN,Microsoft recently open-sourced the GraphRAG framework, which enables more contextual responses than traditional vector-based RAG, especially for summarization-focused queries on textual data.However, a common critique is the LLM costs for constructing the knowledge graph. With the newly released GPT-4o mini, working with GraphRAG would now be ~30x cheaper.We built a demo with quarterly...

https://graphrag-demo.deepset.ai

Hi HN,Microsoft recently open-sourced the GraphRAG framework for information retrieval, utilizing graph-based structures. It automates the construction of knowledge graphs using LLMs and enhances retrieval by connecting related concepts and entities in a query for more contextual and accurate responses.GraphRAG offers a larger connected context for retrieved information, which LLMs use to...