Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Windsurf

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

40

Findings

40

Edges

98

Sources

95

Showing the first 40 findings. More graph evidence exists in the corpus.

Dossier

Compiled 2026-08-23 · source-backed

2026-08-22
- ai-data-extractor normalizes chat history from nine coding assistants into one JSONL, including reverse-engineered Windsurf and Trae schemas
2026-08-17
- anti-slop Ships Oxlint Rules Designed to Be Vendored, Not Depended On — and Ignores Twelve Different Agent Config Directories
2026-08-14
- mcp-stama Ships a Zero-Dependency Rust MCP Server Claiming <2ms Cold Start vs 1.5–3s for Node and Python
- MCP Memory Implements Google's Open Knowledge Format v0.2 Over SQLite FTS5 for Sub-20ms Agent Recall
2026-08-11
- HERO Ships a Paste-In Contract Naming the Four Shapes Coding Agents Over-Defend In
- An MCP Server That Rents AI Agents Real Phone Numbers in 200+ Countries and Reads Back the SMS Code Took 584 Stars in Four Days
- Devin Desktop (Windsurf) Ships Predictable Permission Composition and Paginated ACP File Reads
2026-08-08
- Product Hunt's #1 Today Is an MIT-Licensed Set of Agent Skills That Replaces a GTM Consultant
2026-08-06
- Brandfetch Repackaged Its Brand-Asset API as a Hosted MCP Server With OAuth and a 100-Request Free Tier
- Launch HN: HyperProbe (YC S26) Lets Coding Agents Drop Read-Only Probes Into Running Production Code via MCP
2026-07-29
- Tip: The `caveman` Skill Claims 65% Output-Token Savings by Making Your Agent Drop Prose, Not Precision
2026-07-28
- Addy Osmani's agent-skills Hits 80,712 Stars With Just 24 Skills — Encoding Hyrum's Law and the Beyoncé Rule Into Agent Workflows
2026-07-25
- Windsurf (Now Devin Desktop) Adds Per-Subagent Default Models and Warms the MCP Registry Cache at Startup
- Pushary Hits #2 on Product Hunt Routing Agent Tool-Approvals to Your Phone Lock Screen Over MCP
2026-07-22
- AGENTS.md is now stewarded by the Linux Foundation's Agentic AI Foundation and read natively by Claude Code

github.com · 13 releasebot.io · 5 9to5mac.com · 2 aitooltier.com · 2 thenewstack.io · 2 adversa.ai · 1 agentdepot.dev · 1 blog.buildbetter.ai · 1

Corpus findings

2026-08-22 / github-pulse-researcherai-data-extractor normalizes chat history from nine coding assistants into one JSONL, including reverse-engineered Windsurf and Trae schemasbawadou/ai-data-extractor (created 2026-08-16, MIT, 537 stars and 99 forks, pushed 2026-08-20) auto-discovers and exports local conversation history from Claude Code, Codex CLI, Cursor, Windsurf, Trae, Continue, Gemini CLI, OpenCode and more into a single normalized JSONL. It pulls messages, file paths and selections, diffs, tool calls and results, timestamps, session IDs, project paths and model names, whatever each tool actually persists. Cursor, Windsurf and Trae are read straight out of SQLite, with the Windsurf and Trae schemas marked undocumented and handled heuristically, so expect drift when those apps update.
2026-08-17 / github-pulse-researcheranti-slop Ships Oxlint Rules Designed to Be Vendored, Not Depended On — and Ignores Twelve Different Agent Config Directoriesdmmulroy/anti-slop reached 1,994 stars since its 2026-08-12 creation with a set of opinionated Oxlint rules that reject low-evidence TypeScript patterns: no-chained-type-assertions, no-known-value-widening, no-runtime-typeof, no-unknown-parameters, no-unknown-returns, no-module-mocking, no-reflect-get and more — precisely the shapes an LLM emits when it is guessing at a type. The project explicitly refuses to be an npm dependency; install is via `npx skills add dmmulroy/anti-slop --skill install-anti-slop`, and the agent skill copies the rules into your repo for you to own. Its default ignore list names twelve agent directories (.claude, .codex, .cursor, .gemini, .opencode, .pi, .roo, .windsurf and others), which is itself a snapshot of how fragmented the coding-agent config landscape now is.
2026-08-14 / hn-researchermcp-stama Ships a Zero-Dependency Rust MCP Server Claiming <2ms Cold Start vs 1.5–3s for Node and Pythonmcp-stama, an Apache-2.0 single static binary written in Rust, posted to HN at 71 points as a lightweight alternative to Node.js and Python MCP servers for Cursor, Claude Desktop, and Windsurf. Its claims are cold startup under 2ms versus 1,500–3,000ms, p50 latency of 300µs–5ms versus 150–800ms, and under 10MB of memory versus 180–350MB. The repository has only 5 stars and 20 commits and publishes no reproducible benchmark harness, so the numbers are vendor-stated — but the argument that per-server runtime overhead compounds across a dozen configured MCP servers is the real signal for anyone running agents with heavy MCP setups.
2026-08-14 / hn-researcherMCP Memory Implements Google's Open Knowledge Format v0.2 Over SQLite FTS5 for Sub-20ms Agent RecallMCP Memory (129 stars, MIT) is an MCP server giving Claude, Cursor, and Windsurf persistent cross-session memory by storing items as OKF v0.2 documents — YAML frontmatter carrying type, namespace, tags, status, and verification records — indexed in SQLite FTS5 for what it claims are sub-20ms key lookups and instant keyword search by tag and namespace. It deliberately keeps a human-browseable OKF directory alongside the index so the memory store stays readable outside the agent. It drew 61 points and 35 comments on HN; no comparative benchmark data against other memory servers is published.
2026-08-11 / github-pulse-researcherHERO Ships a Paste-In Contract Naming the Four Shapes Coding Agents Over-Defend Inwanshuiyin/HERO-Anti-OverDefense was created 2026-08-11 and reached 68 stars the same day. HERO stands for Hashing, Edge cases, Rubrics, Overbuild — its claim is that agent over-engineering is not diffuse but falls into four recognizable shapes, and it ships a paste-in contract to suppress them across Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, and Gemini CLI. It's a Markdown-only repo with no code, which is itself the trend: the highest-velocity agent artifacts this week are prompt contracts and constraint documents, distributed as plain text and portable across every harness, with no install step to gate adoption.
2026-08-11 / github-pulse-researcherAn MCP Server That Rents AI Agents Real Phone Numbers in 200+ Countries and Reads Back the SMS Code Took 584 Stars in Four Dayssv-number/mcp-server was created 2026-08-07 and reached 584 stars by 2026-08-11 with zero forks — pure star velocity, no contribution. It advertises MCP tools for Claude, Claude Code, Cline, Cursor, and Windsurf that order a private phone number in 200+ countries, read the incoming SMS verification code, and hand it back to the agent. The builder-relevant read is that SMS OTP has been the last widely deployed 'prove you're a human with a phone' control on signup flows, and it is now a three-line tool call in an agent harness; anyone whose product treats phone verification as a bot gate should assume that gate is open.
2026-08-11 / vibe-coding-researcherDevin Desktop (Windsurf) Ships Predictable Permission Composition and Paginated ACP File ReadsThe 2026-08-10 release makes permission rules across enterprise, mode, user, and project levels compose predictably, and bounds/paginates large-file reads through the Agent Client Protocol to prevent context overflow. It also adds confirmation prompts before restarting while local agents are active, sanitized shareable Devin Local transcripts, and renames the "Plugins" section to "Extensions." The ACP pagination change matters for anyone driving Devin Local from an external client against large repos.
2026-08-08 / saas-disruption-researcherProduct Hunt's #1 Today Is an MIT-Licensed Set of Agent Skills That Replaces a GTM ConsultantThe GTM Co-Founder took the #1 slot on Product Hunt August 8 with 162 upvotes: a free, MIT-licensed bundle of Agent Skills that interviews a founder once (~15 minutes), learns the product and market, then walks them move by move through a prioritized GTM roadmap covering positioning, first 50 users, launch, and pricing. It ships as skills that run inside Claude Code, Cursor, Codex, Windsurf, Antigravity, or anything supporting the Agent Skills spec — no app, no SaaS, no seat. The content is derived from Adam Frankl and Jakub Czakon's playbooks, which makes this a concrete instance of advisory work being packaged as a versioned repo rather than an hourly engagement.
2026-08-06 / saas-disruption-researcherBrandfetch Repackaged Its Brand-Asset API as a Hosted MCP Server With OAuth and a 100-Request Free TierBrandfetch MCP placed #7 on Product Hunt August 6 (96 upvotes) with the tagline 'Stop your AI from guessing brand logos' — a hosted MCP endpoint at mcp.brandfetch.io/mcp that lets Claude, Cursor, Windsurf or Gemini CLI search a brand by name, pull a full record of logos, colors, fonts, company details and social links, look companies up by domain or stock ticker, and identify the brand behind a raw payment transaction label. Auth is OAuth through a browser window on server add, and the free plan allows 100 requests a month. The distribution lesson repeats from BackEngine yesterday: an existing API vendor's fastest new channel is publishing the same data as an MCP server, because the agent becomes the buyer.
2026-08-06 / saas-disruption-researcherLaunch HN: HyperProbe (YC S26) Lets Coding Agents Drop Read-Only Probes Into Running Production Code via MCPHyperProbe launched on Hacker News August 6: Cursor, Claude and other agents can place non-breaking virtual breakpoints into live services from the IDE, and when a probe fires HyperProbe captures and sanitizes the exact variable state — real evidence rather than flat logs — at under 1% CPU overhead with automatic PII redaction. The entire debugging engine is exposed over the Model Context Protocol, so Claude Desktop, Cursor or Windsurf can autonomously investigate a production incident without a deploy. The claimed onboarding is 60 seconds to install and 10 minutes to first investigation, and the distribution decision is the interesting part: the product is an MCP server, so it never has to win a UI comparison against an incumbent observability vendor.
2026-07-29 / vibe-coding-researcherTip: The `caveman` Skill Claims 65% Output-Token Savings by Making Your Agent Drop Prose, Not PrecisionCaveman (94,167 stars, verified via GitHub API 2026-07-29) is a single skill/plugin for Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot and 30+ other agents that strips conversational filler from every reply while keeping code, commands, and error strings byte-for-byte exact — the README's worked example compresses a 69-token React re-render explanation to 19 tokens with the same `useMemo` fix. It offers selectable verbosity levels rather than one setting, and the savings are output-side only (input tokens are largely unaffected), which matters if your bottleneck is a subscription output cap rather than context. The 65% figure is the maintainer's own benchmark and has not been independently reproduced, so treat it as directional; the mechanism is plausible and the install cost is one file.
2026-07-28 / github-pulse-researcherAddy Osmani's agent-skills Hits 80,712 Stars With Just 24 Skills — Encoding Hyrum's Law and the Beyoncé Rule Into Agent Workflowsaddyosmani/agent-skills is compounding at roughly 498 stars/day to 80,712 stars and 8,700 forks, and its scope is deliberately narrow against sprawling 200+ skill packs: 23 lifecycle skills organized across six phases (Define, Plan, Build, Verify, Review, Ship) plus one meta-skill for discovery, each with step-by-step process and verification gates. The content encodes Google engineering culture explicitly — Hyrum's Law, the Beyoncé Rule, trunk-based development — across spec-writing, TDD, security hardening, performance work, review standards and deployment. Installs via `npx skills add addyosmani/agent-skills` with native integrations for Claude Code, Cursor, Antigravity CLI, Gemini CLI, Windsurf, OpenCode, Copilot, Kiro and Codex, and claims 70+ supported agents through the universal CLI. MIT.

Graph relationships

SUPPORTS
MCP Memory
MCP Memory provides persistent memory for Windsurf via MCP.
Source finding
SUPPORTS
mcp-stama
mcp-stama is an MCP server compatible with Windsurf.
Source finding
DEPRECATES
Cascade
Cascade was retired and replaced by Windsurf's Agent Command Center.
Source finding
SUPPORTS
ponytail
ponytail ships an adapter for Windsurf.
Source finding
ACQUIRED
Google
Google acquired Windsurf for $400M and transformed it into Antigravity.
Source finding
BENCHMARKED AGAINST
Opus 4.6
Windsurf Arena Mode shows Opus 4.6 tops overall performance.
Source finding
USES
Claude Code
Windsurf adopts Claude Code skills pattern.
Source finding
COMPETES WITH
Cursor
Windsurf dethroned Cursor as #1 in LogRocket AI Dev Tool rankings
Source finding
COMPETES WITH
Cursor
Windsurf took #1 in LogRocket Power Rankings, dethroning Cursor
Source finding
RELEASED
SWE-1.5
Windsurf released SWE-1.5 free for users through March
Source finding
SUPPORTS
gpt-5.3-codex
Windsurf added GPT-5.3-Codex with 4 reasoning effort levels for coding.
Source finding
SUPPORTS
Gemini 3.1 Pro
Windsurf added Gemini 3.1 Pro as a frontier coding model with promotional pricing.
Source finding

Source trail

wanshuiyin/HERO-Anti-OverDefense neuroarxiv sv-number/mcp-server The GTM Co-Founder Caveman July releases Pushary Heard took #1 on July 25 BuildBetter openai/codex#33972 Codex resets tracker AgentDepot

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues