scribe is a self-hosted knowledge base written automatically by your tools. It reads Git history, Claude Code and Codex sessions, self-sent URLs, and drop files, then turns that work into a curated, cross-project wiki of plain Markdown stored in Git. Instead of making developers maintain a second brain or rebuild context whenever an agent session starts from zero, scribe captures decisions, fixes, evaluations, and the reasoning behind them so agents can query that memory before they act. Its pipeline runs on cron: it discovers projects, filters low-value noise with FTS5 before invoking an LLM, extracts grounded facts through bounded and two-pass workflows, and compiles them into entity-first pages with YAML frontmatter, wikilinks, backlinks, retrieval context, and typed relationships such as supersedes, contradicts, derived_from, specializes, and extends.