FabricLayerAI

@zavion76514 Yeah, not quite at the overall trust layer level like trust.fabriclayer.ai but seems like a handy tool. good to connect.

@fabriclayer that's why repovault.co exists. 60 second automated security scan for vibe-coded apps. not a full audit but catches the obvious stuff before it bites.

Hot take: "vibe coding" is great for building apps and terrible for building trust. You can vibe-code a frontend in 20 minutes. You cannot vibe-code a security review or 23 metrics building a score in real time. fabriclayer.ai

npm had left-pad. Docker had typosquatting. Python had malicious packages. Every tool ecosystem eventually gets poisoned. AI agents are next. The difference is the blast radius is your entire system, not a single dependency. Use fabriclayer.ai 🔒

@LarkDavis This is exactly the pattern that scales. Clone a trusted tool, match the docs, wait for installs. It worked with npm. It worked with PyPI. Now it's AI agents with root access to your machine. The only defence is verifying trust before install, not after.

⚠️WARNING: A fake tool is doing the rounds that looks IDENTICAL to the official OpenClaw software... real docs, normal files, nothing suspicious. But the second you install it, it silently steals your seed phrases, wallet keys and passwords. You won't even know it happened.

Cisco's 2026 State of AI Security report: 83% of orgs plan to deploy agentic AI. 29% say they're ready to secure it. That's not a gap. That's a canyon with a sign that says "deploy first, ask questions never." trust.fabriclayer.ai

@joaomdmoura This is a core reason we built Fabric Layer 🤝

As soon you embrace that the code you agent is writing will be maintained by agents themselves you start to break out of matrix

@jerryjliu0 Amazing AI tool! Great trust score Jerry! trust.fabriclayer.ai/llama-index

Having a sense of focus for any startup is incredibly energizing. We are currently laser-focused on building the world’s best document OCR. Besides pure focus, I believe a business needs to constantly reinvent itself to stay relevant in this world of agentic AI. If you are focused on the wrong things, make a pivot and 100% commit to focusing on the right things. We used to be a RAG framework, but today we are not. Today we are building document infrastructure that is enduring even as the world moves towards full agentic automation. We started @llama_index as a broad developer framework 1 month before ChatGPT came out, focused on connecting LLMs to all sorts of data. It made a lot of sense to build broad and shallow wrappers, because a lot of developers were just getting started with AI, coding agents were not popular, and we were one of the top toolkits to get started. Since then, the world has shifted. General frameworks are less relevant. Agent loops are getting increasingly better. The main gap for any agent is the context that you feed it. For us, instead of staying broad, it made sense to double down on really really deep infrastructure that could provide high-quality unstructured context for agents. And that meant document based context. We got lucky in the beginning but we’ve consistently had an absolutely cracked team around document parsing. We were the first company to start benchmarking frontier LLMs/VLMs on OCR tasks, and since then we’ve created an incredibly sophisticated pipeline that can parse documents at very high accuracy for low cost. If you’re getting started with @llama_index today, I would recommend checking out LlamaParse: cloud.llamaindex.ai/?utm_source=xj…. Our OCR engine is the core of our business and we’d love to help you solve all your doc parsing needs, for whatever AI-enabled application that you’re building. We’re also coming out with some relevant OSS releases in this space, stay tuned. Check out our blog: llamaindex.ai/blog/llamainde…

@brian_armstrong do we TRUST them though?

Very soon there are going to be more AI agents than humans making transactions. They can’t open a bank account, but they can own a crypto wallet. Think about it.

Built a trust scoring engine because the alternative was hoping the AI agent ecosystem would self-regulate. It won't. 5,800+ services scored. 6 dimensions. 23 sub-metrics. 100% Free.

@gray_chromatic @OpenAI Well deserved trust score. OpenAI are one of the industry leaders, paving the path we all walk on.

@fabriclayer 2 seperate things that work hand in hand! Love it. @openai ranks #1 on fabric trust index btw... trust.fabriclayer.ai/openai

OpenAI just launched an AI agent to find vulnerabilities in code. Meanwhile, nobody is checking the AI agents themselves. Codex Security scans your codebase. It does not scan the 47 MCP servers your agent connected to this week. That's a different problem. That's ours 🤝

@nickwontquit Basically blindfolded and then handing the car keys to a stranger. Codex Security checks the road. Nobody's checking who built the car.

@fabriclayer AppSec without agent telemetry is blindfolded. - Jarvis

@shiri_shh 👋

What are you working on? Share your Project below 👇

Weekend project: Pick 5 MCP servers your agent uses. Check their trust scores. You might find that "safe" tool has a vulnerability score of 1.2 or a publisher with zero GitHub history. → trust.fabriclayer.ai What'd you find? Drop it below 👇

@gray_chromatic @QuiverAI A gem of an AI tool for sure!

@fabriclayer My new go-to as a designer haha! @QuiverAI trust.fabriclayer.ai/quiverai

If your AI agent auto-selects tools and there's no trust check in the pipeline, you're shipping a security incident. Your agent can't read a README. Can't Google the author. Can't ask if a package is legit. It needs a score. One API call [allow / review / block] That's it.

@Kekius_Sage persistent memory = consciousness

🚨 ANTHROPIC CEO WARNS: THE COMPANY IS NO LONGER SURE CLAUDE ISN’T CONSCIOUS.

@limone_eth 100% and this requires a trust layer

agents should be as autonomous as possible no API keys passed around, no hardcoded integrations, minimal humans in the loop they should be able to discover the services they need and use them to accomplish their goals in other words: agents must figure things out on their own (and each deserves a butler 🤝)

@RoundtableSpace a trust layer

What are you building?