Cainew

Curated AI news for developers

TL;DR

Tools & Products

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

GitHub

Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

GitHub

A AI general-purpose state-space search engine, validated first on autonomous penetration testing.

GitHub

Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.

GitHub

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

GitHub

A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.

GitHub

A unified Zero-Trust MCP server that gives IDE agents local semantic codebase search, isolated episodic project memory, and hallucination-free framework RAG.

GitHub

Most recruiting agencies start with who they already know. Prism starts with who is actually best for the role. We search beyond existing networks, agency databases, and active job seekers to find high-fit candidates across the open talent market. Then we help engage them with speed, precision, and personalization, giving companies a faster way to reach the people they actually want to hire.

ProductHunt

Research Papers

Killswitch presents a per-function short-circuit mitigation primitive that provides granular control over function execution and error handling, enabling developers to implement safety mechanisms at the individual function level.

RSS

Tutorials

This article explores how HTML proves to be surprisingly effective as a tool for code generation and manipulation when working with Claude, demonstrating the practical value of leveraging web standards in AI-assisted development.

Twitter

Discussion

The article warns that delegating document processing tasks to large language models can result in data corruption and integrity issues, highlighting risks in relying on LLMs for sensitive document handling without proper safeguards.

ArXiv