CODE

→ View original post on X — @sumanth_077

Notte: Open Source Framework for Developing and Scaling AI Agents

By

@sumanth_077

–

20 May 2025 17h04

Turn internet into an agent-friendly environment just using natural language! Notte is the open source framework that allows you to develop, deploy, and scale your own agents with a single API. 100% Open Source

→ View original post on X — @yoheinakajima

While Loops Without Exit Conditions: Programming Best Practices

By

@yoheinakajima

–

20 May 2025 16h03

Apparently you aren’t supposed to create a while loop without an exit either, but

Tiny-agents: Configure custom AI agents locally with PROMPT.md

By

–

20 May 2025 16h01

Optionally, you can add a http://
PROMPT.md file to override the default Agent prompt. Then just point tiny-agents to your local folder: npx @huggingface/tiny-agents run ./my-agent Voilà!

Hugging Face Releases Tiny Agents JavaScript Library

By

–

20 May 2025 16h01

Link to the code: https://
github.com/huggingface/hu
ggingface.js/tree/main/packages/tiny-agents
… PS: this is built on top of @huggingface partners-powered Inference Providers, and our MCP client

Tiny Agents NPM Package Released for Lightweight AI

By

–

20 May 2025 16h01

Today I'm releasing Tiny Agents into its own NPM package It is a squad of lightweight composable agents, built on Hugging Face's Inference Client and MCP stack. Here's a tiny tutorial to get started.

Creating Custom AI Agents with JSON Configuration

By

–

20 May 2025 16h01

Creating your own agent is as easy as creating a folder containing an agent.json file: mkdir my-agent
touch my-agent/agent.json Inside the JSON file, set a model and a provider (or a local endpoint), and a list of MCP servers: {
"model": "Qwen/Qwen2.5-72B-Instruct",

→ View original post on X — @yoheinakajima

MCPs Tool Management and Automated Filtering for AI Agents

By

@yoheinakajima

–

20 May 2025 15h46

Yes! I want to have a massive list of tools that are embedded and filtered down to likely ones automatically but I don’t think that’s easy with MCPs…. but maybe you can?

→ View original post on X — @montreal_ai

α-AGI Framework: Sovereign Agents Marketplace and Continuous Refinement

By

@montreal_ai

–

20 May 2025 15h41

[ α‑AGI Framework Flow ] α‑AGI Insight → α‑AGI Sovereign (Marketplace → Jobs → Agents) → α‑AGI Architect ↺ Continuous sovereign feedback loops for infinite refinement. Unlock history's ultimate Alpha. https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0
… #AGIALPHA $AGIALPHA