Sentrial

Sentrial is an observability platform for AI agents, backed by Y Combinator. It tracks every agent session, tool call, and LLM interaction, then automatically detects issues, diagnoses root causes, and helps teams fix them in code. Developers instrument agents with the Sentrial Python or TypeScript SDK (one-line integrations for LangChain, CrewAI, AutoGen, Mastra, the Vercel AI SDK, and the Claude Agent SDK), by sending OpenTelemetry traces, or by calling the REST ingestion API (https://api.sentrial.com) directly to create sessions and record events. A `sentrial` CLI ships with the SDK for local setup, scriptable session/event inspection, diagnosis, and CI regression gates.

Sentrial publishes 2 APIs on the APIs.io network: Events API and Sessions API. Tagged areas include Company, AI Agents, Observability, Monitoring, and LLM.

Sentrial’s developer surface includes authentication, documentation, API reference, getting-started guide, engineering blog, signup flow, CLI, and 16 more developer resources.

🌐 Visit website 📡 Source on GitHub
46.2/100 developing ▬ flat Agent 51/100 agent ready Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
2 APIs 1 MCP Servers
CompanyAI AgentsObservabilityMonitoringLLMDeveloper ToolsTracing

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 46.2/100 · developing
Contract Quality 15.9 / 25
Developer Ergonomics 13.5 / 20
Commercial Clarity 6.8 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 51/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/sentrial: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 2

Individual APIs this provider publishes, each with its own machine-readable definition.

Sentrial Events API

Track events within agent sessions.

Sentrial Sessions API

Create and manage agent sessions.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

sentrial-mcp.yml

MCP SERVER

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Sentrial Authentication

http · 1 scheme

SECURITY

Sentrial Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 DataModel
DataModel
 Conformance
Conformance
 Lifecycle
Lifecycle

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
CLI

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 Authentication
Authentication

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 1

The organization behind the API

Blog
Blog

Other 1

Properties that don't map to a standard resource type

Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: sentrial
name: Sentrial
description: Sentrial is an observability platform for AI agents, backed by Y Combinator. It tracks every agent session, tool
  call, and LLM interaction, then automatically detects issues, diagnoses root causes, and helps teams fix them in code. Developers
  instrument agents with the Sentrial Python or TypeScript SDK (one-line integrations for LangChain, CrewAI, AutoGen, Mastra,
  the Vercel AI SDK, and the Claude Agent SDK), by sending OpenTelemetry traces, or by calling the REST ingestion API (https://api.sentrial.com)
  directly to create sessions and record events. A `sentrial` CLI ships with the SDK for local setup, scriptable session/event
  inspection, diagnosis, and CI regression gates.
url: https://raw.githubusercontent.com/api-evangelist/sentrial/refs/heads/main/apis.yml
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://www.sentrial.com/og-image.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: enriched
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- AI Agents
- Observability
- Monitoring
- LLM
- Developer Tools
- Tracing
apis:
- aid: sentrial:sentrial-events-api
  name: Sentrial Events API
  description: Track events within agent sessions.
  humanURL: https://www.sentrial.com/docs
  baseURL: https://api.sentrial.com
  tags:
  - Events
  properties:
  - type: OpenAPI
    url: openapi/sentrial-events-api-openapi.yml
  - type: Documentation
    url: https://www.sentrial.com/docs
  - type: APIReference
    url: https://www.sentrial.com/docs/api/sessions
  - type: GettingStarted
    url: https://www.sentrial.com/docs/quickstart
  - type: Authentication
    url: authentication/sentrial-authentication.yml
- aid: sentrial:sentrial-sessions-api
  name: Sentrial Sessions API
  description: Create and manage agent sessions.
  humanURL: https://www.sentrial.com/docs
  baseURL: https://api.sentrial.com
  tags:
  - Sessions
  properties:
  - type: OpenAPI
    url: openapi/sentrial-sessions-api-openapi.yml
  - type: Documentation
    url: https://www.sentrial.com/docs
  - type: APIReference
    url: https://www.sentrial.com/docs/api/sessions
  - type: GettingStarted
    url: https://www.sentrial.com/docs/quickstart
  - type: Authentication
    url: authentication/sentrial-authentication.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/sentrial-domain-security.yml
- type: Authentication
  url: authentication/sentrial-authentication.yml
- type: Documentation
  url: https://www.sentrial.com/docs
- type: APIReference
  url: https://www.sentrial.com/docs/api/sessions
- type: GettingStarted
  url: https://www.sentrial.com/docs/quickstart
- type: Blog
  url: https://www.sentrial.com/blog
- type: SignUp
  url: https://sentrial.com/signup
- type: TermsOfService
  url: https://www.sentrial.com/terms
- type: PrivacyPolicy
  url: https://www.sentrial.com/privacy
- type: GitHubOrganization
  url: https://github.com/sentrialdev
- type: Packages
  url: packages/sentrial-packages.yml
- type: SDKs
  url: packages/sentrial-packages.yml
- type: CLI
  url: cli/sentrial-cli.yml
- type: Conventions
  url: conventions/sentrial-conventions.yml
- type: ErrorCatalog
  url: errors/sentrial-error-codes.yml
- type: DataModel
  url: data-model/sentrial-data-model.yml
- type: Conformance
  url: conformance/sentrial-conformance.yml
- type: Lifecycle
  url: lifecycle/sentrial-lifecycle.yml
- type: Overlay
  url: overlays/sentrial-openapi-overlay.yaml
- type: MCPServer
  url: mcp/sentrial-mcp.yml
- type: LLMsTxt
  url: llms/sentrial-llms.txt
- type: AgentSkill
  url: skills/sentrial-track-agent-session.md
- type: AgentSkill
  url: skills/sentrial-record-tool-call.md
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 17
  pass: local-v1