AI tool comparison
Goose vs Windsurf Wave 11: Cascade Agent with Multi-File Edits and Memory
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Developer Tools
Goose
The open-source AI agent that actually runs your code
25%
Panel ship
—
Community
Paid
Entry
Goose is an open-source, locally-running AI agent built by Block (the company behind Square and Cash App) that goes far beyond code autocomplete. It autonomously installs dependencies, writes and executes code, edits files, runs tests, and manages workflows—all from your machine. Unlike cloud-hosted coding agents, Goose runs entirely local and works with any LLM: OpenAI, Anthropic, Gemini, or your own self-hosted model. The v1.29.0 release (March 31, 2026) adds orchestration support, Gemini-ACP provider integration, tool filtering by MCP metadata visibility, and desktop UI management for sub-agent recipes. It also includes Sigstore/SLSA provenance verification for self-updates and CVE patch for a tar vulnerability—rare signals of production-grade security hygiene in an open-source agent. With 37,000+ GitHub stars and 126 releases, Goose is among the most starred agent projects on GitHub. Its MCP server integration means it plugs into the same ecosystem as Claude, Cursor, and Windsurf—making it a credible self-hosted alternative to Codex or Claude Code for teams that want to own their stack.
Developer Tools
Windsurf Wave 11: Cascade Agent with Multi-File Edits and Memory
Cascade agent gets persistent memory and smarter multi-file edits
75%
Panel ship
—
Community
Free
Entry
Windsurf Wave 11 upgrades the Cascade agent with persistent memory across sessions and enhanced multi-file editing, so context from previous work carries forward without manual re-prompting. The release also claims improved SWE-bench scores and faster code generation throughput. It sits inside the Windsurf IDE, competing directly with Cursor and GitHub Copilot Workspace for the AI-native coding assistant market.
Reviewer scorecard
“Block's engineering pedigree shows here. This isn't a weekend side project—126 releases in, with SLSA provenance, MCP integration, and multi-LLM support baked in. The local execution model is genuinely compelling for anyone worried about sending proprietary code to Anthropic or OpenAI.”
“The primitive here is a stateful, context-aware coding agent that persists a memory graph across sessions — not just a chat window with long context, but an actual representation of your codebase decisions that survives the conversation ending. The DX bet is that memory should be automatic and inferred, not explicit annotation, which is the right call because asking developers to maintain a second brain is dead on arrival. The first-10-minutes test passes: you open a project, Cascade pulls prior context without a prompt, and multi-file edits land with actual coherence across the dependency graph rather than just find-and-replace across files. The honest caveat is that the SWE-bench improvement claim is cited without a reproducible methodology link on the blog post — I'm not scoring that until I see the eval harness. Ship for the memory primitive specifically; the multi-file editing is table stakes at this point but the persistent context is not.”
“Every agentic coding tool claims to 'run your code autonomously'—the failure modes are where they differ. Without sandboxing, an agent that executes arbitrary shell commands on your machine is a footgun waiting to go off. The CVE patch in the latest release suggests they're still catching basic security issues at 37k stars.”
“Direct competitors are Cursor with its .cursorrules and recent memory features, and GitHub Copilot Workspace, both of which have shipped or are shipping analogous capabilities. The specific scenario where Wave 11 breaks is large monorepos with complex build systems — persistent memory trained on a Django service will hallucinate confidently when you switch to the Rust microservice in the same repo, and there's no clear signal that the memory scope is properly bounded. The SWE-bench score improvement cited in the blog is a self-reported number without an external eval link, which I'm discounting to zero until verified. What kills this in 12 months: OpenAI or Anthropic ships native long-context project memory at the API level, and Windsurf's differentiation evaporates unless they've built something on top of the model layer that isn't just a vector store of your commits. Ship narrowly — the execution is ahead of Copilot Workspace on UX, but Cursor is closer than the marketing implies.”
“The MCP integration is the sleeper feature. Once there are 500 well-maintained MCP servers covering every dev tool, database, and API—Goose becomes the OS-level agent runtime that replaces your entire toolchain. Block's financial infrastructure background also hints at where this goes: autonomous agents managing money flows.”
“The thesis here is falsifiable: within 24 months, the dominant developer productivity primitive will not be the individual prompt or the code completion but the persistent agent that accumulates project-specific knowledge the way a senior engineer does — and whoever owns that memory layer owns the developer workflow. The dependency for this bet to pay off is that LLM context windows don't simply grow large enough to make explicit memory graphs unnecessary, which is a real risk given the trajectory of Gemini and Claude context sizes. The second-order effect that matters: if Cascade's memory works, it starts to encode architectural decisions and team conventions in a queryable artifact, which shifts code review and onboarding in ways that are not obviously about 'faster coding.' Windsurf is on-time to this trend, not early — Cursor has been iterating on similar primitives and the race is close. The future state where this is infrastructure is an IDE that functions as institutional memory for engineering teams; ship because they're building toward that, not just toward faster autocomplete.”
“If you're not comfortable reading Rust error logs and configuring LLM API keys, Goose will frustrate you. The dual desktop/CLI interface helps, but the onboarding still assumes you know what MCP is. Not a 'just works' tool for non-engineers—yet.”
“The buyer is an individual developer or an engineering team lead with a tooling budget, and the check size at $15-40/mo per seat is modest enough that it competes on pure product merit with no enterprise moat. The pricing architecture is fine for PLG but the expand story is weak — memory and multi-file edits are table stakes features, not expansion triggers that drive seat growth or upsell to a higher tier. The moat problem is existential: Codeium built its differentiation on a free model for individuals, but Wave 11's memory feature is exactly what Microsoft will ship into VS Code Copilot the moment it's proven to retain developers, and at Microsoft's distribution scale that's a one-move kill. The business survives only if they convert the memory layer into a team-level knowledge product with genuine lock-in — shared memory, enforced conventions, audit logs — before the platform players catch up. Until I see that expand motion priced and shipped, this is a strong product on a weak business chassis.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.