Magic website screenshot

Magic

Magic (magic.dev) is a San Francisco frontier AI research lab building frontier-scale code models - an "AI coworker" for software engineering, and ultimately a path to safe AGI - rather than a shipping developer product. It has raised roughly $515M from Nat Friedman, Daniel Gross, CapitalG, Elad Gil, Sequoia, Jane Street, and Eric Schmidt, and has published research on ultra-long-context models (LTM-1 at a 5M token context window, and the unreleased LTM-2-mini research prototype claimed to handle up to 100M tokens). As of this review Magic does not publish a public, self-serve developer API, API reference, SDK, or waitlist; its website and careers pages describe mission, research, and open roles only, with no product access model, pricing, or documented endpoints. Its GitHub organization (magicproduct) hosts research tooling (e.g. hash-hop, a long-context evaluation harness) and infrastructure forks, not an API client or SDK.

Magic is profiled on the APIs.io network. Tagged areas include AI, AGI Research, Coding Agent, Long Context, and LLM.

Magic’s developer surface includes engineering blog and 7 more developer resources.

🌐 Visit website 📡 Source on GitHub
7.9/100 minimal ▬ flat Agent 0/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessApproval
0 APIs
AIAGI ResearchCoding AgentLong ContextLLMFrontier LabNo Public API

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 7.9/100 · minimal
Contract Quality 0.0 / 25
Developer Ergonomics 0.4 / 20
Commercial Clarity 0.0 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 6.8 / 10
Agent readiness — 0/100 · human only
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 0 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 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/magic-dev: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

Security Posture 2

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

Magic Dev Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Magic Dev Vulnerability Disclosure

security.txt · contact published

SECURITY

Resources

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

VulnerabilityDisclosure
VulnerabilityDisclosure
 DomainSecurity
DomainSecurity

Company 4

The organization behind the API

LinkedIn
LinkedIn
 Website
Website
 Blog
Blog
 Careers
Careers

Other 1

Properties that don't map to a standard resource type

Safety
Safety

Source (apis.yml)

apis.yml Raw ↑ 
aid: magic-dev
url: https://raw.githubusercontent.com/api-evangelist/magic-dev/refs/heads/main/apis.yml
name: Magic
kind: company
description: Magic (magic.dev) is a San Francisco frontier AI research lab building frontier-scale code models - an "AI coworker"
  for software engineering, and ultimately a path to safe AGI - rather than a shipping developer product. It has raised roughly
  $515M from Nat Friedman, Daniel Gross, CapitalG, Elad Gil, Sequoia, Jane Street, and Eric Schmidt, and has published research
  on ultra-long-context models (LTM-1 at a 5M token context window, and the unreleased LTM-2-mini research prototype claimed
  to handle up to 100M tokens). As of this review Magic does not publish a public, self-serve developer API, API reference,
  SDK, or waitlist; its website and careers pages describe mission, research, and open roles only, with no product access
  model, pricing, or documented endpoints. Its GitHub organization (magicproduct) hosts research tooling (e.g. hash-hop, a
  long-context evaluation harness) and infrastructure forks, not an API client or SDK.
accessModel:
  pricing: unknown
  onboarding: approval
  trial: false
  try_now: false
  public: false
  label: Requires approval
  confidence: medium
  source: []
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/magic-dev.png
tags:
- AI
- AGI Research
- Coding Agent
- Long Context
- LLM
- Frontier Lab
- No Public API
created: '2026-07-02'
modified: '2026-07-02'
specificationVersion: '0.19'
apis: []
common:
- type: VulnerabilityDisclosure
  url: security/magic-dev-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/magic-dev-domain-security.yml
- type: GitHubOrganization
  url: https://github.com/magicproduct
- type: LinkedIn
  url: https://www.linkedin.com/company/magicailabs
- type: Website
  url: https://magic.dev
- type: Blog
  url: https://magic.dev/blog
- type: Careers
  url: https://magic.dev/careers
- type: Safety
  url: https://magic.dev/safety
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com