CrabTrap is an LLM-as-a-judge HTTP proxy to secure agents in production. It intercepts and audits AI agent requests in real time. Try it on GitHub now.
AI proxy: fostering a more open ecosystem - Blog - Braintrust
Introducing Braintrust's latest feature: an AI proxy that lets you use open source models like LLaMa 2 and Mistral, as well as all of OpenAI's and Anthropic's models, behind a single interface with caching, security, and API key management built in.
agentOS — A faster, lighter, cheaper alternative to sandboxes
A portable open-source operating system for agents. Stateful runtime, universal agent interface, and secure code execution. One SDK, deploy anywhere.
Anchor - Secure Infrastructure for Computer Use Agents
Secure Infrastructure for Computer Using AI agents - Deploy millions of browser agents to automate any web task. Faster, cheaper, and more reliable than human operations.
Claude on Twitter / X
With self-hosted sandboxes, you can run agents in any environment you control: your own infrastructure, or managed providers like Cloudflare, Daytona, Modal, or Vercel. pic.twitter.com/OELUCt7QRf— Claude (@claudeai) May 19, 2026
Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet | Brave
The attack we developed shows that traditional Web security assumptions don't hold for agentic AI, and that we need new security and privacy architectures for agentic browsing.
Under the hood: Security architecture of GitHub Agentic Workflows
Learn how our threat model and security architecture help teams run agents safely in GitHub Actions.
Defeating Prompt Injections by Design
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models are susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows by enforcing security policies when tools are called. We demonstrate effectiveness of CaMeL by solving $77\%$ of tasks with provable security (compared to $84\%$ with an undefended system) in AgentDojo. We release CaMeL at https://github.com/google-research/camel-prompt-injection.
The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web
The fragmentation of AI agent ecosystems has created urgent demands for interoperability, trust, and economic coordination that current protocols (MCP Hou et al. (2025); Desai (2025), A2A Habler et al. (2025), ACP Liu et al. (2025), and Cisco’s AGP Edwards (2025)) cannot address at scale. We present the Nanda Unified Architecture, a decentralized framework built around three core innovations: fast DID-based agent discovery through distributed registries enables efficient lookup across decentralized networks, while semantic agent cards with verifiable credentials and composability profiles provide rich, machine-readable descriptions of capabilities. At the heart of the system, a dynamic trust layer integrates behavioral attestations with policy compliance mechanisms to create verifiable reputation signals. The architecture introduces X42/H42 micropayments for economic coordination and MAESTRO, a comprehensive security framework incorporating Synergetics’ patented AgentTalk protocol (US 12,244,584 B1) and secure containerization. Real-world implementations demonstrate 99.9% compliance in healthcare applications and significant monthly transaction volumes while maintaining strong privacy guarantees. Our federated registry system enables efficient agent discovery while supporting high-performance autonomous systems. By unifying MIT’s trust research with production systems from Cisco’s Agency Framework and Synergetics’ commercial deployments, we demonstrate how cryptographic proofs and policy-as-code transform agents into trust-anchored participants in a decentralized economy Lakshmanan (2025); Sha (2025). The result enables a globally interoperable Internet of Agents where trust becomes the native currency of collaboration across both enterprise and Web3 ecosystems.
New in Claude Managed Agents: self-hosted sandboxes and MCP tunnels | Claude
Claude Managed Agents can now operate in a sandbox you control and connect to your private Model Context Protocol (MCP) servers
Introducing eve
Introducing eve, the open-source agent framework from Vercel for building, running, and scaling agents in production, with durable execution, sandboxed compute, approvals, channels, tracing, and evals built in.
IronClaw: Unleash Your AI Agent, With Peace of Mind
IronClaw: Unleash Your AI Agent, With Peace of Mind. The open-source secure runtime that runs AI agents in encrypted enclaves on NEAR AI Cloud.
Agent Gateway overview | Gemini Enterprise Agent Platform | Google Cloud Documentation
Secure and govern AI agent connectivity with Agent Gateway. Centralize access policies, mTLS, and Model Context Protocol (MCP) security for agent-to-agent and agent-to-tool interactions across diverse runtimes.
New capabilities for building agents on the Anthropic API | Claude
Claude now offers code execution, MCP server connections, file storage, and extended prompt caching through the API—giving developers powerful tools to build agents that analyze data, connect to external systems, and maintain context for longer periods of time.
truefoundry/trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
agentOS - Everything Agents Need to Run and Operate - Rivet
The complete platform for production AI agents. Stateful runtime, universal agent interface, and secure code execution. One SDK, one platform, deploy anywhere.
