amai-tari is an open-source library that enables behavioral tracing and conduct scoring for AI agents. It provides local, private observability without exposing content, helping developers monitor agent actions and ensure responsible AI behavior. Designed for AI developers and researchers, it integrates with tools like OpenTelemetry and supports MCP.
In the LLM eval & observability space, amai-tari takes a focused approach. It focuses on understanding and monitoring the behavior of AI agents without exposing content, ensuring privacy and security. It is built as an open-source project for AI developers and researchers. amai-tari is open source under the Apache-2.0 license. amai-tari is available on the command line and API, and it can be self-hosted.
amai-tari first shipped in 2026. Key capabilities include behavioral tracing, conduct scoring, and local observability. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
Other apps tracked under the same category.
