Agentic Index
Galileo vs Langfuse (2026)
Both vendors last verified
Choose Galileo for managed evaluation with its own low latency Luna judge models and built in guardrailing. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Choose Langfuse for open source tracing and observability you control end to end. Galileo's Pro covers 50,000 traces for $100 a month on annual billing, above a free 5,000 trace tier, and Langfuse costs nothing on Hobby, $29 monthly on Core, and nothing to self host under MIT. Galileo sells opinionated, vendor maintained metrics, and Langfuse sells an open platform you instrument and extend yourself.
On the Agentic Index agent infrastructure ranking, Galileo and Langfuse both clear the bar: each documents all five production contract capabilities in full. 33 of the 186 vendors in the lane clear it. See the agent infrastructure ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Galileo and Langfuse are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,140 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Galileo if
- Prebuilt evaluation metrics of research quality, out of the box, beat building your own
- Inline guardrailing with low latency judge models is part of the requirement
- You want failure mode detection and root cause analysis done for you
Choose Langfuse if
- Open source self hosting and data control outrank managed convenience
- Your evals are custom anyway, so you want the tracing substrate, not the judges
- The $29 a month unlimited user plan fits your budget reality
| Feature | G Galileo |
L Langfuse |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
GalileoIntegrations & Tool Calling Tracing integrations cover A2A, CrewAI, Google ADK, LangChain and LangGraph, Mastra, Microsoft Agent Framework, the OpenAI SDKs, Pydantic AI, Strands and the Vercel AI SDK, and Galileo connects model providers for its metrics. These bring telemetry in. There are no connectors that let an agent take authenticated actions in outside systems. SourceGalileo, docs.galileo.ai/what-is-galileo and galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseIntegrations & Tool Calling More than 100 integrations with agent frameworks, model providers and gateways send traces into Langfuse, data exports to PostHog, Mixpanel and blob storage, and prompt changes send notices through webhooks and Slack. These move telemetry in and data out, and there are no connectors that let an agent take authenticated actions in outside systems. SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
GalileoWorkflow Orchestration Agents that run elsewhere are what Galileo observes, evaluates and guards. There are no workflows that sequence, branch or retry an agent's steps. SourceGalileo, galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseWorkflow Orchestration For agents that run elsewhere, Langfuse provides tracing, evaluation and prompt management, and prompt composability links prompts together. There are no workflows that sequence, branch or retry an agent's steps, or that mix deterministic nodes with agent steps. SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
GalileoTriggers & Channel Coverage Luna-2 models evaluate all production traffic as it arrives, log stream metrics score incoming traces, Signals detect failures proactively, and real-time monitoring raises alerts, so Galileo's evaluation work starts from incoming telemetry with no person initiating each run. SourceGalileo, galileo.ai llms.txt and homepage, and docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfuseTriggers & Channel Coverage Online evaluation runs LLM as a judge and code evaluators on production observations as they arrive, and monitors and alerts fire on metric and evaluator thresholds. Evaluation work therefore starts from incoming telemetry with no person starting each run, and prompt changes also emit webhooks. SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
GalileoKnowledge Grounding & RAG Galileo evaluates the grounding of RAG systems built elsewhere with context adherence and RAG metrics. It has no retrieval structure over the customer's knowledge that grounds an agent's answers. SourceGalileo, galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseKnowledge Grounding & RAG Traces, prompts and evaluation datasets are stored, but there is no retrieval structure over the customer's documents or knowledge that grounds an agent's answers. Langfuse evaluates the grounding of RAG systems built elsewhere instead of providing one. SourceLangfuse, langfuse.com pricing and llms.txtread 2026-09-21 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
GalileoMemory & State Persistence Traces, sessions and datasets are kept for observability and evaluation, but there is no session, conversation or long-term memory that an agent reads back as context. SourceGalileo, docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfuseMemory & State Persistence Sessions, users and traces are recorded for inspection, and there is no session, conversation or long term memory that an agent reads back as context. SourceLangfuse, langfuse.com pricing and homepageread 2026-09-21 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
GalileoHuman Oversight & Guardrails Evaluations become production guardrails through Agent Control, which applies inline runtime protection to agent requests and responses, while Luna-2 models run the checks at low latency across all traffic. Together they apply structured guardrails and policy constraints at run time. SourceGalileo, galileo.ai llms.txt and homepage, and docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfuseHuman Oversight & Guardrails Protected deployment labels restrict who can promote a prompt version to production, and CI checks can require an approved baseline before a change ships, so changes to an agent's behavior pass a release gate that people control. There is no approval step, escalation rule or pause before an agent acts at run time. SourceLangfuse, langfuse.com pricing and llms.txtread 2026-09-21 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
GalileoSecurity, Identity & Governance Galileo reports SOC 2 Type 2 certification, and its plans include project access control, with standard RBAC on Pro and RBAC with SSO integration on Enterprise. SourceGalileo, galileo.ai llms.txt and pricing, and docs.galileo.ai/what-is-galileo (Security section)read 2026-09-21 |
||
|
LangfuseSecurity, Identity & Governance Reports for the SOC 2 Type II and ISO 27001 attestations are available from the Pro plan, and there is a region ready for HIPAA and a GDPR DPA. Access control covers RBAC at organization and project level, sign in with Google, Azure AD or GitHub, Enterprise SSO with Okta or Entra ID and SSO enforcement on the Teams add-on, SCIM provisioning, audit logs, data masking on the client side and data retention management. SourceLangfuse, langfuse.com pricing and homepageread 2026-09-21 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
GalileoObservability & Auditability Every agent step is captured in end to end traces, with agent graph visualization, sessions and distributed tracing over OpenTelemetry. Real time monitoring raises alerts, Signals detect failure patterns automatically, and the SDKs carry a logger, decorators and context helpers. Together that shows step by step what the agent did. SourceGalileo, galileo.ai llms.txt and docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfuseObservability & Auditability Hierarchical traces capture every LLM call, tool invocation and retrieval step of an agent run, so each run's steps and tool calls are visible. They appear as trace trees and agent graphs with session and user tracking, token cost and latency, and can be filtered by user, session, cost, latency or metadata. Audit logs are kept separately on Enterprise, data can be exported in batches or on a schedule to blob storage and to PostHog or Mixpanel, and historical data access runs 30 days on Hobby, 90 days on Core and 3 years on Pro. SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
GalileoDeployment & Data Residency On the Enterprise plan, Galileo deploys hosted, in the customer's VPC or on premises. SaaS, on-premises and in-VPC deployment are all offered. SourceGalileo, galileo.ai pricing and llms.txtread 2026-09-21 |
||
|
LangfuseDeployment & Data Residency Customers of Langfuse Cloud choose US, EU or JP data regions, and there is a region ready for HIPAA and AWS PrivateLink. The MIT licensed platform self hosts with Docker Compose, Kubernetes via Helm, or Terraform on AWS, GCP and Azure, with paid Enterprise additions for self hosted deployments. SourceLangfuse, langfuse.com pricing, homepage and llms.txtread 2026-09-21 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
GalileoPrebuilt Agents, Templates & Packs One AI Assistant inside the app, in beta, ships with sample projects to start from, alongside Galileo's evaluator library. There is no set of prebuilt agents or templates for a customer to select from. SourceGalileo, docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfusePrebuilt Agents, Templates & Packs The Langfuse Assistant in the app is the one prebuilt agent, and a Langfuse skill packages best practice workflows for instrumentation, prompt management and API access into a customer's coding agent. Beyond those two, there is no set of prebuilt agents or templates for a customer to choose from. SourceLangfuse, langfuse.com llms.txt and pricingread 2026-09-21 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
GalileoModel Flexibility & Routing Model integrations connect the customer's LLM providers, with costs per model, and Galileo's LLM-as-a-judge metrics and playground experiments run on them beside its own Luna-2 models. The customer chooses the models behind Galileo's own evaluation features. SourceGalileo, docs.galileo.ai/what-is-galileo and galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseModel Flexibility & Routing Customers configure their own LLM connections, which the Playground uses to test prompts on real production inputs and compare models side by side, and which power the LLM-as-a-judge evaluators the customer sets up. The customer brings its own providers and chooses the models Langfuse's own LLM features run on. SourceLangfuse, langfuse.com homepage, pricing and llms.txt (LLM Connections)read 2026-09-21 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
GalileoAPIs, SDKs & MCP Extensibility Galileo offers a Python SDK, a TypeScript SDK, a REST API with a reference covering authentication and endpoints, and a Galileo MCP server for AI-enabled IDEs such as Cursor and VS Code. SourceGalileo, docs.galileo.ai/what-is-galileo and galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseAPIs, SDKs & MCP Extensibility An extensive public API has published rate limits by plan, alongside native Python and TypeScript SDKs, OpenTelemetry ingestion for Java, Go and other languages, a CLI, and a platform MCP server that lets IDE agents manage prompts and query traces. Stable APIs based on IDs manage evaluators, and there is an agent skill. SourceLangfuse, langfuse.com homepage, pricing and llms.txtread 2026-09-21 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
GalileoTesting, Debugging & Optimization Galileo ships more than 20 out-of-the-box evals for RAG, agents, safety and security plus custom evaluators, LLM-as-a-judge metrics tuned from live feedback with Autotune and distilled into Luna-2 models that score all production traffic, and experiments run in code, playgrounds or unit tests against datasets with side-by-side comparison and annotations. That tests the customer's agent before production and scores quality over time. SourceGalileo, galileo.ai homepage and docs.galileo.ai/what-is-galileoread 2026-09-21 |
||
|
LangfuseTesting, Debugging & Optimization Evaluation of the customer's application runs online and offline. It covers datasets, experiments from the SDK or UI compared side by side against baselines, LLM as a judge and code evaluators managed by API, custom scores, user feedback and human annotation queues, alerts on evaluator results, and CI checks that block regressions against thresholds and approved baselines. The customer's agent is tested with datasets before production, and output quality is scored over time. SourceLangfuse, langfuse.com llms.txt, homepage and pricingread 2026-09-21 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
GalileoBrowser & Computer Use There is no browser, desktop or computer control by an agent. Galileo observes, evaluates and guards agents. SourceGalileo, galileo.ai llms.txtread 2026-09-21 |
||
|
LangfuseBrowser & Computer Use Langfuse observes and evaluates agents, and there is no browser, desktop or computer control by an agent. SourceLangfuse, langfuse.com homepageread 2026-09-21 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | G Galileo |
L Langfuse |
|---|---|---|
|
Entry price Lowest public entry point |
From $100/mo billed yearly · free tier | Free Hobby (50K units/mo) · Core $29/mo · open source self host |
|
Pricing confidence How public the numbers are |
Public, exact | Public, exact |
|
Billing Primary billing axis |
Monthly traces within subscription tiers; Pro pricing scales with trace volume | usage |
|
Variable cost Workload / overage exposure |
Medium variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
Free tier
|
|
Buying motion Self-serve vs sales call |
Self-serve | Self-serve |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Galileo
-
· Observability / auditability
Decision model metrics in Galileo classify and score large volumes of text much faster and at far lower cost than metrics that use an LLM as the judge.
Source -
· Observability / auditability
Galileo, now sold as Splunk Agent Observability, released Luna-3, the third generation of its own evaluation models, for enterprise users in the us0, us1, eu0 and au0 realms.
Source -
· Funding / partnership
Galileo has officially transitioned to become Splunk Agent Observability.
Source
Langfuse
-
· Deployment / data residency
FIPS mode is now available in self hosted Government deployments of Langfuse from v4.71.0.
Source -
· Security / enterprise
Project API keys in Langfuse can now be created with a permission level: Full access, Viewer, Ingestion (create traces, scores and media only) or Scores ingestion.
Source -
· MCP / tool calling / API
Langfuse introduced stable, ID-based public APIs for managing LLM-as-a-Judge and code evaluators.
Source
Cisco owns Galileo, whose product took the Splunk Agent Observability name on 7 August 2026 while galileo.ai keeps selling Galileo plans. Langfuse joined ClickHouse in January 2026 and remains MIT licensed.
More comparisons with Galileo or Langfuse
Other matchups in agent infrastructure platforms
Not the pairing you were after? These compare a different set of agent infrastructure platforms on the same 14 capabilities.