Full-text search across 63082 articles. Combine with topic and date filters; results sorted by relevance.
A custom agentic harness built for vulnerability research uncovered two vulnerabilities in the open-source FreeRDP RDP client that can be chained into remote code execution on the client, with a human researcher validati…
Agentboxd launched live on 24 Sep 2026, offering AI agents real email inboxes on its own mail servers at agents.agentboxd.com, created with a single API call via POST /v1/inboxes. The service authenticates inbound mail w…
Personal Jarvis launched as a free, open-source AI workspace that runs on a user's own computer, centered on a voice orchestrator that connects conversations to agents, coding sessions, desktop actions, and user-selected…
A September 2026 comparison of open-source coding models found GLM-5.3-Flash from Z.ai best for agentic coding, DeepSeek V4 Flash cheapest per token, and MiniCPM5-2B best for on-device use. GLM-5.3-Flash, a 320B mixture-…
A developer built GuardianKane, a verification layer for Claude Code that placed 2nd in the TestMuAI Kane CLI hackathon, after an AI agent marked a task complete while shipping a performance chart that rendered the same …
Nous Research released the Hermes Agent plugin "Claude Subscription DirectSDK (Experimental)," which drives the unmodified official Claude Code executable as a request-scoped model client for Claude Pro/Max subscriptions…
A developer released router, a pre-release command-line tool that selects an AI coding agent, model, and reasoning effort for a task and launches it inside a Herdr pane, supporting Cursor, Claude Code, Codex, and OpenCod…
Ollama installs and runs open AI models locally for free under the MIT license, serving an API on localhost:11434 that editors and agents can query, according to the tool's own README verified on 12 August 2026. The inst…
A developer team interviewed over 100 tech leads and senior engineers about AI-generated code reviews and found that human attention is a fixed budget while PRs have grown larger. They built a change map that tiers chang…
An engineer at a financial technology company describes how LLM agents have automated nearly the entire software development lifecycle, from triaging errors and writing code to QA and deployment, leaving humans only to c…
A developer explores seven collaboration platforms designed for teams where AI agents work alongside humans, including GitHub and Jira. The article argues that as AI coding agents take on larger development tasks, tradit…
A developer released a deployment package for running the Qwen3.8-27B coding agent locally on an RTX 5060 Ti 16GB GPU, achieving task completion in about 14m20s on a Go repository test. The package uses llama.cpp with qu…
SandrPod, an open-source, self-hosted control plane for AI agent code execution, launched v0.5.10, enabling developers to run unmodified E2B SDK code on their own infrastructure across 8 clouds including Aliyun and Tence…
A developer published a set of mandatory coding guidelines for AI agent development, emphasizing branch management, code quality principles, and syntax verification. The rules require contributors to avoid direct commits…
A developer built MaruCheck, an open-source QA and verification tool that creates an independent verification layer between AI coding agents and shipped software. The tool uses a 'Quality Contract' to maintain a persiste…
GitHub's August 17, 2026, outage lasted 7 hours and 47 minutes, with peak error rates of 20% on web and API requests and 50% on archive and raw content downloads, caused by three compounding failures: an Istio service me…
A developer argues that AI-generated code is breaking the traditional definition of correct software, where green CI pipelines and passing unit tests no longer guarantee semantic correctness. The developer proposes shift…
JetBrains shipped Rider 2026.2.1 with a bundled refactoring-code skill that gives AI agents direct access to its refactoring engine, cutting median task time from 157.9 seconds to 26.6 seconds (83% faster) and cost per t…
A developer known as Lukie-81 has built RepoRelay, an open-source tool that gives AI coding assistants like ChatGPT access to a local repository without exposing the entire machine. The tool uses a secure MCP tunnel to e…
PyTorch's built-in GELU function is 20% faster than a hand-rolled version when training GPT-2 small models, according to a developer's benchmark. The same code training the same model on the same data ran at about 21,000…