Built for the agents, not the developer: a governance layer from Microsoft and an agent-only language from Vercel

The Lens

Agent Governance Toolkit puts a policy check between your AI agent and every action it takes. Tool calls, resource access, and agent-to-agent messages all get evaluated against rules you write before anything runs. The distinction that matters: this is application-layer enforcement, not prompt instructions asking a model to behave, so a jailbreak in the conversation does not talk its way past it. MIT, maintained by Microsoft, free. It is framework-agnostic on purpose, with adapters for LangChain, CrewAI, AutoGen, AWS Bedrock, Google ADK, and Azure AI among others, plus SDKs for Python, TypeScript, Rust, Go, and .NET. You get a CLI, a governance dashboard, and published specs mapped against the OWASP Agentic Top 10. Installation is a package manager command; the actual work is writing policy that reflects what your agents should be allowed to do, which nobody can do for you. Someone shipping a weekend agent can skip this. Anyone putting an autonomous agent in front of production systems or customer data needs this or an equivalent, and there is no free-versus-paid decision to make because Microsoft ships the whole thing MIT with no commercial gate. The catch is scope, and it is narrower than the marketing suggests. This governs what an agent does, not what a model says, so prompt injection that produces a bad answer rather than a bad action passes straight through and you still need a content safety layer beside it. It is also public preview, with breaking changes expected before GA.

The Lens

HTML Anything is a desktop editor that takes Markdown, CSV, or notes and asks your existing coding agent (Claude Code, Cursor, Codex, Gemini, others) to render them as styled HTML: keynote decks, magazine articles, resumes, posters, social cards. Apache 2.0. Reuses whatever agent sessions you're already logged into, so the marginal cost is zero. Self-hosted by design. There's no cloud tier. Run it locally, it scans your PATH for installed agent CLIs, you pick one and a template. The 75 templates ship as SKILL files (Anthropic's skill format) and produce single-file HTML you can paste into WeChat, Zhihu, X, or just download as PNG. Setup is install dependencies, run pnpm dev. For anyone who already pays for Claude Code, Cursor, or similar and wants polished HTML output without sending more tokens through paid APIs: this is the angle. For people without an agent CLI installed: skip it, the value disappears. It's downstream of someone else's project (nexu-io/open-design) and the README leans hard on showcase shots. The template library is the actual product. If the templates don't fit your output, you're writing your own SKILL files in custom HTML and CSS, which is the work the tool claims to spare you.

The Lens

N8n is the open source alternative to Zapier. It gives you a visual workflow builder where you drag nodes, connect them, and watch data flow through. Over 400 integrations built in. Self-hosting is free under a 'sustainable use' license (not fully open source, you can't resell it as a service). The cloud version starts at $24/mo. The self-hosted version has no feature restrictions, no execution limits, and no user limits. The catch: setting up n8n in Docker and keeping it running takes real skill. Updates can break workflows. The 'sustainable use' license means you can't build a competing automation platform on top of it. And while the visual builder is powerful, complex logic (loops, error handling, conditional branches) gets messy in a node graph. Sometimes a Python script is cleaner than 40 connected nodes.

The Lens

zerolang is an experimental programming language built for AI agents, not people. The idea: give an agent a language whose compiler speaks back in clean, structured JSON, so the agent can check syntax, trace dependencies, and get repair suggestions without parsing human-readable error spew. It comes from Vercel Labs, Apache-licensed and free. Everything about it is tuned for machines: token-efficient syntax, fast startup, low memory, zero dependencies. The compiler exposes stable inspection commands with predictable output contracts, which is exactly what an autonomous coding loop needs to work reliably instead of guessing. The catch is right there in the README: this is pre-1.0, security holes are expected, and it's explicitly not for production, sensitive data, or trusted infrastructure. It's a research bet on what agent-native tooling could look like, not something to build a product on yet. Worth watching if you work on autonomous code generation. Skip it if you need anything stable.