Newsletter Saturday, October 3, 2026

Daily update on the AI tools we track. Headlines come from public sources (X, GitHub, Hacker News); the Dutch commentary and summaries are machine-generated. Each headline links to our own news page on that topic; the source link is right next to it.

In brief

Claude Code & agents

• Claude Code is a mess. Until you install this. There's an official Anthropic plugin called claude-code-setup. It tells you what automations · source: X · 2026-10-02
  This official plugin package from Anthropic helps configure Claude Code and is relevant for setting up automations.
• Claude Code es un lío. Hasta que instalas esto. Hay un plugin oficial de Anthropic llamado claude-code-setup. Te dice qué automatizaciones p · source: X · 2026-09-29
  This official plugin package from Anthropic helps configure Claude Code and is relevant for setting up automations.
• Anthropic already solved this. Twice. Claude Code nests rules by folder. Claude Tag nests them by Slack channel. Projects, where most work l · source: X · 2026-10-02
  This article covers how Claude Code and Claude Tag nest rules by folder or channel, which is relevant for organizing projects.
• Claude Code Mods · source: Hacker News · 2026-10-01
  This concerns modifications for Claude Code, which may be relevant for customizing the coding assistant.

Cloudflare OS & self-hosted

• We’ve updated Kitesurf, our Workers-based browser for AI agents, with WebMCP support, improved DOM performance, and terminal-based rendering · source: X · 2026-09-28
  This update to Kitesurf adds WebMCP support, better DOM performance, and terminal rendering, relevant for Workers-based browsers.
• Cloudflare turned 16 this week 🎂 So here are 16 launches you should try first: 1. Clef + Clef-flash: open-source decision models with determ · source: X · 2026-10-02
  Cloudflare is introducing open-source decision-making models, which is relevant for developers who want to automate decision-making.
• excited to announce that @Cloudflare Artifacts is now in open beta! with Artifacts, you can give every application and agent its own repo th · source: X · 2026-10-01
  Cloudflare Artifacts provides every application and agent with its own repository, which is relevant for managing project code.
• Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic[.ai], Exa, and Linkup. Developers can now i · source: X · 2026-10-02
  Cloudflare AI Gateway now supports native web search integration, which is relevant for retrieving up-to-date web data in applications.

Agent tooling & MCP

• The AI agent era is getting very real. Hedra just made its vision models accessible directly through MCP + CLI. That means your agents can n · source: X · 2026-10-01
  Hedra is making visual models accessible via MCP and CLI, which is relevant for enabling agents to perform visual tasks.
• Microsoft APM v0.33.0 just shipped. npm for agent context, not another skill folder copy script. One apm.yml. One apm.lock.yaml. Skills, pro · source: X · 2026-10-02
  Microsoft APM manages agent context via configuration files, which is relevant for structured sharing of skills and prompts.
• Release v1.1.0: MCP tool annotations, architecture docs, wiki and security policy · source: GitHub · 2026-10-02
  This release includes MCP tool annotations and documentation, which is relevant for building with the Model Context Protocol.
• Migrating your Pine Script indicators to Indie® takes just minutes: 1. Drop your Pine Script into our built-in AI Assistant, MCP integration · source: X · 2026-09-30
  This tool migrates Pine Script indicators using an AI assistant and MCP integration, which is relevant for traders and developers.

Models & pricing

• Benchmarking AI Agent Performance: Metrics and Frameworks https://msinformationtech.blogspot.com/2026/10/benchmarking-ai-agent-performance.h · source: X · 2026-10-01
  This article discusses metrics and frameworks for benchmarking AI agents, which is relevant for measuring agent performance.
• Uncensored and Offensive Security AI Models Benchmark · source: Hacker News · 2026-09-29
  This benchmark focuses on uncensored and offensive security AI models, which is relevant for security researchers.
• Your AI agent's model changes more than its answers. It also changes the speed, the reasoning, and the AI Credits each task can consume. In · source: X · 2026-10-02
  This article discusses how model changes affect speed, reasoning capability, and costs, which is relevant for API cost management.
• So for $PODM @pod_miner I *believe* it Runs LLM inference on the https://UsePod.ai marketplace Finds the cheapest GPU boxes on https://Vast. · source: X · 2026-10-02
  This system performs LLM inference and searches for inexpensive GPUs, which is relevant for lowering AI hosting costs.

Skills & plugins

• Bear market or not, RareSkills still cooks. Over the past year, we built and refined an AI tutor that teaches Zero Knowledge Proofs interact · source: X · 2026-10-01
  RareSkills has built an interactive AI tutor for Zero Knowledge Proofs, which is relevant for technical education.
• The Technical Education and Skills Development Authority (TESDA) launched its cloud computing and artificial intelligence (AI) courses on Fr · source: X · 2026-10-02
  TESDA has launched cloud and AI courses, which is relevant for pursuing technical training.

Repos, releases & updates

• Stages of grief about the effect of AI on open source · source: Hacker News · 2026-10-02
  This item discusses the stages of acceptance regarding the impact of AI on open source, which is relevant for open-source developers.
• 10 GITHUB REPOS TO FIND OUT IF YOUR AI ACTUALLY WORKS These open-source repos help you test, evaluate and monitor AI systems: 1. DeepEval Li · source: X · 2026-10-02
  This list shows open-source repositories for testing and evaluating AI systems, which is relevant for quality control.
• GitHub is becoming ridiculous for AI agents. 10 open-source repos that can turn one strong model into a full autonomous system. 1. LangGraph · source: X · 2026-10-02
  This list shows open-source repositories to turn AI models into autonomous systems, which is relevant for agent development.
• This is where GPT-6 Astra gets absurdly powerful 10 open-source GitHub repos I'd use to build the system around the model BUILD THE AGENTS 0 · source: X · 2026-10-02
  This list shows open-source repositories for building systems around AI models, which is relevant for agent architecture.

Funding & market

• Austin-based Homeward, a startup that helps homeowners buy before selling their existing homes or get cash offers for their properties, has · source: X · 2026-10-01
  Homeward is a startup that helps home buyers, providing background information on proptech but not directly relevant to indie developers.
• AI trend-spotting meets D2C: UniqYou bags ₹15.8 Cr seed funding at a ₹64 Cr valuation from Arkam & Antler. Can algorithms predict what women · source: X · 2026-10-02
  UniqYou has raised seed funding for AI-driven trend analysis in fashion, which is relevant for e-commerce algorithms.
• Why prompt AI when it can act first? Backed by $4M, Sol scans your emails to finish promised tasks before you even ask. Read: https://buyme · source: X · 2026-10-01
  Sol scans emails to execute promised tasks, which is relevant for automating workflow steps with AI.
• This week’s list of the largest U.S. startup funding rounds was pretty much all about AI. That includes the biggest financing — a $1 billion · source: X · 2026-10-02
  This article discusses major funding rounds in the US with a focus on AI, which is relevant for market trends in the tech sector.

← October 2, 2026 · Archive