<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Runtime on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/runtime/</link>
    <description>Recent content in Runtime on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 25 Jul 2026 12:45:18 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/runtime/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Cline agent: open runtime for PlanAndAct workflows</title>
      <link>https://aiagentsnews.top/posts/cline-agent-open-runtime-for-planandact-workflows/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/cline-agent-open-runtime-for-planandact-workflows/</guid>
      <description>This open runtime unifies IDE and terminal workflows, boasting 64.2k GitHub stars while executing bash commands without vendor lock-in.</description>
    </item>
    <item>
      <title>OpenAI tool namespaces: hosted vs local execution</title>
      <link>https://aiagentsnews.top/posts/openai-tool-namespaces-hosted-vs-local-execution/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/openai-tool-namespaces-hosted-vs-local-execution/</guid>
      <description>OpenAI&#39;s Agents SDK defines exactly five tool categories. Learn how namespaces separate hosted execution from local runtime for better token efficiency.</description>
    </item>
    <item>
      <title>Agent runtime rules: boost scores by 14 points</title>
      <link>https://aiagentsnews.top/posts/agent-runtime-rules-boost-scores-by-14-points/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-runtime-rules-boost-scores-by-14-points/</guid>
      <description>See how SelfUse jumped TerminalBench scores from 23.8% to 38.1% by mining execution traces instead of tweaking model weights manually.</description>
    </item>
    <item>
      <title>AGUI protocol on Bedrock: Stream agents via SSE</title>
      <link>https://aiagentsnews.top/posts/agui-protocol-on-bedrock-stream-agents-via-sse/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agui-protocol-on-bedrock-stream-agents-via-sse/</guid>
      <description>Discover how to configure your container on port 8080 to stream SSE events and separate agent logic from frontend rendering with AGUI.</description>
    </item>
    <item>
      <title>crewAI 1.14.7: Secure State and Pluggable Backends</title>
      <link>https://aiagentsnews.top/posts/crewai-1147-secure-state-and-pluggable-backends/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/crewai-1147-secure-state-and-pluggable-backends/</guid>
      <description>crewAI 1.14.7 resolves critical CVEs and adds pluggable backends. Learn how state isolation supports the framework&#39;s 54.7k GitHub stars.</description>
    </item>
    <item>
      <title>LangGraph SDK 0.4.1: Stateless Projections Explained</title>
      <link>https://aiagentsnews.top/posts/langgraph-sdk-041-stateless-projections-explained/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/langgraph-sdk-041-stateless-projections-explained/</guid>
      <description>LangGraph SDK 0.4.1 enforces stateless projections and extracts decoders. Learn how the 36.2k-star repo now handles V3 streaming for RemoteGraph instances.</description>
    </item>
    <item>
      <title>Runtime policy stops dangerous agent tool calls</title>
      <link>https://aiagentsnews.top/posts/runtime-policy-stops-dangerous-agent-tool-calls/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/runtime-policy-stops-dangerous-agent-tool-calls/</guid>
      <description>Learn how a runtime policy engine evaluates every proposed action to allow, deny, hold, or modify tool calls before execution.</description>
    </item>
    <item>
      <title>LangChain framework: Swap models instantly</title>
      <link>https://aiagentsnews.top/posts/langchain-framework-swap-models-instantly/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/langchain-framework-swap-models-instantly/</guid>
      <description>LangChain offers 1000+ integrations to swap models without rewriting code. Its durable runtime ensures persistence and checkpointing for production agents.</description>
    </item>
    <item>
      <title>LangChain v1.0 drops AgentExecutor for LangGraph</title>
      <link>https://aiagentsnews.top/posts/langchain-v10-drops-agentexecutor-for-langgraph/</link>
      <pubDate>Wed, 08 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/langchain-v10-drops-agentexecutor-for-langgraph/</guid>
      <description>LangChain v1.0 removes AgentExecutor, enforcing LangGraph as the sole runtime. Python 3.10 is now required for typesafe streaming and structured outputs.</description>
    </item>
    <item>
      <title>Eve framework review: minimal deps, max clarity</title>
      <link>https://aiagentsnews.top/posts/eve-framework-review-minimal-deps-max-clarity/</link>
      <pubDate>Sun, 05 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/eve-framework-review-minimal-deps-max-clarity/</guid>
      <description>Alice Labs analyzed 18+ deployments showing Eve reduces mental load by swapping chains for a single runtime dependency and file conventions.</description>
    </item>
    <item>
      <title>Agent sessions: Why durable execution beats containers</title>
      <link>https://aiagentsnews.top/posts/durable-agent-sessions-beat-containers-by-100x/</link>
      <pubDate>Fri, 26 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/durable-agent-sessions-beat-containers-by-100x/</guid>
      <description>Durable agent sessions beat containers by 100x. Learn how the Agents SDK runtime manages state without external databases for reliable scaling.</description>
    </item>
    <item>
      <title>Delegation runtime cuts context overhead by 80%</title>
      <link>https://aiagentsnews.top/posts/delegation-runtime-cuts-context-overhead-by-80/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/delegation-runtime-cuts-context-overhead-by-80/</guid>
      <description>Stop context pollution before it breaks your workflow. Delegation runtime isolates subtasks, reducing context window overhead by 80% while keeping control.</description>
    </item>
    <item>
      <title>Memory blindness: Test if your agent uses custom storage</title>
      <link>https://aiagentsnews.top/posts/memory-blindness-test-if-your-agent-uses-custom-storage/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/memory-blindness-test-if-your-agent-uses-custom-storage/</guid>
      <description>After six months of false confidence, I found native memory replaced my custom build. Use this one-minute test to verify true agent retrieval.</description>
    </item>
    <item>
      <title>Productized CLI agents need runtime profiles, not demos</title>
      <link>https://aiagentsnews.top/posts/productized-cli-agents-need-runtime-profiles-not-demos/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/productized-cli-agents-need-runtime-profiles-not-demos/</guid>
      <description>With code churn hitting 7.1%, your CLI agent needs runtime profiles to separate chat from code execution safely.</description>
    </item>
    <item>
      <title>SandboxRecord cuts latency in OpenHands cloud 1.38</title>
      <link>https://aiagentsnews.top/posts/sandboxrecord-cuts-latency-in-openhands-cloud-138/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/sandboxrecord-cuts-latency-in-openhands-cloud-138/</guid>
      <description>OpenHands cloud 1.38.0 uses SandboxRecord to skip runtime API calls, removing network handshakes that slow down 40% of future agent apps.</description>
    </item>
  </channel>
</rss>
