Topic

#Ai Agents

206 articles on Ai Agents — news, releases, guides and analysis from the SourceFeed engine.

Tutorial 3d ago 6

Extend Claude Code with Custom Subagents and Slash Commands

Build a versioned diff-review subagent and a /pr-summary command your whole team inherits from the repo.

Lenn Voss

Tunix takes aim at the idle-TPU tax in agentic RL

Google's JAX-native trainer decouples rollouts from learning so tool-calling agents stop starving the hardware.

Article · 4d ago6

Text-to-CAD makes mechanical design a coding-agent problem

A 14k-star skills library turns Claude Code and Codex into a prompt-to-printed-part pipeline.

Article · 4d ago6

Codex plugins settle the agent extension format war

OpenAI's trending examples repo shows coding-agent extensions converging on the shapes Anthropic shipped first.

Article · 5d ago7

Why 28,000 developers told their agent they have ADHD

A viral skill turns clinical ADHD guidance into formatting rules, and exposes how badly chat-tuned defaults fit terminal work.

Article · 5d ago7

Sandbox Untrusted AI-Generated Code with gVisor

Run LLM-generated Python behind gVisor's user-space kernel with no network, no capabilities, and hard limits.

Tutorial · 1w ago6

Automate Multi-File Refactors with Claude Code Subagents

Build a scout-and-surgeon subagent pipeline behind a /refactor command that cannot touch your test suite.

Tutorial · 1w ago6

Everything Claude Code hit 249K stars. Install almost none of it

The fastest-growing repo of the year is best used as a parts bin, not an operating system.

Article · 1w ago7

Prompt engineering finally gets a build step

Google's transpilation pitch joins Anthropic's Agent Skills and Microsoft's POML in treating prompts as compiled, validated artifacts.

Article · 1w ago7

Claude Hacked Real Companies Because the Sandbox Wasn't One

Anthropic audited 141,006 eval runs and found three real breaches, a containment lesson for anyone running agents.

Article · 1w ago7

Create Custom Agent Skills for Claude Code

Bundle a script and a SKILL.md into a project skill your whole team can run with one slash command.

Tutorial · 1w ago6

Google is rebuilding its cloud around code it doesn't trust

Sandboxes in Ray, singleton Cloud Run runtimes, and RL time-slicing share one design assumption: the caller is a model.

Article · 1w ago7

The 32k-star security pack that coaches agents past refusal

reverse-skill brings badly needed structure to agent-driven hacking, then trusts the model itself to hold the safety gate.

Article · 1w ago7

Build a Self-Correcting AI Agent with Reflection and Retry Loops

Add a critic call and a deterministic check so a Claude agent fixes its own output until the tests pass.

Tutorial · 1w ago6

The 60k-Star Research Skill Is a 2,300-Line Prompt

last30days shows what agent skills become at scale, and why you should read the hooks before installing.

Article · 2w ago7

Your Slack Bot's Database Is Now a Claude Session

Vercel's template wires Claude Managed Agents into Chat SDK, and the thin bridge is the point.

Article · 2w ago7