Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.

DSH updater + official docs sync plugin for DeepSeek Harness: one-click npm update of @deepseek-ai/dsh with live progress, incremental sync of the official docs/ to local with progress, and dsh_docs_search / dsh_docs_read model tools. DSH 更新器 + 官方文档同步器（进度

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Turn any text field into a two-way LLM channel: it reads what you write and fills what you ask. Flags a slip as you type, answers anything you end with _. Claude Code, OpenCode, Gemini CLI, shell, Chrome, DeepSeek Harness. Model-agnostic, open standard, no chat window.

Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI, terminal TUI, and harness integration.

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.