<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>alineo blog</title><description>Updates and notes from the alineo team.</description><link>https://alineo.tech/</link><language>en</language><item><title>How to stop a runaway AI agent swarm</title><link>https://alineo.tech/blog/stop-a-runaway-ai-agent-swarm/</link><guid isPermaLink="true">https://alineo.tech/blog/stop-a-runaway-ai-agent-swarm/</guid><description>Pause, steer, or stop a whole tree of sandboxed AI agents from outside them. Real calls, real timings, and what these controls can&apos;t reach.</description><pubDate>Sun, 20 Sep 2026 00:00:00 GMT</pubDate></item><item><title>An MCP server for swarm control</title><link>https://alineo.tech/blog/mcp-server-for-swarm-control/</link><guid isPermaLink="true">https://alineo.tech/blog/mcp-server-for-swarm-control/</guid><description>alineo-mcp puts alineod&apos;s swarm-control API behind stdio, so any MCP client — Claude Code, Claude Desktop, Cursor — can spawn, steer, and pause sandboxed agent swarms as tool calls.</description><pubDate>Thu, 17 Sep 2026 00:00:00 GMT</pubDate></item><item><title>A control plane for swarms of agents</title><link>https://alineo.tech/blog/control-plane-for-agent-swarms/</link><guid isPermaLink="true">https://alineo.tech/blog/control-plane-for-agent-swarms/</guid><description>alineod spawns, steers, and recovers trees of sandboxed agents over HTTP and SSE, so orchestrating a swarm isn&apos;t code you write yourself.</description><pubDate>Sun, 13 Sep 2026 00:00:00 GMT</pubDate></item><item><title>The docs are now built for agents</title><link>https://alineo.tech/blog/docs-built-for-agents/</link><guid isPermaLink="true">https://alineo.tech/blog/docs-built-for-agents/</guid><description>Every alineo docs page is available as clean Markdown, indexed in llms.txt, and one click away from ChatGPT, Claude, or Cursor.</description><pubDate>Tue, 08 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Keeping secrets out of agent sandboxes</title><link>https://alineo.tech/blog/keeping-secrets-out-of-agent-sandboxes/</link><guid isPermaLink="true">https://alineo.tech/blog/keeping-secrets-out-of-agent-sandboxes/</guid><description>An agent that runs code and reaches the network is one prompt injection from leaking its credentials. alineo injects them at the network edge, so the sandbox never holds the value.</description><pubDate>Tue, 08 Sep 2026 00:00:00 GMT</pubDate></item><item><title>A permission gate for sandboxed agents</title><link>https://alineo.tech/blog/permission-gate-for-sandboxed-agents/</link><guid isPermaLink="true">https://alineo.tech/blog/permission-gate-for-sandboxed-agents/</guid><description>AgentSpec.permissions puts a human in front of an agent&apos;s tool calls — a one-word mode or a full per-tool policy, enforced on every call before it runs.</description><pubDate>Tue, 01 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>