An open protocol for governing actions between AI systems
iLang is an MIT-licensed communication and governance protocol for AI agents. It carries intent, authority, completion criteria, evidence, and an action score between systems so actions can be checked before and after execution.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 4 November 2026.
Is this your tool? Claim this listing to manage your content and analytics.
Ask about iLang
Get answers based on iLang's actual documentation
Try asking:
About
iLang is a developer-oriented protocol for defining how AI systems exchange and govern actions. Rather than being an agent platform itself, it provides a shared grammar for passing intent, authority, evidence, and a definition of done between AIs....
iLang is best understood as a governance and interoperability layer, not a standalone autonomous agent. It does not browse, operate software, or complete workflows by itself; an agent or model still needs tools and an execution environment. Its most...
Executes tasks you assign, one step at a time, within narrow domains.
Dimension Breakdown
Categories
Ask about iLang
Try asking:
- Free / open source — full functionality available at no cost.
When iLang changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.