`Runtime` launches team sandboxes for coding agents

Turns agent coding from local setup into reproducible infra. Strong fit when non-engineers need safe codebase access, less useful for solo toy apps.

[ KEY POINTS ]

Engineering defines instructions, skills, and integrations once; Runtime snapshots Docker Compose, Kafka, Redis, and seeded DBs for fast reusable sessions.
Secrets pass through a managed proxy, while command allow/deny lists, egress controls, and RBAC run at the infra layer.
Works with Claude Code, Codex, Cursor, Copilot, Gemini, and Devin; triggers include Slack, Linear, GitHub, CLI, web app, and API.
Open-source core plus hosted free tier. Pricing is a flat platform fee plus compute, so real value depends on agent workload volume.

Originalwww.runtm.com/Read original →

// related

#0001
#0001Agents & tools Google AI Forum12 hours ago
`Google Antigravity 2.0` Cuts RAM, Breaks Migration Trust
60radar
Google AntigravityCoding agent IDE — agent-first development workflow
The shift to an agent-first IDE removes direct editing and file-level warnings. RAM dropped from 1GB+ to 150-500MB, but migration risk makes it hard to adopt blindly.
- Forced updates moved users to Antigravity 2.0 without notice; side-by-side installs can overwrite the older IDE directory.
- Direct code editing and visual warning markers are gone. The workflow now favors agent commands over manual inspection.
- Runtime monitoring got more sensitive, but subagents misread graceful app shutdowns as failures. Process lifecycle still needs polish.
- Automatic Efficiency Mode cuts memory from 1GB+ to 150-500MB, making the tool viable as a background command center.
Source: discuss.ai.google.dev/t/google-antigravity-2-0-review-beRead original →
FIG-0011:1
60radar
FIG-0011:1
#0002
#0002Agents & tools GeekNews15 hours ago
Microsoft Starts Pulling `Claude Code` Licenses
40radar
Claude CodeAI coding CLI — agentic code work from the terminal
Internal tool access can flip when it threatens the platform owner’s stack. Keep coding-agent workflows portable; single-vendor lock-in is costly.
- Microsoft had opened Claude Code to thousands of developers since December, then began a broad license rollback after six months of heavy internal use.
- The cited pressure point is GitHub Copilot CLI: a rival coding CLI gaining traction inside Microsoft creates direct product conflict.
- Treat agent choice as replaceable infrastructure. Prompts, scripts, and repo workflows should survive a switch from Claude Code to another CLI.
Source: news.hada.io/topic?id=29759Read original →
FIG-0021:1
40radar
FIG-0021:1
#0003
#0003Agents & tools Google AI Forum17 hours ago
`Google Antigravity 2.0` shifts to shared model quota
60radar
Google AntigravityAI coding agent IDE — supports multiple models per task
Quota is pooled across Flash, Pro, GPT, and Claude instead of expanded. Better models get more usable headroom, but cheap prompts now drain the same weekly compute budget.
- The 5-hour reset can refill exhausted GPT and Claude pools to max, because quota now appears shared across models.
- Flash consumes less compute per prompt, while Pro or Claude burns more from the same pool. Minor edits should stay on cheaper models.
- If one model stops refilling, the whole weekly compute budget is likely low. Treat model choice as cost control, not just quality control.
- Google cites compute constraints and demand, so this is flexibility, not a quota increase.
Source: discuss.ai.google.dev/t/the-new-antigravity-usage-model/Read original →
FIG-0031:1
60radar
FIG-0031:1

`Runtime` launches team sandboxes for coding agents

// related

`Google Antigravity 2.0` Cuts RAM, Breaks Migration Trust

Microsoft Starts Pulling `Claude Code` Licenses

`Google Antigravity 2.0` shifts to shared model quota