Designing, evaluating, and shipping autonomous AI agents.
7589 posts
Passkey-backed SSH for humans and AI agents
Gives agents Android + iOS devices. Screen in, pruned snapshot out. Replaces Appium, Espresso, XCUITest. Zero deps, zero wasted tokens.
Turn Claude Code into an interactive scientific workspace: workflow, file system, and knowledge graph.
Extensible MCP module for Magento2 - Interact with your store through any MCP-compatible AI agent
Integrate penetration testing tools and payloads into your workflow through the Model Context Protocol using STDIO or HTTP.
Lightweight typed knowledge-graph memory for AI agents. Document ingestion + LLM-extracted entities/relations with hybrid recall. Zero exter...
Runtime artifact existence & freshness verification for AI agent completion claims — a lightweight, zero-LLM MCP gate that source-binds 'don...
Secure local AI agent runtime — vault-backed secrets, sandboxed execution, cryptographic audit chain, procedural skill system
IDE-agnostic deep-research framework for AI agents: maps a topic wide, commits to depth on purpose, adversarially verifies its findings, and...
Capture browser and server logs in one correlated place - and let your AI agent read them over MCP
A marketing world model for merchants — make marketing data findable, understandable, and usable for AI, agents, and MCP apps.
A Deception Security Layer for MCP Servers. It injects "ghost tools" (fake security-sensitive tools) that act as honeypots.
