Magic.dev
AI-coding startup focused on extremely long-context models (claimed 100M tokens) and a frontier coding agent. Raised $320M Series B from Eric Schmidt, CapitalG, Atlassian Aug 2024. Lower public-product surface than peers — mostly known for the model claims and the funding round.
At a glance
- Type
- Coding-agent startup; ultra-long-context model + agent
- Tier
- T2
- Section
- Agent IDEs & coding harnesses
- Created
- 2022
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- searched not found
- Funding
- $465M total $1.5-1.6B val Series B 2024-08 (CapitalG, Atlassian, Eric Schmidt, Nat Friedman)
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- agent-controlled
- unit
- token
- governance
- opaque
- conflict
- no
When to use
Optimised for: ultra-long-context (100M-token) coding agent
Anti-fit: private beta — limited access; product surface is mostly model-based, not IDE-based
Pros & cons
Pros
Most-funded startup in the category outside Cognition/Anysphere; ultra-long-context model claim is uniquely positioned.
Cons
Largely unreleased product through 2025; product surface is opaque vs the public-launched competition.
Claims & capabilities
Eric Schmidt-backed; $465M total raised at ~$1.6B val (Aug 2024); claims 100M-token context window (LTM-2-Mini).
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Cloud (private beta)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- Bedrock AgentCore (AWS) T2
AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).
- Claude Code (Anthropic) T1
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.
- GitHub Copilot (Agent Mode) T1
The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.
- Aider (harness) T2
OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.
- Amazon Q Developer T1
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.