Adaptive ML

Adaptive ML builds Adaptive Engine, an enterprise platform for developing, evaluating, and serving specialized open-source large language models via reinforcement-learning post-training. The three-phase workflow (Adapt, Evaluate, Serve) lets teams fine-tune smaller models to outperform commercial APIs, measure them with custom AI judges and graders, and feed production signals back into training. Adaptive Engine is self-hosted (Kubernetes/Helm) and exposes an OpenAI-compatible REST API for chat completions and embeddings, plus interactions, comparisons, outcomes, dataset/recipe management, and chunked uploads. Tooling includes the Python adaptive-sdk and adaptive-harmony libraries and the adpt CLI. Adaptive ML was acquired by Datadog.

Adaptive ML publishes 1 API on the APIs.io network: Adaptive Engine API. Tagged areas include Company, Ai Ml, LLM, Fine-Tuning, and Reinforcement Learning.

The Adaptive ML catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Adaptive ML’s developer surface includes documentation, API reference, getting-started guide, engineering blog, signup flow, support, authentication, and 21 more developer resources.

🌐 Visit website 📡 Source on GitHub
43.3/100 thin Agent 75/100 agent native Full breakdown ↓
scored 2026-07-20 · rubric v0.4
1 APIs 1 MCP Servers 0 Features
CompanyAi MlLLMFine-TuningReinforcement LearningModel EvaluationInferenceOpenAI-CompatibleMLOps

API Rating

API Evangelist API Evangelist Rating How this is scored →
scored 2026-07-20 · rubric v0.4
Composite quality — 43.3/100 · thin
Contract Quality 9.4 / 25
Developer Ergonomics 16.1 / 20
Commercial Clarity 4.7 / 20
Operational Transparency 3.8 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 75/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 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 6 / 6
Agent Skills 5 / 5
Well-Known Catalog 4 / 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/adaptive-ml: 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

Adaptive Engine API

OpenAI-compatible REST API (concorde) for inference (chat completions, embeddings), interaction/comparison/outcome logging, dataset and recipe download, and chunked file upload ...

MCP Servers

adaptive-ml-mcp.yml

MCP SERVER

Event Specifications

Adaptive Ml Webhooks

ASYNCAPI

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 WellKnown
WellKnown
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill
 AgenticAccess
AgenticAccess

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Lifecycle
Lifecycle
 Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Conformance
Conformance
 DataModel
DataModel
 Webhooks
Webhooks

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

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support
Support
 ChangeLog
ChangeLog

Commercial 1

Pricing, plans, and the legal terms of use

PrivacyPolicy
PrivacyPolicy

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Other 1

Properties that don't map to a standard resource type

Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: adaptive-ml
name: Adaptive ML
description: Adaptive ML builds Adaptive Engine, an enterprise platform for developing, evaluating, and serving specialized
  open-source large language models via reinforcement-learning post-training. The three-phase workflow (Adapt, Evaluate, Serve)
  lets teams fine-tune smaller models to outperform commercial APIs, measure them with custom AI judges and graders, and feed
  production signals back into training. Adaptive Engine is self-hosted (Kubernetes/Helm) and exposes an OpenAI-compatible
  REST API for chat completions and embeddings, plus interactions, comparisons, outcomes, dataset/recipe management, and chunked
  uploads. Tooling includes the Python adaptive-sdk and adaptive-harmony libraries and the adpt CLI. Adaptive ML was acquired
  by Datadog.
url: https://raw.githubusercontent.com/api-evangelist/adaptive-ml/refs/heads/main/apis.yml
x-type: company
x-source: index-ventures-portfolio
x-tier: profile
x-tier-reason: enriched-from-public-developer-surface
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-17'
image: https://www.adaptive-ml.com/favicon.ico
tags:
- Company
- Ai Ml
- LLM
- Fine-Tuning
- Reinforcement Learning
- Model Evaluation
- Inference
- OpenAI-Compatible
- MLOps
apis:
- name: Adaptive Engine API
  description: OpenAI-compatible REST API (concorde) for inference (chat completions, embeddings), interaction/comparison/outcome
    logging, dataset and recipe download, and chunked file upload on a self-hosted Adaptive Engine deployment.
  humanURL: https://docs.adaptive-ml.com/v0.14/reference/api
  baseURL: https://your-adaptive-deployment/api/v1
  tags:
  - Inference
  - Embeddings
  - LLM
  properties:
  - type: OpenAPI
    url: openapi/adaptive-ml-openapi-original.json
  - type: Documentation
    url: https://docs.adaptive-ml.com/v0.14/reference/api
  - type: Authentication
    url: authentication/adaptive-ml-authentication.yml
  - type: Overlay
    url: overlays/adaptive-ml-openapi-overlay.yaml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://www.adaptive-ml.com
- type: DeveloperPortal
  url: https://docs.adaptive-ml.com
- type: Documentation
  url: https://docs.adaptive-ml.com/v0.14/introduction
- type: APIReference
  url: https://docs.adaptive-ml.com/v0.14/reference/api
- type: GettingStarted
  url: https://docs.adaptive-ml.com/quickstart
- type: Blog
  url: https://www.adaptive-ml.com/blog
- type: SignUp
  url: https://www.adaptive-ml.com/book-a-demo
- type: Support
  url: https://www.adaptive-ml.com/contact-us
- type: PrivacyPolicy
  url: https://www.adaptive-ml.com/privacy
- type: GitHubOrganization
  url: https://github.com/adaptive-ml
- type: Authentication
  url: authentication/adaptive-ml-authentication.yml
- type: Packages
  url: packages/adaptive-ml-packages.yml
- type: SDKs
  url: packages/adaptive-ml-packages.yml
- type: CLI
  url: cli/adaptive-ml-cli.yml
- type: ChangeLog
  url: changelog/adaptive-ml-changelog.yml
- type: Lifecycle
  url: lifecycle/adaptive-ml-lifecycle.yml
- type: Conventions
  url: conventions/adaptive-ml-conventions.yml
- type: ErrorCatalog
  url: errors/adaptive-ml-problem-types.yml
- type: Conformance
  url: conformance/adaptive-ml-conformance.yml
- type: DataModel
  url: data-model/adaptive-ml-data-model.yml
- type: MCPServer
  url: mcp/adaptive-ml-mcp.yml
- type: WellKnown
  url: well-known/adaptive-ml-well-known.yml
- type: LLMsTxt
  url: llms/adaptive-ml-llms.txt
- type: Overlay
  url: overlays/adaptive-ml-openapi-overlay.yaml
- type: AgentSkill
  url: skills/_index.yml
- type: AgenticAccess
  url: agentic-access/adaptive-ml-agentic-access.yml
- type: Webhooks
  url: asyncapi/adaptive-ml-webhooks.yml
- type: DomainSecurity
  url: security/adaptive-ml-domain-security.yml