Synthetic Sciences

Synthetic Sciences is a Y Combinator-backed AI research lab building foundation models for scientific discovery. Its flagship product, Atlas, is an agent-first research graph and infrastructure layer for autonomous science: durable typed nodes (hypotheses, experiment plans, recorded runs, evidence, decisions) linked into a shared, forkable map that humans and AI agents read and write directly over a REST API and the @synsci/atlas CLI. Atlas bundles a Library for indexing and grounded search over repos, docs, papers, and datasets, a cross-provider GPU compute marketplace, GEPA-based optimization and refereed autoresearch, and nine agent Skills. The lab also ships two open-source (Apache 2.0) projects: OpenScience, a model-agnostic AI workbench that runs the full research loop, and Delphi, a self-hosted MCP server that gives coding agents semantic context over code, papers, and HuggingFace datasets.

Synthetic Sciences publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Machine Learning, Scientific Research, and Developer Tools.

Synthetic Sciences’ developer surface includes documentation, API reference, getting-started guide, pricing, signup flow, support, CLI, and 17 more developer resources.

30.3/100 thin ▬ flat Agent 42/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs 1 MCP Servers
CompanyArtificial IntelligenceMachine LearningScientific ResearchDeveloper ToolsAgentsFoundation ModelsKnowledge GraphModel Context ProtocolCLIResearch Infrastructure

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 30.3/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 15.7 / 20
Commercial Clarity 4.7 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 42/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 9 / 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/synthetic-sciences: 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 1

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

Atlas REST API

The direct HTTP API behind the Atlas CLI — the research graph, Library, runs, evidence, compute, and research surfaces. Bearer (thk_*) auth; JSON responses; Idempotency-Key on w...

MCP Servers 1

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

Security Posture 2

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

Synthetic Sciences Authentication

http/oauth2 · 2 schemes

SECURITY

Synthetic Sciences Domain Security

TLSv1.3 · HSTS

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 6

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 1

Status, limits, changes, and where to get help

Commercial 1

Pricing, plans, and the legal terms of use

Company 1

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: synthetic-sciences
name: Synthetic Sciences
description: 'Synthetic Sciences is a Y Combinator-backed AI research lab building foundation models for scientific discovery.
  Its flagship product, Atlas, is an agent-first research graph and infrastructure layer for autonomous science: durable typed
  nodes (hypotheses, experiment plans, recorded runs, evidence, decisions) linked into a shared, forkable map that humans
  and AI agents read and write directly over a REST API and the @synsci/atlas CLI. Atlas bundles a Library for indexing and
  grounded search over repos, docs, papers, and datasets, a cross-provider GPU compute marketplace, GEPA-based optimization
  and refereed autoresearch, and nine agent Skills. The lab also ships two open-source (Apache 2.0) projects: OpenScience,
  a model-agnostic AI workbench that runs the full research loop, and Delphi, a self-hosted MCP server that gives coding agents
  semantic context over code, papers, and HuggingFace datasets.'
url: https://raw.githubusercontent.com/api-evangelist/synthetic-sciences/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://app.syntheticsciences.ai/synsc-logo.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
- a16z
- firestreak-ventures
- pareto-holdings
x-tier: profiled
x-tier-reason: enriched-from-public-surface
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 16
  pass: local-v1
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Artificial Intelligence
- Machine Learning
- Scientific Research
- Developer Tools
- Agents
- Foundation Models
- Knowledge Graph
- Model Context Protocol
- CLI
- Research Infrastructure
apis:
- name: Atlas REST API
  description: The direct HTTP API behind the Atlas CLI — the research graph, Library, runs, evidence, compute, and research
    surfaces. Bearer (thk_*) auth; JSON responses; Idempotency-Key on writes. Base https://app.syntheticsciences.ai/api/v1.
  humanURL: https://docs.syntheticsciences.ai/atlas/rest-api
  baseURL: https://app.syntheticsciences.ai/api/v1
  tags:
  - Research
  - Agents
  - Knowledge Graph
  properties:
  - type: Authentication
    url: authentication/synthetic-sciences-authentication.yml
  - type: Conventions
    url: conventions/synthetic-sciences-conventions.yml
  - type: ErrorCatalog
    url: errors/synthetic-sciences-problem-types.yml
  - type: DataModel
    url: data-model/synthetic-sciences-data-model.yml
common:
- type: Website
  url: https://syntheticsciences.ai
- type: DeveloperPortal
  url: https://docs.syntheticsciences.ai
- type: Documentation
  url: https://docs.syntheticsciences.ai/atlas
- type: APIReference
  url: https://docs.syntheticsciences.ai/atlas/commands
- type: GettingStarted
  url: https://docs.syntheticsciences.ai/atlas/quickstart
- type: Pricing
  url: https://docs.syntheticsciences.ai/atlas/billing
- type: SignUp
  url: https://app.syntheticsciences.ai
- type: Support
  url: mailto:team@syntheticsciences.ai
- type: GitHubOrganization
  url: https://github.com/synthetic-sciences
- type: ProductSite
  url: https://tryatlas.sh
- type: LLMsTxt
  url: llms/synthetic-sciences-llms.txt
- type: Packages
  url: packages/synthetic-sciences-packages.yml
- type: SDKs
  url: packages/synthetic-sciences-packages.yml
- type: CLI
  url: cli/synthetic-sciences-cli.yml
- type: MCPServer
  url: mcp/synthetic-sciences-mcp.yml
- type: Authentication
  url: authentication/synthetic-sciences-authentication.yml
- type: Conventions
  url: conventions/synthetic-sciences-conventions.yml
- type: Idempotency
  url: conventions/synthetic-sciences-conventions.yml
- type: ErrorCatalog
  url: errors/synthetic-sciences-problem-types.yml
- type: Lifecycle
  url: lifecycle/synthetic-sciences-lifecycle.yml
- type: DataModel
  url: data-model/synthetic-sciences-data-model.yml
- type: Conformance
  url: conformance/synthetic-sciences-conformance.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DomainSecurity
  url: security/synthetic-sciences-domain-security.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io