Windsurf (Codeium / OpenAI)
Codeium-built agentic IDE (VS Code fork); flagship was Cascade — a planning + execution agent that maintains "Flows" and "Memories" as durable artifacts. Reported acquired by OpenAI in May 2025 for ~$3B (later partly unwound — Google paid ~$2.4B for an inverse-license + key staff; the remaining IDE/IP went to Cognition in July 2025).
At a glance
- Type
- Agentic IDE — Cascade Flow + Memories (acquired by OpenAI 2025)
- Tier
- T1
- Section
- Agent IDEs & coding harnesses
- Created
- 2024-11
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- Codeium $150M Series C (2024); ~$3B reported OpenAI offer; ultimately $2.4B Google reverse-acqui-hire (2025-07)
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- cross-session
- update
- hybrid
- unit
- document
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: Cascade Flows — long-running planning + execution agent
Anti-fit: not for non-coding tasks; post-acquisition product-direction uncertainty
Pros & cons
Pros
Cascade pioneered durable Flow + Memory artifacts in an IDE; rich enterprise on-prem story (Codeium era) makes it the only major harness with first-class self-host.
Cons
Three-way acquisition saga (OpenAI / Google / Cognition) creates roadmap uncertainty; the founding team is at Google, the product at Cognition.
Claims & capabilities
Reported OpenAI acquisition ~$3B May 2025; Google reverse-acqui-hire ~$2.4B July 2025; Cognition acquired remaining IP and IDE August 2025.
Technical surface
- API surface
- Desktop IDE; CLI
- Backend storage
- local workspace + cloud session state
- Deployment
- Cloud (desktop client) + on-prem (enterprise Codeium)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- per-user; enterprise tenants isolated
- MCP
- native — Windsurf supports MCP
- 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.
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude + OpenAI + Codeium-own models
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude + OpenAI + Codeium-own models