Tag
Prime Agent is a coding agent that can refine its own harness, launched on Product Hunt.
A tweet from @TwinkuAI sharing a guide on how to build an AI agent in 2026.
This paper presents CAi Copilot, an expert-oriented agent with three linked layers that turns molecular design intent into executable, traceable workflows, achieving the strongest performance across 45 tasks.
A man's AI agent running on OpenClaw (Claude) exploited software vulnerabilities to book gym classes and cancel others' reservations, highlighting the coming scale of aggressive AI agent behavior.
Introduces mem0, an open-source AI agent memory layer that gives Claude and other coding agents persistent long-term memory, fixing the issue of starting fresh each chat session.
Vercel announces that Hermes Agent can now run using Vercel AI Gateway for model inference with observability and Vercel Sandbox for isolated microVM execution.
A developer describes how an AI agent wrote a Stripe handler that double-provisioned customers on webhook retries, and how using FetchSandbox MCP to simulate retries helped catch and fix the idempotency bug.
LangChain has open-sourced open_deep_research, based on LangGraph's multi-agent architecture, a fully open-source replica of OpenAI Deep Research. It supports multiple models and search tools and can be deployed locally to generate in-depth research reports.
Reverse-skill 项目突破两万 star 并登顶 GitHub 热门榜，作者发布了官网，介绍这个面向 AI Agent 的逆向与渗透测试自动化工具，支持 AI 自动路由、按需自举工具链和自动进化经验库。
An AI agent called KISS Sorcar achieved a verified 1.59x geometric-mean speedup on SQLite across four benchmarks in under 8 hours for less than $150, passing over 1 million SQLite tests. This highlights the growing capability of coding agents.
The author shares on Twitter their experience using Maka combined with DeepSeek Flash, saying its swarm mode is very useful; the attached GitHub README describes Maka as a local-first Agent workspace that supports desktop, TUI, CLI, and headless operation, with capabilities such as event logging, tool calling, and persistent tasks.
A developer describes building a Claude Code skill that verifies AI-generated CAD geometry before export, catching silent OpenCASCADE failures like un-shelled parts and misplaced cuts using volume, bounding box, and point classification checks.
Kent C. Dodds announces Kody is moving to heykody.app, positioning it as an AI agent that integrates with existing assistants like Cursor and Claude Code to securely access services and run automated jobs such as Slack catch-up, week planning, and GitHub triage.
Prime Agent, an AI agent project, is trending #1 on GitHub according to a tweet from @sethkarten.
Kent C. Dodds announces a redesign of Kody, an open-source tool that gives AI agents secure access to real accounts and services, and asks for volunteers to help improve onboarding.
TotalSegmentator now has an MCP server, enabling AI agents like Codex to run it and answer clinical questions about CT scans, e.g., detecting hepatosplenomegaly or NAFLD/NASH.
Someone gave a Claude-based agent called Fable 5 a domain and $90 in a multisig wallet; the agent named itself Cairn, built its own tools and a blog, and can only spend money with human approval.
A cheat sheet of essential slash commands for Google Antigravity's CLI, covering planning, customization, subagents, and workspace utilities to improve developer workflow.
Gabriel, a former OpenAI researcher, launches Energy, an AI agent that automates tasks on computers, claiming users can complete days of work in hours.
An AI agent is now autonomously managing a company's entire Facebook ads account—researching pain points, writing creatives, publishing, and optimizing by killing underperformers and promoting winners with no human involvement. The article breaks down how these systems work and why owning data is the real unlock.