# Github > Markdown twin of https://roboterminal.app/companies/github · https://roboterminal.app/companies/github.md ## On shared sources - [Anthropic](https://roboterminal.app/companies/anthropic) (5) - [OpenAI](https://roboterminal.app/companies/openai) (5) - [Cursor](https://roboterminal.app/companies/cursor) (3) - [DeepSeek](https://roboterminal.app/companies/deepseek) (2) - [Aider](https://roboterminal.app/companies/aider) (1) - [Alibaba](https://roboterminal.app/companies/alibaba) (1) - [Alibaba Group](https://roboterminal.app/companies/alibaba-group) (1) - [Amazon](https://roboterminal.app/companies/amazon) (1) - [Apple](https://roboterminal.app/companies/apple) (1) - [Asus](https://roboterminal.app/companies/asus) (1) - [Augment Code](https://roboterminal.app/companies/augment-code) (1) - [AWS](https://roboterminal.app/companies/aws) (1) - [Browser Use](https://roboterminal.app/companies/browser-use) (1) - [Claude Code](https://roboterminal.app/companies/claude-code) (1) - [Cloudflare](https://roboterminal.app/companies/cloudflare) (1) - [Cognition](https://roboterminal.app/companies/cognition) (1) - [Dell](https://roboterminal.app/companies/dell) (1) - [Felicis](https://roboterminal.app/companies/felicis) (1) - [Google](https://roboterminal.app/companies/google) (1) - [Goose](https://roboterminal.app/companies/goose) (1) - [Microsoft](https://roboterminal.app/companies/microsoft) (1) - [NVIDIA](https://roboterminal.app/companies/nvidia) (1) - [SpaceX](https://roboterminal.app/companies/spacex) (1) - [Vercel](https://roboterminal.app/companies/vercel) (1) - [Warp](https://roboterminal.app/companies/warp) (1) - [xAI](https://roboterminal.app/companies/xai) (1) ## Pulse - [@stretchcloud on X](https://x.com/stretchcloud/status/2107998158508917177) $2,599 buys a Windows laptop that Microsoft says renders AI images 4.3 times faster than a 16 inch MacBook Pro on M5 Pro. The marketing is aimed squarely at Apple. The architecture underneath is aimed… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101853928107520008) The gain came from the harness, not the model. That line from https://t.co/VlWgutdPl7's research roundup today sums up where agentic engineering is right now: 41.2% to 91.8% success on long-horizon ro… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101456302279119022) Cache hit rates are the new benchmark. DeepSeek Harness is hitting 99% cache hit rates in production. The mechanism: KV cache prefix caching combined with append-only sessions. When you architect sess… - [@stretchcloud on X](https://x.com/stretchcloud/status/2099716085658325426) DeepSeek just shipped deepseek-harness under MIT and the architecture is striking. Every component of the agent loop is a swappable plugin: model, tools, sandbox, UI, and the agent loop itself. Want C… - [@stretchcloud on X](https://x.com/stretchcloud/status/2099118397963251828) GitHub shipped Project HydraFusion on September 4th and I keep coming back to one number: plus 4.9 percentage points on TerminalBench versus Claude Opus 5 alone. That is not a cost story. That is a qu… - [@stretchcloud on X](https://x.com/stretchcloud/status/2099095747992191156) FreeCAD now has an MCP server. Let that land for a moment.Six months ago MCP was a way to give your AI assistant access to Notion pages and GitHub issues. Now it is how you connect an LLM to a paramet… - [@stretchcloud on X](https://x.com/stretchcloud/status/2098921097253339535) Introducing Agency. Never prompt again. AI prompts you. The inversion is the interesting part. Most AI tools wait for you to tell them what to do. Agency works the other way: you give it your life con… - [@stretchcloud on X](https://x.com/stretchcloud/status/2098816407526105290) Most code review tools today are either fully LLM-driven or fully rule-based. Alibaba's open-code-review is neither. They open-sourced the tool they run at scale internally. The architecture is hybrid… - [@stretchcloud on X](https://x.com/stretchcloud/status/2098388085113524594) The shift I keep watching unfold in coding tools finally got a name: persistent coordinator agents. Cursor just shipped Projects. One thread that stays open as long as the work lasts. A coordinator ag… - [@stretchcloud on X](https://x.com/stretchcloud/status/2098211924307513571) OpenAI's Agents API went into public beta today. No extra fees beyond usage. Every developer gets the same harness that runs Codex internally. The execution environment options are what matter. OpenAI… - [@stretchcloud on X](https://x.com/stretchcloud/status/2097919497810112939) Warp is at $30 per PR. They think they can get to $10. The two levers driving the cost down: choosing the most efficient model for each task from their own benchmark data (GPT 5.6 Sol (high) right now… - [@stretchcloud on X](https://x.com/stretchcloud/status/2095364663014047801) GitHub is running a full event on September 10: the first-ever GitHub Copilot Day. The focus is practical developer workflows: effective ways to use Copilot, agents, model choice, the GitHub Copilot a… - [@stretchcloud on X](https://x.com/stretchcloud/status/2095289165550354579) The planning layer for agent work has been missing. GitHub Next just shipped Chopin, and the diagnosis is correct: current agent planning tools are cumbersome, static, lonely, and drown you in walls o… --- Source: Roboterminal · https://roboterminal.app/companies/github.md