10 min read—
Agent Autoloop: Run Claude Code in the Background
Agent Autoloop runs Claude Code and Codex in the background on cron, GitHub events and webhooks. Agents exit while waiting for approval — no process, no tokens.
Tag: AI Agents
All the articles with the tag "AI Agents".
- 10 min read—
Gemini Decisions API: Fast Decisions for AI Agents
Google's Gemini Decisions API with Gemini Decision 1 scores up to 1,000 questions in one request in 150–250 ms for $0.10 per 1M input tokens, with confidence.
- 8 min read—
OpenAI Codex Security: Scan, Patch, and Re-Verify Flaws
OpenAI's Codex Security finds, validates, and patches vulnerabilities with agents — scan repos, auto-patch, re-verify fixes, and block PRs by severity in CI.
- 9 min read—
Muse Ember: Cheap Small Model for AI Agents
Muse Ember, 9 Nov 2026, matches Claude Haiku 5.5 on Intelligence Index at about $0.14 per task, a third of Haiku's cost. When to use it — and when not to.
- 9 min read—
Do AI Agents Really Work? The Real Numbers
DoorDash got a few hundred agent orders, Uber just four rides, Airbnb almost no agent bookings at all. What do the real numbers say about the AI agent hype?
- 12 min read—
Orkas: Local-First Multi-Agent Team for Your Desktop
Orkas turns Claude Code, Codex and 16 specialist agents into a local-first desktop team that keeps projects, to-dos and scheduled work moving across days.