Claude Code auto mode: a safer way to skip permissions
…When content looks like an attempt to hijack behavior, the probe adds a warning to the agent's context before the result is passed along—telling the agent to treat this content…
Search
All sources
xda-developers.com
41
anthropic.com
13
pcworld.com
9
9to5mac.com
8
theregister.com
7
developer.nvidia.com
7
theverge.com
6
wired.com
5
engadget.com
4
arstechnica.com
3
about.gitlab.com
3
techcrunch.com
3
These open-source tools do what Claude charges for, and some do it better
…However, Cowork is something I've tested extensively, and Hermes Agent is an open-source AI agent folks at XDA have landed on after putting OpenClaw (the more popular open-source agent…
How we contain Claude across products
…Multi-agent trust escalation. On the one hand, sub-agents can isolate untrusted content, returning structured facts rather than raw text up to the main agent. On the other hand, this can…
Vibe coding apps taught me how hard real coding is
…an agentic but forgetful AI chatbot that communicates through Discord and frequently complains that it’s exceeded its tool-call count; a GitHub-ready agentic workflow helper that I actually didn’t…
Discussions and forums
Thoughts on Claude Code 2.1.139 Agent View and Background Sessions
Spent half a day trying Claude Code 2.1.139’s new Agent View and background sessions — useful, but still has quite a few rough edges.The first item in the 2.1.139 changelog released on 2026-05-11 was Added agent view (Re…
1
Show HN: AnyFrame – Sandboxes for AI Agents
Hey HN! we built https://anyfrm.com, a way to point Claude Code or Codex at any repo and get a fresh sandbox running it in seconds.Python SDK + demo: https://github.com/tinyhq/anyframe-pythonAnyFrame has three key featur…
3
LLM models are not ready for orchestrating many agents
Hi, i have been experimenting with many coding agents distributed in a tree like heirarchy. here is what i found: 1. current LLM models are not trained for orchestrating or managing multiple agents, they prefer doing the…
1
Show HN: I threw away my analytics dashboard and replaced it with 42 MCP tools
Back in October, I built a web analytics tool. It had two distinguishing features: it was cheap, and it had a weekly AI email summary so you wouldn't have to check your dashboards. Turned out that cheap made no differenc…
3
4
Show HN: I built a RAG and knowledge graph agent that runs locally
Claw-Coder is an AI agent that runs locally on your laptop and has access to powerful tools instead of configuring claude or codex to use a local model just use claw-coder. Why was claw-coder created? Answer: To solve th…
7
7
Claude Opus 4.8 just launched — and Anthropic says it's far less likely to ‘fake’ answers
…autonomous and agent-driven. Claude can now run more dynamic workflows In addition to the new model, a new research preview feature called Dynamic Workflows was also announced. The feature allows Claude…
Introducing Claude Opus 4.8
Our latest model, Claude Opus 4.8, is an upgrade to our Opus class of models, with stronger performance across coding, agentic tasks, and professional work, and the consistency to handle long…
Measuring AI agent autonomy in practice
Societal Impacts Measuring AI agent autonomy in practice Feb 18, 2026 AI agents are here, and already they’re being deployed across contexts that vary widely in consequence, from email triage to…
Claude Code's leaked source code revealed some features Anthropic wasn't ready to share yet
…An always-on, proactive AI agent called Kairos An AI agent that works while you sleep The most interesting unreleased feature that was spotted in the Claude Code source code was an…
Gemini, Claude, and ChatGPT are done waiting for your prompts
…proactive" AI (i.e., AI agents that go to work without even being asked). ChatGPT jumped onto the proactive AI bandwagon early, releasing the ChatGPT Pulse feature way back in September 2025…
Project Glasswing: what Mythos showed us
…Context - Coding agents are tuned for one focused stream of work: building a feature, fixing a bug, writing a refactor. They ingest a lot of source code, hold a single hypothesis at…