Tag
Hermes Agent can now be exported as a single file, encompassing skills, memory, persona, and crons for easy sharing and deployment.
The author built LintLang, a deterministic linter for agent configs that catches structural language defects like vague tool descriptions and conflicting instructions before runtime, and notes that Character.AI's Larch framework adopted it in CI. The post asks developers which runtime failures should be caught statically.
Johnny Heo shares a tip for improving user-facing explanations by adding a style rule to agent or Claude.md files to write clearly without jargon, and setting personality to none in .codex/config.toml.