Show HN: OpenVerb – A deterministic action layer for AI agents
TL;DR
Hi HN, I’ve been working on a project called OpenVerb, which explores an architectural idea for AI systems: separating reasoning from execution. Most AI agent frameworks today focus on improving reasoning loops, planning, and orchestration (LangChain, LangGraph, etc.). But once an agent decides to perform an action, execution usually becomes a direct tool call, script, or API invocation. That approach works, but it also creates some issues:.
Key Points
- custom glue code for every integration
- inconsistent action schemas
- limited determinism in execution
- difficult auditing and policy enforcement OpenVerb experiments with treating actions as a protocol layer, not just function calls. Instead of arbitrary tool calls, systems define structured verbs that describe:
- the action being performed
Nauti's Take
OpenVerb tackles a real pain point: AI agents that reason brilliantly but execute chaotically. Separating reasoning from execution via a structured verb protocol could finally bring the auditability and consistency enterprise teams desperately need.
Whether it gains traction depends on adoption—protocols only work if everyone plays along.
Sources