Agent-net, the team building an agent-to-agent marketplace where AI agents discover, trust, and pay each other, has released Webagent, an open source harness for standing up public-facing business agents. The premise is straightforward: give it your website, get an agent, and let it talk to other agents. Instead of writing orchestration code, a business fills in a declarative JSON spec, picks one provider for each of nine pluggable slots, and runs webagent serve.
Is it deployable? Yes, with caveats. The repo ships under Apache 2.0, builds green, and runs live Slack, WhatsApp, and HTTP agents backed by MCP tools today. It is still labeled v0, and the browser action provider, OAuth-gated MCP, OTel export, and the AgentNet identity and billing layer are listed as not yet built.
Slots, Providers, Picks
Webagent is written in Go. An agent is one Brain (an LLM plus instruction) over a set of slots defined in core/. Each slot is a Service Provider Interface with a registry of providers in spi/ and a designated default:
| Slot | Built-in providers | Default |
|---|---|---|
| Retrieval | live, keyword, hybrid | live |
| Memory | session | session |
| Guardrail | basic, off | basic |
| Channel | a2a, web, slack, whatsapp (telegram stub) | a2a |
| Secrets | env, file, static | env |
| Presenter | text, terminal (QR), web | text |
| Model | echo, openrouter, gateway | echo |
| Action | none, demo, mcp | none |
| Observability | none, log, memory | none |
The design serves three audiences on one contract: businesses that configure by picking from the menu, businesses that extend by registering a custom provider, and partner companies that ship adapters. Nobody forks the core. Every provider must pass its slot's conformance suite to be certified.
Safety Is Code-Enforced, Not Prompt-Enforced
The most important architectural decision is action.Guard. Rather than relying on prompt instructions to constrain behavior, Webagent enforces safety at the code level, ensuring that agent actions remain within defined boundaries regardless of what the underlying LLM decides to do. This matters more than ever in 2026, as enterprise adoption of autonomous agents accelerates and the cost of a single unguarded tool call continues to rise.
via MarkTechPost