Causari vs Evaluation Context Protocol (ECP)

The first content-addressable ledger for AI agents. Every prompt, model, read, write and reasoning becomes an immutable causal event, captured at the wire, no agent...

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems.

About Causari

The first content-addressable ledger for AI agents. Every prompt, model, read, write and reasoning becomes an immutable causal event, captured at the wire, no agent cooperation required. Trace, bisect, revert and explain every line your agents wrote. re audit reads plain git history, detects AI-authored commits from verifiable metadata ( Co-Authored-By trailers, bot authors, aider markers) and measures how many of those lines are still alive at HEAD. Every number carries its evidence class: VERIFIED (explicit metadata) is never mixed with PROBABLE (heuristic).

About Evaluation Context Protocol (ECP)

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems. ECP gives evaluators a common way to inspect what an agent returned, what tools it used, and what audit evidence it exposed, independent of the framework that built the agent or the platform that runs the test. tool_calls Did the agent call the required tool with the right arguments?. ecp run --manifest Can this run in CI and fail a build?.