Santiago Galindo

A system to improve everyone's life

[m0h @exploraX_]

https://t.co/gxTNr2YjLT

[Hasan Toor @hasantoxr]

🚨 BREAKING: CHINA just released a Python framework for building AI agents. 100% OPEN SOURCE.

It has visual agent design, MCP tools, memory, RAG, and reasoning. All built in. All working together.

It's called AgentScope.

You describe your agent system. It builds the architecture, wires the tools, and runs the whole thing. You come back and there's a working multi-agent pipeline. Not a prototype. Not a demo. The actual system.

Not a wrapper.
Not a chatbot builder.

A full Agent-Oriented Programming framework that thinks in agents from the ground up.

Here's what it does out of the box:
→ Visual agent builder so you design your entire system before writing a single line of code
→ Native MCP tool support, plug any external tool directly into any agent in your pipeline
→ Built-in memory so every agent remembers context, decisions, and history across sessions
→ RAG pipeline ready to connect your own documents, databases, and knowledge bases
→ Reasoning modules that let agents plan, reflect, and self-correct without human input
→ Multi-agent coordination so your agents collaborate as a system, not a pile of isolated API calls

Here's how it thinks:

You define your goal. AgentScope maps the agent roles. Each agent gets its tools, its memory, its reasoning layer. They coordinate. Results flow back up. You get a finished output.
A single complex task might route through a planner agent, a researcher agent, a coder agent, and a critic agent, each doing its job, then converge into one clean deliverable.

Here's the wildest part:
AgentScope is built by Alibaba DAMO Academy. The same lab behind Qwen. They didn't assemble this from existing pieces. They designed the entire framework from first principles around how agents actually need to think, remember, and work together. Most frameworks give you building blocks. AgentScope gives you an architecture. The community has already started plugging it into data pipelines, research workflows, and full automation systems the team never planned for.

100% Open Source. Apache 2.0 License.

[Poe Zhao @poezhao0605]

In one week this March, at least 6 local governments across China launched competing subsidy packages for OpenClaw adoption. Compute vouchers worth up to $2.8 million per entity per year. Seed funds. Housing allowances.

The real shift: the target is no longer the firm. It’s the individual AI operator. China’s local governments are competing for one-person companies.

But the compute economics behind these subsidies tell a more complicated story.
I break down who’s building real ecosystems and who’s planting flags: https://t.co/NxPYNMcV9r

[Julián @juliandeangeIis]

https://t.co/2DyIJtml1s

[Elvis @elvissun]

https://t.co/DotZ3V6XhJ

[Rohit @rohit4verse]

probably the only article you need to master claude code

[Muhammad Ayan @socialwithaayan]

BREAKING: AI can now do market research like McKinsey (for free).

Here are 12 insane Claude Opus 4.6 prompts that replace $5,000 consultant: (Save for later)

[cogsec @affaan]

https://t.co/s9QK7Xdoaz

[Mohamed Djoudir @mohamed_djoudir]

Next.js SaaS Template (2026 Edition)

built with
- Next.js 16 & React 19
- Tailwind CSS 4
- Framer Motion
- Next-intl (RTL support)

Comes with
Dark-themed design, i18n (EN + AR), Pricing pages, Blog, Auth pages, Charts & animations.

Demo + Source Code
(First comment) 👇

[Guillermo Rauch @rauchg]

In love with this aesthetic
https://t.co/pYz1Gn97jD

[Vercel @vercel]

We just released 𝚛𝚎𝚊𝚌𝚝-𝚋𝚎𝚜𝚝-𝚙𝚛𝚊𝚌𝚝𝚒𝚌𝚎𝚜, a repo for coding agents.

React performance rules and evals to catch regressions, like accidental waterfalls and growing client bundles.

How we collected them and how to install the skill ↓
https://t.co/kfLSbKl15X

[Kevin Kern @kevinkern]

This is one of my rules to avoid using useEffect (with TanStack Start).

[Guillermo Rauch @rauchg]

Pitch me your AI product or idea

[Santiago Galindo @spgalh]

@sairahul1 Hustle

[Santiago Galindo @spgalh]

@0xmetaschool I want to join

[LlamaIndex 🦙 @llama_index]

Have your conversational voice assistant do RAG over 1M+ PDFs 💬📑

This is a great 🧵 and demo by @MarcusShiesser showing you how to augment an @elevenlabs conversational assistant with a RAG tool powered by LlamaCloud document processing technology.

1. Serve the LlamaCloud retrieval API through @flydotio
2. Connect it to @elevenlabs as a tool

Check it out 👇 Resources below
LlamaCloud: https://t.co/DoZgCPCYPQ
ElevenLabs: https://t.co/cd7k5I6jlh

[Santiago Galindo @spgalh]

@iamkylebalmer Online

[Shubham Saboo @Saboo_Shubham_]

AI Agents and RAG tutorials with step-by-step instructions

100% Free and Opensource.

[LlamaIndex 🦙 @llama_index]

We’ve become increasingly interested in document agent workflows that can automate practical workflows beyond one-step RAG/IDP tasks. 📑🤖

First up - an e2e invoice processing agent 🧾: given an invoice, extract out the relevant information, match it with the relevant vendor contract and apply any vendor-specific discounts, and generate a payments plan.

Powered by @llama_index workflows, LlamaParse for parsing/extraction, and LlamaCloud indexing.

https://t.co/zH5W8ccxRk

[Santiago Galindo @spgalh]

@krea_ai Hi, can I fix hands/fingers with this tool? it is very common to see issues with hands unfortunately :(