Give your DSH agent eyes via any OpenAI-compatible vision model - 11 provider presets (Doubao/Qwen-VL/GLM-V/OpenAI/Gemini/Ollama...), capability checkboxes that inject live prompt guidance, and analysis of images the user drops into the chat; the agent writes its own observation prompt, and base64 never enters its context.
Give your DeepSeek Harness agent eyes. dsh-client-vision is a screen-capture + external image-recognition plugin for DeepSeek Harness: the agent takes a screenshot (or points at any image), hands it to a vision-capable model through a pluggable channel, and gets back plain text it can actually act on — no multimodal model required.
Empowers DeepSeek Harness AI with cross-session long-term memory, manages your to-dos and skills, and orchestrates multiple AI sessions and external agents to collaborate—it learns from you over time, so context stays intact even when you switch conversations.
Assembled context for DeepSeek Harness: a context tree over the session surface with per-node assemble modes (full / key / off), agent-authored presets, and a panel that decides what the model actually sees.
DSH Cordis plugin: turn any source text into an AI knowledge graph (facts/inferences/concepts/definitions/examples/counter-examples/rules) with two-way linking between the graph and the original text.
Local knowledge base for DeepSeek Harness: zero-dependency SQLite FTS5 index for markdown/text/code/web pages, source-cited retrieval, session experience library, interactive kbquery Web panel + knowledge galaxy.
LaTeX snippet expansion in the DSH web composer: Tab expands a trigger into a formula template with the caret in the first hole, then walks the rest. // expands with no Tab at all.
Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.
Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.
仿 Codex 的 DSH Web GUI 输入历史插件：会话输入框按 ↑/↓ 浏览历史 prompt，Esc清除当前对话框并进入历史，跨会话、跨重启持久保留，仅存纯文本，安全接管不误伤草稿。 A Codex-style input-history plugin for the DSH Web GUI: recall previous prompts with ↑/↓ in the composer, persisted across conversations and restarts, text-only storage with safe key routing.
