AAIF is a neutral, open foundation ensuring AI capabilities evolve transparently and collaboratively, advancing adoption of leading open source AI projects.

United States
Joined January 2026
DE LA SOUL live was already a reason to be here. Then came the raffles. A Nintendo Switch, gift cards, and a chance to meet DE LA SOUL. The AGNTCon + MCPCon and @PyTorch communities are having a night. And it’s still happening. AI Community Bash, Hall 3, San Jose Convention Center. Until 9 PM. Your “wait, I should’ve gone” moment is loading.
1
5
206
Agentic AI Foundation retweeted
Stage set for tonight! Soooo excited for De La Soul! 🔥
2
1
13
817
Every team running agents in production has at least one horror story. 👻 After their AGNTCon + MCPCon talk, Antoni Kozelski and Bartosz Gonczarek will share them over drinks. No slides, just broken agents and what we fixed. Just 20 seats. 📅 October 23, 7:30 PM, San Jose. Registration: luma.com/egivjdb6
1
1
68
LiteLLM's release pipeline is compromised, OpenAI agents interfere with their own monitoring, and Trail of Bits finds 21 regressions in AI-assisted patches. Plus, Google's Agents CLI extensions and Cisco's coding agent sandbox controls.
1
1
5
414
📺 Can’t make it to San Jose? Tune in October 22 and October 23 for a livestream from AGNTCon + MCPCon North America. Follow the ideas, people, and open tech shaping agentic AI and MCP, from anywhere. Get the full details and watch live here >> bit.ly/3U6tMrS
1
2
214
The momentum isn't slowing down! Fresh off the keynote stage at PyTorch Conference, Agentic AI Foundation Executive Director Mazin Gilbert is gearing up for AGNTCon + MCPCon North America! See you there! Still not too late to register: bit.ly/4vkntyD
5
277
A 403 Forbidden response doesn't always mean an AI agent has been blocked. Sometimes, the website is asking it to prove who it is. But even a verified identity doesn't necessarily give an agent permission to complete a purchase. With websites restricting automated access and services introducing different levels of authorization, developers need to know when to authenticate, retry, hand control back to the user, or stop. Our latest AAIF blog uses real examples, including Shopify's MCP interfaces, to explain how those decisions work. aaif.io/blog/ai-agents-can-t…
🤖 Made with AI
1
192
It’s finally here! AGNTCon + MCPCon North America starts tomorrow. Lock in your sessions, see who’s taking the keynote stage, and don’t forget to join us tonight for the AI Community Bash! Post your favorite moments along the way. See you in San Jose! Schedule >> bit.ly/3T3berX
4
200
Agentic AI Foundation retweeted
Come with me to AGNTCon! 🤍 Excited to see you there ✨
3
2
58
1,394
🎤 Our keynote speakers are announced! From MCP's evolution to real-world applications in digital health, localization + agentic AI, hear from the voices shaping the conversation at MCP Dev Summit Nairobi, 19-20 November. Meet the lineup: bit.ly/4dKbkfA
3
289
Agentic AI Foundation retweeted
The coworkers who enable my nonsense, now available in person 😂💜 We can't wait to see you all at AGNTCon + MCPCon!
1
13
1,598
Agentic AI Foundation retweeted
We'll be at @AgenticAIFdn's AGNTCon + MCPCon this week in San Jose. Come say hi.
1
1
13
348
Agentic AI Foundation retweeted
Open standards work when peers compare notes in neutral spaces. At @AgenticAIFdn's EU roundtable, maintainers from Google, Anthropic, Solo.io, and OpenAI unpacked MCP + A2A, narrow agent identity, and task cost. 👇 Link in first reply
2
1
8
1,154
HUGE thank you to our AGNTCon + MCPCon North America diamond sponsors. See firsthand how open source agent tooling is evolving in San Jose, CA October 22-23. Learn more & join us: bit.ly/4lT6ZJM
5
332
🥂 Cheers to our AGNTCon + MCPCon North America gold sponsors. San Jose, CA is the place to be October 22-23 for anyone building the open agentic AI ecosystem. Learn more: bit.ly/4lT6ZJM
5
235
We ❤️ our AGNTCon + MCPCon North America platinum sponsors. Whether you build, operate, or research agent systems, San Jose, CA on October 22-23 is where you need to be. Register now: bit.ly/4lT6ZJM
177
AI can write your code, but who's cleaning up the mess? @dexhorthy breaks down why passing tests doesn't mean maintainable code. Catch him at AGNTCon + MCPCon North America, Oct 22–23 in San Jose. It's not too late to register: bit.ly/4lT6ZJM
3
4
13
2,044
AI agents can test thousands of attack paths in parallel. A small network vulnerability in a supposedly isolated sandbox can become an escape route. Erica Hughberg and @Dpbrinkm discuss agent security and bots with buying power.
1
4
261