Comparison · Observability
MCP-Native Agent Eval vs SDK-Instrumented Enterprise AI Observability.
TL;DR
Iris grades what an agent did with its tools — the trace, the answer, the cost — not whether an MCP server honours its own contract; a server test harness answers that question, and Iris runs beside it. For the method, see the agent eval guide.
Feature comparison
Twelve features, the same twelve on every comparison. Every Galileo cell links the page it was read from and the date. The highlighted cells are Iris's own call on which side is stronger for a team running MCP agents — 4 to Iris, 3 to Galileo — not a measurement.
| Feature | Iris | Galileo |
|---|---|---|
| Integration method | One block in the MCP config, no code — the agent discovers Iris and its tools on connect | Python/TypeScript SDK: GalileoLogger, @log decorator, wrapped OpenAI client, LangChain callback; plus OpenTelemetry.Galileo's page · read 2026-09-21 |
| Self-hosting | One process, one SQLite file; Docker image with a health check | Enterprise plan lists hosted, VPC, or on-prem deployment; Free and Pro tiers are hosted.Galileo's page · read 2026-09-21 |
| Where it runs | Nothing in the agent's process — Iris is a separate server the agent calls | In-process SDK instrumentation; SDK integrations capture prompts and responses without explicit logging code.Galileo's page · read 2026-09-21 |
| Evaluation | 21 built-in deterministic rules and 9 custom-rule types, in-process; 6 judge templates on a key you supply; every rule's precision and recall published | Out-of-the-box metrics plus custom LLM-as-a-judge or code-based metrics; Luna-2 small language models score at scale.Galileo's page · read 2026-09-21 |
| Cost tracking | Per-trace USD cost and tokens; a cost spike judged against the agent's own history | Experiment comparison shows cost per response and metric cost, plus input/output token counts and latency.Galileo's page · read 2026-09-21 |
| MCP support | Protocol-native — Iris is an MCP server with 12 tools; OTLP traces in | Ships an MCP server (api.galileo.ai/mcp/http/mcp) for IDEs: datasets, prompt templates, experiments, log-stream signals.Galileo's page · read 2026-09-21 |
| License | MIT, the whole package | Platform is proprietary (paid tiers); the galileo-python SDK on GitHub is under the Apache License 2.0.Galileo's page · read 2026-09-21 |
| Ownership | Independent and founder-led | Cisco acquisition announced 2026-04-09, completed per Splunk; as of 2026-08-07 Galileo is Splunk Agent Observability.Galileo's page · read 2026-09-21 |
| Dashboard | A local dashboard on its own port: traces, moments, regressions, five views | Web console at app.galileo.ai with projects and Log streams; a Playground runs experiments in the console.Galileo's page · read 2026-09-21 |
| Framework support | Any MCP client (1 verified, 9 claimed — see /clients); OTLP/HTTP from anything else | Integrations: OpenAI, OpenAI Agents SDK, LangChain, LangGraph, CrewAI, Google ADK, Strands, Vercel AI, Bedrock, OTel.Galileo's page · read 2026-09-21 |
| Prompt management | Not included | Prompt templates created, stored and retrieved by name via the SDK for experiments; docs advise versioning them.Galileo's page · read 2026-09-21 |
| Enterprise and compliance | Self-hosted. Nothing leaves your machine unless you set IRIS_OTEL_ENDPOINT, which exports traces to the collector you name, or enable the LLM judge with your own key. No compliance certification is claimed before it is held | SOC 2 Type II and HIPAA (BAAs) stated on its trust page; Enterprise plan lists RBAC, SSO, VPC or on-prem deployment.Galileo's page · read 2026-09-21 |
Decision guide
Every Galileo statement on this page was read from one of these pages on the date shown. The file behind this page is website/src/lib/compare/galileo.json.
Last verified: 2026-09-21. This comparison is based on publicly available documentation and may not reflect recent changes to Galileo. We aim to keep this page accurate and fair.
See something outdated or incorrect? Report an inaccuracy — we review and update within 48 hours.
Add Iris to your MCP config. First trace in 60 seconds. No SDK, no signup, no infrastructure.