Skip to content

Project

Windsurf

Windsurf is an AI-powered coding assistant and IDE that integrates large language models into software development workflows, competing with tools like Cursor.

Known aliases

  • Windsurf Editor

Current stories

buildOne report1 publisher

n8n opens workflow building to Claude Code, Cursor and other agent hosts over MCP

n8n has opened its MCP tools to agent hosts including Claude Code, Codex and Cursor, so their agents can build and edit workflows from inside the coding tool. The workflows still run in n8n, so each host a team connects is one more place that can change a live automation.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+8
Incentives60
Confidence30
buildOne report1 publisher

One MCP server needs a generated config file for every desktop client it serves

Cursor, Claude Desktop, Windsurf, OpenClaw and Hermes each expect a different JSON config for the same MCP server, according to a dev.to guide. Its fix generates each file from code and adds two server-side shims for requests a config file cannot correct.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+20
Incentives70
Confidence45
productConfirmed3 publishers

Teams standardized on Cursor have until November 12, 2026 to prove a fallback works

OpenAI has served SpaceX notice on its Cursor contract with a proposed Nov. 12, 2026 shutoff, which leaves anyone who standardized on Cursor with a dated job of naming the models each workflow needs and their substitutes.

Perspective Coverage

3 publishers
Builder
Builder 35%
Operator
Operator 28%
Investor
Investor 37%

Reality

Evidence68
Adoption20
Hype gap+20
Incentives75
Confidence65
buildConfirmed8 publishers

OpenAI's Cursor cutoff reclassifies model access as a supply-chain dependency

OpenAI plans to end Cursor's direct access to its models on November 12, citing doubts that SpaceX will stay inside its terms of service. Whether developers can still bring their own OpenAI keys remains unclear.

Perspective Coverage

8 publishers
Builder
Builder 39%
Operator
Operator 31%
Investor
Investor 30%

Reality

Evidence74
Adoption35
Hype gap+30
Incentives72
Confidence68
buildOne report1 publisher

GitHub lost 3,800 internal repos to code running with its editor's permissions

A dev.to writeup traces roughly 3,800 exfiltrated GitHub repositories to one trojanised Nx Console install from the official Marketplace, where the sandbox that would have contained it has been an open feature request since 2018.

Publishers:dev.to

Reality

Evidence42
Adoption28
Hype gap+18
Incentives62
Confidence45
buildOne report1 publisher

A docs audit splits agent memory into four capabilities the five coding tools answer differently

Vendor pages for Claude Code, Cursor, Codex, VS Code and Windsurf, re-checked on 2026-09-12, show that all five resume a previous session. The complaint about agents forgetting points at the other three questions.

Publishers:dev.to

Reality

Evidence80
Adoption
Not scored
Hype gap+10
Incentives45
Confidence68
productOne report1 publisher

Salesforce exposes its platform to coding agents through more than 60 new MCP tools

Headless 360 makes capabilities that used to sit behind the Salesforce console callable as APIs, MCP tools and CLI commands, and more than 60 of the new tools point coding agents such as Claude Code and Cursor at live orgs.

Publishers:salesforce.com

Reality

Evidence28
Adoption26
Hype gap+42
Incentives92
Confidence55
productOne report1 publisher

Investors repriced Cognition at $48bn without touching the revenue multiple they paid in May

The Series E takes company-reported run-rate from $492M to close to $900M in four months, but nothing in the announcement says how much of that is Devin agent work and how much is Windsurf editor seats.

Publishers:siliconangle.com

Reality

Evidence38
Adoption55
Hype gap+22
Incentives74
Confidence46
investOne report1 publisher

Cognition's $48bn price keeps the same 53x run-rate multiple it carried in May

The Series E doubled the valuation while run-rate revenue rose 83% to nearly $900m, so the price per dollar of revenue barely moved, which leaves the undisclosed gross margin under an $800m compute burn as the open question.

Reality

Evidence38
Adoption60
Hype gap+26
Incentives82
Confidence52
productOne report1 publisher

OpenAI drops a customer it projected at $1B a year rather than serve SpaceX-owned Cursor

OpenAI says it cannot be confident SpaceX will honour its terms, so one of its largest customers loses access. For anyone reselling model capacity, that puts an ownership-change risk in the stack no clause covers.

Publishers:wired.com

Reality

Evidence52
Adoption44
Hype gap+16
Incentives83
Confidence55
buildOne report1 publisher

Cognition's $47bn ask prices Devin at about 94 times its own run rate

The round is still under negotiation, but the multiple it implies will outlast the negotiation. That multiple is the figure every seller of coding agents will get measured against the next time procurement asks why the seat price moved.

Publishers:runtimewire.com

Reality

Evidence34
Adoption54
Hype gap+37
Incentives71
Confidence44
buildOne report1 publisher

A code graph caught the login bug sitting three hops and an event bus from the diff

Swapping similarity search for a dependency graph took one engineer's review context from 150,000 tokens to 18,000. The saving is file count, not compression, so it holds only where the change sits in a sparse corner of the tree.

Publishers:dev.to

Reality

Evidence24
Adoption30
Hype gap+35
Incentives
Not scored
Confidence28
productOne report1 publisher

Wu says Cognition is not for sale. The more useful fact is who bought Cursor last week.

A denial of a Bloomberg report on SpaceX buying Cognition leaves the compute relationship unaddressed, and leaves buyers choosing coding tools from a shrinking independent field.

Publishers:techcrunch.com

Reality

Evidence32
Adoption44
Hype gap+34
Incentives76
Confidence37
scienceOne report1 publisher

OX Security says MCP command execution is a design choice, so server owners own the risk

The vendor reports 10-plus CVEs and up to 200,000 exposed instances, and says Anthropic declined to change the protocol, describing the behaviour as expected.

Publishers:ox.security

Reality

Evidence32
Adoption34
Hype gap+46
Incentives86
Confidence33
buildOne report1 publisher

One MCP command, three JSON shapes, and a failure mode that never errors

PDF4me's guide wires the same server into five clients using three structurally different config blocks. Get the shape wrong and no client raises an error.

Publishers:dev.to

Reality

Evidence46
Adoption
Not scored
Hype gap+8
Incentives68
Confidence44