Moda

Moda is a continual-learning and observability layer for AI agents and LLM-native software, built by ModaLabs (YC W26, San Francisco). It turns production agent traces into validated improvements to the agent harness (prompts, tools, workflows, retrieval, memory, evals) rather than the model weights. The platform ingests conversations via a lightweight SDK plus OpenTelemetry/OTLP intake, then provides intent discovery, behavioral failure detection, tool-call failure taxonomies, frustration root-cause attribution, and prompt management. Moda exposes an HTTP ingestion API, a read-only Data API for analytics, first-party Python and TypeScript SDKs, a CLI, a production MCP server, and Claude Code skills so teams and agents can query and act on their agent analytics.

Moda publishes 2 APIs on the APIs.io network. Tagged areas include Company, AI Agents, LLM Observability, Agent Analytics, and Continual Learning.

Moda’s developer surface includes documentation, API reference, getting-started guide, engineering blog, changelog, pricing, support, and 20 more developer resources.

37.0/100 thin ▬ flat Agent 34/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
2 APIs 1 MCP Servers
CompanyAI AgentsLLM ObservabilityAgent AnalyticsContinual LearningMonitoringDeveloper ToolsMCPOpenTelemetryPrompt ManagementY Combinator

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 37.0/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 16.1 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 2.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 34/100 · agent aware
Machine-Readable Contract 0 / 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/moda: 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.

Moda Ingestion API

HTTP ingestion API for sending LLM/agent conversation events to Moda. Accepts batched events (conversation_id, role, message, plus token/model/trace metadata) over a single POST...

Moda Data API

Read-only analytics API for programmatic access to Moda conversation data: overview/KPIs, conversations, world state, topic clusters, frustrations, and tool failures. Authentica...

MCP Servers 1

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

moda-mcp.yml

MCP SERVER

Security Posture 2

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

Moda Authentication

apiKey · 2 schemes

SECURITY

Moda Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 4

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 3

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: moda
name: Moda
description: Moda is a continual-learning and observability layer for AI agents and LLM-native software, built by ModaLabs
  (YC W26, San Francisco). It turns production agent traces into validated improvements to the agent harness (prompts, tools,
  workflows, retrieval, memory, evals) rather than the model weights. The platform ingests conversations via a lightweight
  SDK plus OpenTelemetry/OTLP intake, then provides intent discovery, behavioral failure detection, tool-call failure taxonomies,
  frustration root-cause attribution, and prompt management. Moda exposes an HTTP ingestion API, a read-only Data API for
  analytics, first-party Python and TypeScript SDKs, a CLI, a production MCP server, and Claude Code skills so teams and agents
  can query and act on their agent analytics.
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://avatars.githubusercontent.com/u/242691421?v=4
url: https://raw.githubusercontent.com/api-evangelist/moda/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- general-catalyst
- y-combinator
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- AI Agents
- LLM Observability
- Agent Analytics
- Continual Learning
- Monitoring
- Developer Tools
- MCP
- OpenTelemetry
- Prompt Management
- Y Combinator
apis:
- name: Moda Ingestion API
  description: HTTP ingestion API for sending LLM/agent conversation events to Moda. Accepts batched events (conversation_id,
    role, message, plus token/model/trace metadata) over a single POST endpoint, authenticated with a Bearer API key.
  humanURL: https://docs.moda.dev/ingestion/direct-api
  baseURL: https://moda-ingest.modas.workers.dev
  tags:
  - Ingestion
  - Events
  - Observability
  properties:
  - type: Documentation
    url: https://docs.moda.dev/ingestion/direct-api
  - type: Authentication
    url: authentication/moda-authentication.yml
  - type: ErrorCatalog
    url: errors/moda-problem-types.yml
- name: Moda Data API
  description: 'Read-only analytics API for programmatic access to Moda conversation data: overview/KPIs, conversations, world
    state, topic clusters, frustrations, and tool failures. Authenticated with an API key via the x-api-key header or the
    MODA_API_KEY environment variable; wrapped by the Moda CLI and MCP server.'
  humanURL: https://docs.moda.dev/data-api/overview
  baseURL: https://moda.dev
  tags:
  - Analytics
  - Data API
  - Read-only
  properties:
  - type: Documentation
    url: https://docs.moda.dev/data-api/overview
  - type: CLI
    url: cli/moda-cli.yml
  - type: MCPServer
    url: mcp/moda-mcp.yml
  - type: DataModel
    url: data-model/moda-data-model.yml
common:
- type: DomainSecurity
  url: security/moda-domain-security.yml
- type: Website
  url: https://moda.dev
- type: DeveloperPortal
  url: https://docs.moda.dev
- type: Documentation
  url: https://docs.moda.dev
- type: APIReference
  url: https://docs.moda.dev/ingestion/direct-api
- type: GettingStarted
  url: https://docs.moda.dev/quickstart
- type: Blog
  url: https://moda.dev/blog
- type: ChangeLog
  url: https://moda.dev/changelog
- type: Pricing
  url: https://moda.dev/pricing
- type: TermsOfService
  url: https://moda.dev/terms
- type: PrivacyPolicy
  url: https://moda.dev/privacy-policy
- type: Login
  url: https://moda.dev/login
- type: Support
  url: https://moda.dev/support
- type: GitHubOrganization
  url: https://github.com/ModaLabs
- type: Packages
  url: packages/moda-packages.yml
- type: SDKs
  url: packages/moda-packages.yml
- type: CLI
  url: cli/moda-cli.yml
- type: MCPServer
  url: mcp/moda-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/moda-llms.txt
- type: Authentication
  url: authentication/moda-authentication.yml
- type: Conventions
  url: conventions/moda-conventions.yml
- type: ErrorCatalog
  url: errors/moda-problem-types.yml
- type: Lifecycle
  url: lifecycle/moda-lifecycle.yml
- type: Conformance
  url: conformance/moda-conformance.yml
- type: DataModel
  url: data-model/moda-data-model.yml
- type: ChangeLog
  url: changelog/moda-changelog.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 16
  pass: local-v1