dsh-plan-lattice
Native continuity recovery for long-running DeepSeek Harness agents
798 results
Native continuity recovery for long-running DeepSeek Harness agents
Codex-style multiple independent selection comments for DeepSeek Harness (DSH).
Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, human-owned, no embeddings
Hands for your DeepSeek Harness agent — autonomous browser operation with a native permission model. Accessibility-ref page snapshots let a text-only model navigate, act, and test without vision or CSS-selector guessing.
Selection quoting for the dsh web GUI: a toolbar over selected assistant text that attaches the selection to the composer as a removable quote banner, prepended to the outgoing message at send
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
In-process graph memory for DeepSeek Harness, backed by TriviumDB.
dsh-voice — voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first, plain audio files under ~/.dsh/voice/
纸质主题 — a warm paper-texture appearance for DeepSeek Harness, inspired by Claude Code (cream paper, ink text, terracotta accents).
Dynamic chat-image bridge, recognition tool, onboarding wizard and failure self-check for text-only models on DeepSeek Harness
DSH plugin for local GSV-TTS-Lite voice cloning + Edge cloud simple mode: voice presets, auto-read, engine setup assistant, read-aloud button, settings panel
Feishu and Lark text, image, and file channel bridge for DeepSeek Harness
DSH 中转站模型思考强度配置与自动识别插件
Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.
Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)
MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
DSH PDF 解析插件: 为 agent 提供 pdf_info / pdf_extract_text / pdf_render_page 三个工具。基于 pdfjs-dist + @napi-rs/canvas; 对未内嵌字体的 PDF (如嘉立创EDA导出) 自动改用系统字体渲染文字。热插拔 — 通过 cordis.patch.yml + profile node_modules 软链接挂载, 无需改动 dsh 源码。
MCP server that lets any agent discover, install, and run DeepSeek Harness plugins.
External vision proxy plugin for DeepSeek Harness, enabling text-only models (DeepSeek-V3 / R1) to analyze and understand images via OpenAI-compatible vision APIs.
GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection
Markdown viewer for the dock file explorer: renders .md/.markdown/.mdx files with a one-click switch to the text editor.
Semantic repo index for DeepSeek Harness — tree-sitter symbol index, code search, and a bounded ranked repo map injected into agent context.