Featured in OpenAI Agents SDK

AI Agent Observability, Evaluation & Policy Enforcement

Enforce, not just observe. OpenTelemetry-native tracing with runtime policy enforcement, prompt registry & evals, cost attribution, and EU AI Act evidence.

OpenTelemetry-nativeApache 2.0SOC 2 (in progress)LangChainCrewAIOpenAI Agents SDK
Agentis Control Plane

Runtime Policy Enforcer

Active · 100% Span Coverage
LangChain Agent
3 spans · $0.0034
OpenAI Agents SDK
EU Art. 50 Passed
PII Intercepted
Hard Block · 0ms Egress
OTEL Realtime Costs
100% Accurate @ 10% Sample
Interactive Terminal Console

Observe, Enforce & Audit in Real Time

Explore how Agentis provides full visibility and active runtime control across your entire AI fleet.

01 / 06

How many AI agents are running right now?

Unified Agent Registry
02 / 06

Which agent generated the most LLM cost?

Cost & Token Attribution
03 / 06

Did any agent expose customer data?

PII & Sensitive Data Detection
04 / 06

Did any agent use a restricted LLM model?

Policy Monitoring & Enforcement
05 / 06

Is this prompt better than production?

Prompt Registry & Evals
06 / 06

Can you prove compliance?

Compliance Evidence Built In
READY

$ agentis.init()

One init call — trace, cost, and govern every agent
agentis · governance console
$agentis agents list
142 agents · 3 environments
Customer SupportHEALTHY
Data PipelineDEGRADED
Code ReviewerHEALTHY
142 agents synced
Unified Visibility

One Dashboard. Every Agent.

Stop switching between LangSmith, custom Grafana dashboards, and spreadsheets. Agentis gives you a single pane of glass for all your AI agents, regardless of framework.

System Live & Healthy

Governance & Telemetry Console

Active Agents
5
+1 today
Traces / Min
42
5% trend
Errors (24h)
142
-12% vs prev
Policy Violations
23
0% flat
Token Spend
$1,250.45
+8% vs prev

Agent Registry Inventory

Live health, environment, executions & spend

5 synced
Agent NameStatusEnvironmentExecutionsCost
W
Web Researcher
HEALTHYproduction248$220.00
Z
Zendesk Copilot
DEGRADEDstaging27$12.00
S
Stripe Risk Evaluator
CRITICALdev18$100.00
D
Data Scientist GPT
HEALTHYproduction30$13.00
S
Shopify Support Bot
HEALTHYstaging20$7.00
Top Spenders (24h)
$1,250.45
Web Researcher$1,220.00
Stripe Risk Evaluator$100.00
Model Mix
GPT-4o82% volume
Claude 3.5 Sonnet18% volume
System Behavior
Retry Rate
9.2%
HIGH
Error Rate
3.4%
NORMAL
The Control Plane

Stop toggling between tools.

Everything you need to observe, evaluate, govern and control your AI agents in production.

01 / UNIFIED REGISTRY

Unified Agent Registry

One source of truth for all agents across LangChain, CrewAI, and OpenAI Agents SDK. Track version, health, environment, and ownership — zero code changes.

Agent Registry Status142 agents active
Customer Support (prod)HEALTHY
Data Pipeline (staging)DEGRADED
Code Reviewer (dev)HEALTHY
02 / DISTRIBUTED TRACING

End-to-End Tracing Waterfall

Full OpenTelemetry-native visibility into every LLM call, tool use, and agent decision.

Trace ID: 72d76daf2693SUCCESS

Execution timeline & distributed span waterfall

2.50s total
$0.0051
0ms625ms1,250ms1,875ms2,500ms
user_input_processing250ms · $0.0001
120 tokens
knowledge_base_search620ms · $0.0008
1,450 tokens (embedding)
llm_generation (gpt-4o)1450ms · $0.0038
850 in / 210 out
response_masking & pii_guard150ms · $0.0004
210 tokens
Selected Span Inspectorspan_3

Synthesized resolution response incorporating refund policy parameters.

Duration1450ms
Calculated Cost$0.0038
Tokens850 in / 210 out
Outcomesuccess
03 / RUNTIME ENFORCEMENT

Policy Monitoring & Hard Blocks

3-tier guardrail detection across explicit annotations, provider-native signals, and heuristics.

Interactive Guardrail & Policy Tester

Test how Agentis's runtime engine intercepts runaway agents and data leaks in real time

Agent Action Invocation
support_agent.reply(user_id=1024)
"Customer SSN is 123-45-6789. Refund issued."

Click "Simulate Runtime Check" to trigger the policy evaluation engine.

04 / PROMPT EVALUATIONS

Prompt Registry & Version Compare

Compare prompt wording side-by-side with latency, tokens, and benchmark pass rates before promoting.

Prompt Registry & Evals Compare

Prompt: support-reply (7 versions tracked)

+13% Accuracy Lift
v7Tighten refund policy bounds
Candidate

"You are a helpful customer agent. Enforce max refund window of 30 days without exception."

Pass Rate94%
Latency840ms
Avg Cost$0.0031
v6Add {{account_tier}} variable
Production

"You are a helpful customer support agent. Handle refund disputes with flexibility."

Pass Rate81%
Latency910ms
Avg Cost$0.0039
Dataset: 48 benchmark refund cases · 3 LLM-as-judge scorers
OpenTelemetry-Native

One SDK. Every Framework.

Drop-in tracing for LangChain, CrewAI, OpenAI Agents SDK, AutoGen, and LlamaIndex.

openai_agents_sdk_quickstart
import { Agent, Runner } from "@openai/agents";
import { agentis } from "agentis";

// Initialize Agentis automatic OpenTelemetry processor
agentis.init({
  apiKey: process.env.AGENTIS_API_KEY,
  environment: "production",
  redactPii: true
});

const supportAgent = new Agent({
  name: "Support Specialist",
  model: "gpt-4o",
  instructions: "Answer billing questions within policy limits.",
});

const result = await Runner.run(supportAgent, "Process refund for #4092");

1. Autonomous Run

Multi-agent reasoning, tool invocations, & LLM completions.

@observe() active

2. Runtime Interceptor

Passive span-end inspection & 3-tier active guardrail gates.

0ms overhead · Hard block ready

3. Immutable Evidence

Integrity-hashed audit logs for EU AI Act & HIPAA readiness.

Cryptographic SHA-256
Key Differentiators

Why Teams Choose Agentis

The only tool that enforces, not just observes

Others alert you after the fact. Agentis’s policy engine hard-blocks agents mid-execution — stopping runaway costs, infinite loops, and PII leaks before they hit production.

Guardrail detection with zero runtime overhead

A passive span processor inspects every trace as it ends. Three detection tiers — explicit, provider-native, heuristic — with no changes to your agent code and zero added latency.

Cost totals that don’t lie at 10% sampling

Sampling cuts trace volume but your costs don’t scale with it. Agentis emits OTEL metrics for every LLM call independently — token and cost totals stay 100% accurate regardless of sample rate.

One registry, not locked to one SDK

LangSmith works best if you use LangChain. Agentis is OpenTelemetry-native — works across every framework today and every one you adopt next quarter. Switch in one afternoon with pip install agentis.

Enterprise Ready

Security that enterprises trust

Built for teams that need observability, auditability, and governance at scale.

Enterprise Security

SOC 2 Type II certification in progress. Security controls designed for enterprise procurement.

PII Redaction (SDK)

Optional pattern-based masking before export via init(redact_pii=True). ML PII detection planned.

RBAC & Access Control

Granular role-based access control today. OIDC/SAML SSO on the enterprise roadmap.

Start building with Agentis today.

Choose your path to start tracing and monitoring your AI agents

Use SDK Locally

Open Source

Export traces to your own observability stack. Works with Jaeger, Grafana Tempo, Zipkin, SigNoz, and any OpenTelemetry backend.

  • No account required
  • OTLP standard export
  • Full SDK control
SDK Quickstart

Use Agentis Platform

Full Power

Access the complete Agentis dashboard with agent-first governance, cost attribution, policy guardrails, and team collaboration.

  • Policy guardrails
  • Cost attribution
  • Prompt registry & evals
Platform Quickstart