News
Execution engine without an IDE: tickets from the dashboard to any repo
You write a ticket in the boostN dashboard and it runs on the right repository — no IDE needed. Multiple repos, in parallel, in seconds.
KI-Werkzeuge
Tools, Editoren und Runtimes für die Arbeit mit Künstlicher Intelligenz.
News
Google Gemini is now available as an agent in boostN — Mistral is next
Google Gemini is now live as an agent in boostN — work with your Google subscription through our execution pipeline. Mistral is coming next.
News
The Ralph Loop Goes Mainstream in 2026 — and Brings a Token-Burn Problem
Autonomous coding agents in an endless loop: what Ralph Loop and Loop Engineering really are — and why the bill explodes without hard stops.
News
Uber burned its 2026 AI budget in four months — and now caps Claude Code
Uber spent its full 2026 AI coding budget in four months. Its fix: $1,500 per employee, per month, per tool.
News
Cursor: Composer 2.5 and the new Auto-Review run mode
Cursor ships Composer 2.5 (May 18) and the Auto-Review run mode (May 29, 2026): more speed with fewer approval prompts — sandbox and allowlist as guardrails.
News
Microsoft Builds Its Own AI Models — and Wants Off OpenAI
At Build 2026, Microsoft unveils seven in-house MAI models. MAI-Code-1-Flash runs right inside GitHub Copilot — cheaper than GPT-5.5.
Blog
Saving Tokens with Claude: 6 Principles That Make Experts Twice as Fast
How I turned my CLAUDE.md from a style guide into a token budget — 6 principles for lower cost, less waiting, and more honest reporting.
Blog
Controllable Remote Coding Sessions: One Level Above the IDE
The session URL had suddenly vanished from the terminal. How we found it again via a server endpoint — and why it enables working above the IDE.
Blog
When whisper.cpp Swallows the Start of a Sentence — and the Glossary Is to Blame
Our speech recognition kept chopping off half the sentence up front. The culprit wasn't the mic — it was the keyword glossary itself. Proven by an A/B test.
Blog
Why AI Models Find Different Code Problems
Three frontier models, the same 1000-line script, three different finding lists — and why that very spread makes multi-orchestration strong.
Blog
The AI does whatever it wants — and no CLAUDE.md, no memory, no rule on earth will stop it
You write rules, curate memories, build guidelines — and a week later you're going in circles again. Why that is, and what actually helps.
Blog
Finally solved: two hours of testing to get the headless Antigravity CLI right
With agy headless, --model is silently ignored if it comes after -p. The undocumented fix: --model must come before -p.
AI Coding Tools Compared LangGraph Agent Frameworks at a Glance Google Antigravity The Hugging Face Ecosystem Running LLMs locally — hardware, tools, models Microsoft Agent Framework Pipeline Frameworks — LangChain, LlamaIndex and when you actually need them Self-Hosted Agent Stack (n8n, Dify, Ollama) Vector Databases Compared Microsoft Project Polaris
Accelerate Aider Auto-Classifier AutoGen Chroma Claude Code Continue.dev CrewAI Cursor Diffusers DSPy Flowise GitHub Copilot GPT4All Haystack Datasets (HF) Spaces (Hugging Face Spaces) Hugging Face Hugging Face Hub Jan LangChain LangGraph llama.cpp Llamafile LlamaIndex LM Studio Make (Integromat) Milvus Ollama Open WebUI Permission Mode pgvector Pinecone Qdrant TensorRT-LLM Text-Generation-WebUI TGI (Text Generation Inference) Transformers (Library) vLLM Weaviate whisper.cpp Windsurf Zapier AI
Evergreen Content
Evergreen Pillar Article
Anthropic Claude Code — what it is and how it works
Claude Code is Anthropic's official AI coding tool. How it's built, what it does, and how tool use, MCP and permissions fit together.
Deep-Dive Articles (3)
- 1 Claude Code and MCP servers: how external tools get integrated
How the Model Context Protocol connects Claude Code to databases, APIs and custom tools — and what to watch out for on permissions.
- 2 Claude Code auto-classifier: the security layer between model and tools
How the auto-classifier in Claude Code scores tool calls live, blocks risky actions, and which defense layers sit behind it.
- 3 Claude Code: the features every user should know
The most important features in Claude Code — from slash commands and hooks to plan mode, sub-agents and MCP integration.
Evergreen Pillar Article
AI Guardrails That Actually Hold: Why Rules Alone Are Not Enough
Memories, CLAUDE.md, and slash commands are suggestions — not commands. What it really takes to make AI models stop reliably on critical actions.