Full-text search across 58411 articles. Combine with topic and date filters; results sorted by relevance.
A modular skill system for Claude Code solves the problem of one-off skills breaking at scale across multiple client projects. The system establishes a single source of truth for skills, commands, and tool definitions th…
A developer built a token fuel gauge for Claude Code to monitor usage in real time, preventing quality degradation from hitting the 5-hour block limit. The system combines ccusage and cost logs into a status-line indicat…
Warden is a free, self-hosted Go binary that orchestrates fleets of coding agents in isolated git worktrees, tracking costs and token savings without a database or telemetry. The tool supports multiple agent backends, a …
AMD published a blog post detailing a workflow that combined ROCm profiling tools with Cursor's AI code-assist agent to optimize a double-precision HIP kernel on an Instinct MI250 GPU, achieving a cumulative 28.3× speedu…
GitHub Copilot switched to usage-based billing, increasing costs for users. Local LLMs offer a cost-effective alternative, with tools like Ollama and LM Studio enabling agentic coding without cloud dependency. The author…
Anthropic released Claude Opus 4.8 with five configurable effort levels — Low, Medium, High, Max, and Ultra Code — that directly control the model's reasoning depth, speed, and cost. The effort levels determine how many …
Amazon Bedrock now supports running the open source, terminal-native AI coding agent OpenCode against open weight models including Moonshot AI Kimi K3, OpenAI GPT-OSS 120B, and NVIDIA Nemotron 3 Super 120B, keeping infer…
A developer who hit ¥1.2M/month in revenue built an autonomous system to auto-disable unused Claude Code plugins, addressing a context-window tax that costs up to 4,000 tokens per session. The system runs weekly via Laun…
Quarkslab has released pcode_graph, a Python library for building semantic graphs from binary code, and demonstrated its use in training a neural network to detect function similarities across architectures and compilers…
CodeRabbit raised $143 million in a Series C funding round at a $1.5 billion valuation, co-led by Atomico and Smash Capital, with participation from BMW i Ventures, Datadog, Hirtle Callaghan, SineWave Ventures, Scenic Ma…
Soamee, a software agency, reported that 331 of its 639 commits on its website repository since January 2025 involved Claude Code, with the tool generating translations, scripts, and repetitive components, while humans h…
AI coding tools widen the gap between senior and junior developers, according to an engineer's analysis. While AI boosts output for experienced developers who use architectural safeguards, less experienced developers pro…
A Princeton team's CoALA framework defines four types of memory for AI agents—working, semantic, procedural, and episodic—and Claude Code implements each as plain files and commands rather than a vector database, with ep…
Claude Code connects to external tools such as browsers, databases, and GitHub through MCP (Model Context Protocol), which supports two transport types: HTTP for already-deployed remote servers and stdio for locally run …
OpenAI's GPT-6 Astra, while impressive at computer use and image understanding, fails to deliver useful software engineering output, according to developer Armin Ronacher, who ran a 35-hour 'software factory' experiment …
Anthropic's Claude Code CLI ships with sensible defaults, but sustained agentic work requires manual configuration of three key files—CLAUDE.md, project-level .claude/ settings, and global ~/.claude/ preferences—to preve…
A developer built a multi-agent AI system where one agent writes code, a second scores it, and a third refines it in an automated loop. The pipeline uses Claude models to generate, evaluate, and improve Python scripts un…
Anthropic's Claude Code supports two multi-agent architectures: sub-agents, which operate in isolated sessions under a central orchestrator and cannot communicate with each other, and agent teams, which enable peer-to-pe…
ZhipuAI released GLM 5.2, an open-weight large language model with a 1-million-token context window and MIT license, which outperforms GPT-4.5 on design and coding benchmarks. The model offers frontier-level performance …
Anthropic's Claude Code, paired with the Gmail MCP server, enables users to build a skill that automatically reads inbox newsletters, scores AI stories, generates a ranked digest, and drafts LinkedIn posts each morning. …