Read Gergely’s note (and excellent video) on the state of the industry (https://newsletter.pragmaticengineer.com/p/the-state-of-the-tech-industry-in), especially the bit where mid-size companies have built their own agent harnesses and cloud coding agents are what most devs will actually run. We are an AWS shop with a model gateway, LibreChat, and n8n already in place, and I am looking at Strands as a self-hosted harness in our own account. Two things I cannot tell from the outside: How are folks using cloud coding agents? We've mainly settled on OpenCode as a coding harness. Has anyone let internal users deploy their own agent harness, AWS Strands or otherwise, from a chat in a central platform account, without it becoming a second control plane? Curious what survived contact with security, not a benchmark.

Greetings! I'm sharing my "Second Brain". It's a work in progress, currently about 30% complete. Getting familiar with all this terminology isn't easy, but it has been really useful, especially in cybersecurity, where there's so much of it. A huge thank you to my mentor, Alex, for his guidance and support! :) ~~~ ├── 01 MAC_M5/ │ ├── _AltTab_Config_.md │ ├── _imnocaciones/ │ ├── _OBSIDIAN ALEX/ │ ├── _Obsidian General/ │ ├── _Repositorios/ │ ├── _TAB_Mission_ALTTAP.md │ ├── Aereospace/ │ ├── Automatizado y 🧠/ │ ├── Docker/ │ ├── GHOSTING/ │ ├── Gitconfig/ │ ├── Hedr/ │ ├── Hermes/ │ ├── IA MAC.md │ ├── Idioma del teclado.md │ ├── ip del docker.md │ ├── karabiner/ │ ├── Key dividid JOSEAN MARTIENEZ.md │ ├── LOGITECH.md │ ├── NEOVIM/ │ ├── netcat.md │ ├── notas Diarias/ │ ├── opencode.md │ ├── Passw/ │ ├── Pi agentes/ │ ├── pyhton.md │ ├── QMK/ │ ├── QMU.md │ ├── Raycast.md │ ├── Raycast for Mac.md │ ├── scrollable-tiling Wayland macbok.md │ ├── Skailet/ │ ├── streme deckc MCP.md │ ├── Televisión/ │ ├── Terminales/ │ ├── Tmux.conf/ │ ├── Videos Programados.md │ ├── voz Speech to Text.md │ ├── WAve link.md │ ├── Workmux todo en uno/ │ ├── yazi/ │ └── zshrc./ ├── Agent/ │ ├── Daily-review.md │ ├── Docs/ │ ├── pi-vault-agent/ │ ├── References/ │ ├── scripts/ │ ├── Skills/ │ └── Templates/ ├── AGENTS.md ├── Archive/ │ ├── _assets/ │ ├── Agent-Sessions/ │ ├── Background-Tasks/ │ ├── gemini-scribe/ │ ├── Prompts/ │ ├── Scheduled-Tasks/ │ ├── Sin nombre/ │ ├── Skills/ │ └── z otros/ ├── Areas/ │ ├── Admin/ │ ├── Culture/ │ ├── Dating citas y vida en pareja.md │ ├── Exercise/ │ ├── Family/ │ ├── Food & Drink/ │ ├── Health & Body/ │ ├── Home limpieza, orden y mejoras de la casa.md │ ├── Investing/ │ ├── Languaje/ │ ├── Mindfulness/ │ ├── Music/ │ ├── Network/ │ ├── Performance/ │ ├── Shop/ │ ├── Skill/ │ ├── Social/ │ ├── Software/ │ ├── Sport Deportes y actividades al aire libre.md │ ├── Swipe Library capturas de ideas y textos que te inspiran.md │ └── Travel/ ├── certification/

Hi, To keep your local system clean, do you guys run agents in devcontainers or just run it locally? I know some people run their dev work in devcontainers where claude or codex is present so they can go crazy without accidentally creating junk on their system.