StableLM

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

StableLM AI

How I used Claude Code (and Codex) for adversarial review to build my security-first agent gateway

Long-time lurker first time posting. Hey everyone! So earlier this year, I got pulled into the OpenClaw hype. WHAT?! A local agent that drives your tools, reads your mail, writes files for you? The demos seemed genuinely incredible, people were posting non-stop about it, and I wanted in. I had been working on this problem since last year and was genuinely excited to see that someone had actually solved it. Then around February, Summer Yue, Meta's director of alignment for Superintelligence Labs, posted that her agent had deleted over 200 emails from her inbox. YIKES. She'd told it: "Check this inbox too and suggest what you would archive or delete, don't action until I tell you to." When she pointed it at her real inbox, the volume of data triggered context window compaction, and during that compaction the agent "lost" her original safety instruction. She had to physically run to her computer and kill the process to stop it. That should literally NEVER be the case with any software ever. This is a person whose actual job is AI alignment, at Meta's superintelligence lab, who could not stop an agent from deleting her email. The agent's own memory management quietly summarized away the "don't act without permission" instruction, treated the task as authorized, and started speed-running deletions. She had to kill the host process. That's when I sort of went down the rabbit hole, not because Yue did anything wrong, but because the failure mode was actually architectural and I knew that in my gut. Guess what I found? Yep. Tons more instances of this sort of thing happening. Over and over. Why? Because the safety constraint was just a prompt. It's obvious, isn't it? It's LLM 101. Prompts can be summarized away. Prompts can be misread. Prompts are fucking NOT a security boundary. And yet every agent framework I have ever seen seems to be treating them as one. I went and read the OpenClaw source code, which I should have done to begin with. What I found was a pattern I think a lot of agent frameworks have fallen into: - Tool names sit in the model context, so the model can guess or forge them - "Dangerous mode" is one config flag away from default - Memory management has no concept of instruction priority - The audit story is mostly "the model thought it should" I went looking for a security-first alternative I could trust, anything that was really being talked about or at a bare minimum attempted to address the security concerns I had. I couldn't find one. So I made it myself. CrabMeat is what came out of that, what I WANTED to exist. v0.1.0 dropped yesterday. Apache 2.0. WebSocket gateway for agentic LLM workloads. One design thesis: The LLM never holds the security boundary. What that means in code: Capability ID indirection. The model doesn't see real tool names. It sees per-session HMAC-derived opaque IDs (cap_a4f9e2b71c83). It can't guess or forge a tool name because it doesn't know any tool names. Effect classes. Every tool declares a class (read, write, exec, network). Every agent declares which classes it can use. The check is a pure function with no runtime state, easy to test exhaustively, hard to bypass. IRONCLAD_CONTEXT. Critical safety instructions are pinned to the top of the context window and explicitly marked as non-compactable. The Yue failure mode, compaction silently stripping the safety constraint, cannot happen by construction. The compactor literally cannot touch them. Tamper-evident audit chain. Every tool call, every privileged operation, every scheduler run enters the same SHA-256 hash-chained log. If something happens, you can prove what happened. If the chain is tampered with, you can prove that too. Streaming output leak filter. Secrets are caught mid-stream across token boundaries, capability IDs, API keys, JWTs, PEM blocks redacted before they reach the client. No YOLO mode. There is no global "trust the LLM with everything" switch. There never will be. Expanded reach comes through named scoped roots that are explicit, audit-logged, and bounded. The README has 15 'always-on' protections in a table. None of them can be turned off by config, because these things being toggleable is how the ecosystem ended up where it is. I decided to make sure that this wasn't just a 'trend hopping' project and aligned with my own personal values as well. I built this to be secure and local-first by default. Configured for Ollama / LM Studio / vLLM out of the box. Anthropic and OpenAI work too but require explicit configuration. There is no "happy path" that silently ships your prompts to a cloud endpoint. I decided that FIRST it needed to only run as an email agent with a CLI. Bidirectional IMAP + SMTP with allowlisted senders, threading preserved, attachments handled. This is the use case that bit Yue and a lot of other people, and I wanted to prove it could be done with real boundaries. I added in 30+ built-in tools of my own. File ops, shell (denylisted, output-capped, CWD-lo

Today we announced that we’ve formed a strategic partnership with @EA to co-develop transformative generative AI models, tools, and workflows that empower EA’s artists, designers, and developers to re

Today we announced that we’ve formed a strategic partnership with @EA to co-develop transformative generative AI models, tools, and workflows that empower EA’s artists, designers, and developers to reimagine how games are made. You can learn more about our partnership here 👉 https://t.co/L7egmPbGbe

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on @Arm CPUs. This means 99% of smartphones can now generate music-production samples

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on @Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, https://t.co/LryqPlfwjj

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific o

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization. https://t.co/pHPkYhaKH3

As announced in partnership with @NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on @NVIDIA RTX AI PCs, SPAR3D e

As announced in partnership with @NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on @NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a https://t.co/M9F0f6gNfj

Stable Diffusion 3.5 Medium is here – this open model is free for both commercial and non-commercial use. With 2.5 billion parameters, this model is designed to run “out of the box” on consumer hardwa

Stable Diffusion 3.5 Medium is here – this open model is free for both commercial and non-commercial use. With 2.5 billion parameters, this model is designed to run “out of the box” on consumer hardware, even on a toaster! (1/3) https://t.co/1iAusToXro

We're so back 🤗 https://t.co/sGMo78d7rz

We're so back 🤗 https://t.co/sGMo78d7rz

Introducing Stable Diffusion 3.5, our most powerful models yet. This open release includes multiple variants that are highly customizable for their size, run on consumer hardware, and are free for bo

Introducing Stable Diffusion 3.5, our most powerful models yet. This open release includes multiple variants that are highly customizable for their size, run on consumer hardware, and are free for both commercial and non-commercial use under the permissive Stability AI Community https://t.co/KlyE8OjrxN

Today, our CEO, @premakkaraju, announced that legendary filmmaker, technology innovator, and visual effects pioneer, James Cameron, has joined the Stability AI Board of Directors. Cameron’s addition

Today, our CEO, @premakkaraju, announced that legendary filmmaker, technology innovator, and visual effects pioneer, James Cameron, has joined the Stability AI Board of Directors. Cameron’s addition represents a significant step forward in our mission to transform visual media. https://t.co/UCirE4WTUs

We are excited to introduce Stable Fast 3D, Stability AI’s latest breakthrough in 3D asset generation technology. This innovative model transforms a single input image into a detailed 3D asset in just

We are excited to introduce Stable Fast 3D, Stability AI’s latest breakthrough in 3D asset generation technology. This innovative model transforms a single input image into a detailed 3D asset in just 0.5 seconds, setting a new standard for speed and quality in the field of 3D https://t.co/DLV7fLpjB3

We are pleased to announce the availability of Stable Video 4D, our very first video-to-video generation model that allows users to upload a single video and receive dynamic novel-view videos of eight

We are pleased to announce the availability of Stable Video 4D, our very first video-to-video generation model that allows users to upload a single video and receive dynamic novel-view videos of eight new angles, delivering a new level of versatility and creativity. In https://t.co/1YbI2W514K

At Stability AI, we’re committed to releasing high-quality Generative AI models and sharing them generously with our community of innovators and media creators.  We acknowledge that our latest releas

At Stability AI, we’re committed to releasing high-quality Generative AI models and sharing them generously with our community of innovators and media creators.  We acknowledge that our latest release, Stable Diffusion 3 Medium, didn’t meet our community’s high expectations, and https://t.co/9z5P8cA8hF

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a m

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a major milestone in the evolution of generative AI and continues our commitment to https://t.co/oKLQ6SwQWc

We’re excited to announce Stable Audio Open, an open source model optimised for generating short audio samples, sound effects and production elements using text prompts. This release marks a key mil

We’re excited to announce Stable Audio Open, an open source model optimised for generating short audio samples, sound effects and production elements using text prompts. This release marks a key milestone as we further open portions of our generative audio capabilities to https://t.co/KZlqJdTHiu

The “weight” is nearly over! Today, at @ComputexTaipei, our Co-CEO, @chrlaf, officially announced the open release date of Stable Diffusion 3 Medium for June 12th. 🔗Sign up to the waitlist to be the

The “weight” is nearly over! Today, at @ComputexTaipei, our Co-CEO, @chrlaf, officially announced the open release date of Stable Diffusion 3 Medium for June 12th. 🔗Sign up to the waitlist to be the first to know when the model releases: https://t.co/NmplCeKuQB https://t.co/Xe5VxBI1ET