StartupSan Francisco, CA · Est. 2021
Galileo
Evaluation platform for LLMs and agentic systems.
Acquired.
Galileo (makers of the Luna evaluation models) scores agent runs for hallucination, tool-use errors and task completion — automated quality gates for harness engineering. Cisco acquired Galileo in April 2026 and folded it into Splunk's agent observability; the old rungalileo.io domain has lapsed.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsSplunk positions Galileo's Luna-2 small evaluator models as low-cost, low-latency judges, so every production request can be evaluated instead of a sample.[1]
- DocsEvaluation, tracing of multi-step agent and RAG workflows, and runtime checks for hallucination and prompt injection come in one product.[1][2]
- DocsCisco has completed the acquisition and the product is now Splunk Agent Observability, so Splunk customers can buy it under an existing enterprise vendor relationship.[1]
- DocsAgent Control, its governance control plane, was released under Apache 2.0 in March 2026, so teams can inspect that layer themselves.[1]
Cons
- Metadatagalileo.ai/pricing now redirects to Splunk's pricing page, and Splunk's acquisition page says nothing about existing Galileo contracts, accounts or support.[1][2]
- DocsGalileo reports its own efficiency figures (for example, Luna being about 97% cheaper than GPT-4-based judging), and the Luna evaluator models are proprietary.[1]
- DocsA comparison by competitor Openlayer rates Galileo's drift detection as limited, its modality support as text-only, compliance mapping as manual and governance as project-level only.[1]
- Best for
- Enterprises already using Splunk or Cisco observability that want agent evals and runtime guardrails from a vendor they already have.
- Watch out for
- Pricing and packaging are being folded into Splunk, so get contract continuity in writing before you commit.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Co-founder & CTO
Evals & benchmarks
Co-founder & CEO
Evals & benchmarks
Co-founder & COO
Evals & benchmarks
On X
No posts from them in our X feed yet.
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
San Francisco, CA · Est. 2023
Enterprise-grade evals, data and AI gateway.
Braintrust turns prompts and agent traces into testable datasets and CI, plus an inference gateway — helping teams measure whether harness changes actually improve agent quality.
Berkeley, CA · Est. 2020
Observability and evaluation for AI — makers of OSS Phoenix.
Arize traces and evaluates LLM and agent systems in production; their open-source Phoenix tracer is a common instrumentation choice for agent harnesses that need to be debuggable.
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Similar entries · 1
- Patronus AIStartup
Sources
Verified Nov 16, 2026