Tag
A get-started guide for configuring agent permissions for Claude Tag, covering agent identity setup and design decisions.
Codex can self-configure to integrate third-party models like DeepSeek and Ollama by reading and modifying its config file automatically.
This tutorial explains how to install Codex++ and configure a DeepSeek API key to unlock the full features of Codex AI tool in China, bypassing the need for a ChatGPT account or subscription.
A migration guide for moving from OpenClaw to Hermes Agent, detailing the transfer of persona, memory, skills, and config files with options for preview, dry-run, and secret migration.
Explains three levels of git ignore files: per-repo checked-in (.gitignore), per-repo not checked-in (.git/info/exclude), and global machine-level (~/.config/git/ignore), plus how to check which file is ignoring a specific file.
A detailed configuration guide that teaches users how to connect OpenAI Codex to third-party models like DeepSeek through the open-source proxy tool CC Switch, solving protocol incompatibility issues.
A user shares their Docker deployment configuration for running the GLM-5.2-FP8 model on HGX-H200 hardware using SGLang, achieving 262k context and 70 tokens/s.
The author reflects on common misconceptions about CLAUDE.md, pointing out that instead of piling on information, one should compress decision criteria, constrain execution boundaries, and consolidate high-frequency rules to improve the efficiency of code agents like Claude Code.
Explains how to build dedicated agent profiles in Hermes Agent, allowing users to configure identity, skills, memory, and model, and enabling multiple profiles to work together via an orchestrator or Kanban board. A new dashboard profile builder simplifies the process.
A lean CLAUDE.md configuration file that enforces project conventions for Claude Code, with battle-tested rules to improve output quality without exceeding 200 lines.
A guide listing common mistakes when setting up OpenClaw, including skipping persistent memory, not enabling outbound capabilities, overloading system prompts, not setting fallback behavior, and failing to use multiple models for different tasks.
A blog post from Posit defends YAML against the prevailing consensus that TOML is superior, tracing the history of configuration formats and arguing that YAML's specification and tooling have evolved to address past criticisms.
Claude platform launched a terminal feature, allowing users to perform API calls, launch smart agents, upload files, sync YAML configuration files, and view run logs via CLI. Claude Code can also directly use this terminal.
Introducing the Auxiliary Models feature in Hermes Agent, which allows independent configuration of models for each auxiliary task. It also includes a fallback mechanism that automatically switches to backup models. Support for the Hermes Desktop client is also mentioned.
Developer Julien Barbier shares his CLAUDE.md configuration file for AI coding agents, which improves efficiency by providing explicit instructions for Claude, Gemini, and Codex. The file is customizable and includes setup instructions for multiple tools.
A network engineer provides a free service offering full BGP feeds for IPv4 and IPv6, intended for lab use, with detailed configuration examples for Cisco IOS and IOS XR.
An in-depth article revealing undocumented configuration options and hook capabilities in Claude Code, sourced from the npm package's source code, including the internal 'YOLO Classifier' for auto-approval permissions.
A comprehensive guide to using Claude Code as a programmable agent with memory, custom commands, and project configuration for advanced developers.
A tweet explains how to clone Andrej Karpathy's AGENTS.md workflow into Codex by pasting the 65-line file into Global Custom Instructions, making Codex behave more like a structured autonomous coding agent.
A developer discovered 85 undocumented settings for Anthropic's Claude API, leading to significant cost reductions by optimizing configuration such as memory scoping, extended thinking, and cache control.