Features
Self-hosted deployment on own infrastructure
Model-agnostic agent execution (Claude, GPT, Gemini, etc.)
Live per-step traces of tool calls, retrievals, reasoning
Replay and side-by-side comparison of agent runs
Audit-ready output with source citations
Real-time drift detection and alerts
Code Mode for up to 98% fewer tokens per run
Secure sandboxed execution for tool calls
Integration with MCP servers
Supports 50+ data types (emails, docs, spreadsheets, calls)
Open source and MIT-licensed
Air-gapped deployment support
Built on Agent-Verifiable Protocol (AVP)
Automatic model switching on provider downtime
On-prem and air-gapped deployment
OpenTelemetry-native ingestion for logs, metrics, and traces
Instant log filtering and search with OpenTelemetry context
Centralized Prometheus and OpenTelemetry metrics monitoring
Real-time distributed tracing with heatmap drilldowns
Perses-based dashboards with configuration as code
Agent0: autonomous incident investigation and fix PRs
PromQL support for queries and alerting
Kubernetes monitoring with pre-built dashboards
Google Cloud SQL monitoring (PostgreSQL, MySQL, SQL Server)
Web events on GeoMap with clustering and tooltips
Synthetic monitoring and website monitoring
Cost control via monthly budget limits and spam filters
Configuration as code for dashboards and rules
Dash0 CLI with OAuth support and OTLP proxy
Keyboard-centric navigation and filtering