MIT-licensed monitoring platform for AI agents that records each program execution as a session and visualises a waterfall of LLM calls, action events, tool calls and errors, with prompt and completion inspection, event-type breakdowns, timings and LLM spend tracking. Self-hostable; no documented access control or retention.
hybrid · generally available · Research snapshot 2026-09-06
Show me the session waterfall for one agent execution, including tool calls, errors and the exact prompt and completion for a chosen LLM call.
Capabilities and evidence
Support labels reflect the supplied research. Documentation and vendor claims are not independent product tests. “Not established” means the researcher did not find support; it does not prove a capability is absent.
Documented by provider
Each execution of the program is recorded as a session, with a Session Waterfall visualising LLM calls, action events, tool calls and errors, drilldowns showing total execution time and exact prompt and completion for a given LLM call, plus event-type breakdowns and custom traces via a decorator.
Limit: Multi-agent handoffs, datasets, human feedback and evaluations are not documented on the introduction page.
The repository states the AgentOps app is open source under the MIT license and that the full app including dashboard and API backend can be run on the customer's own cloud, with integrations listed for the OpenAI Agents SDK, CrewAI and AG2/AutoGen and spend tracking for foundation-model providers.
Limit: OpenTelemetry support, RBAC, SSO, audit logs, retention and compliance are not stated; the latest listed release predates 2026.