57 results
DSH 提示词库插件：集中管理提示词（增删改查、标签分类、导入导出、AI 优化），聊天快捷收录与调用，附会话监控与文件预览。 DSH Prompt Library plugin: manage prompts (CRUD, tags, import/export, AI polish), quick capture & reuse in chat, plus conversation monitor and preview.
A note-taking plugin for DeepSeek Harness (DSH). It provides a full MD notes manager and MD notes editor, letting you quickly capture conversation content into notes. Notes can be maintained by syncing to a Git repository.
DeepSeek Harness (dsh) browser companion: a Chrome side panel that embeds the full dsh web UI and lets the dsh agent read the current page, capture HTTP traffic, and drive the browser.
Unofficial, high-fidelity Claude Code-style TUI for DeepSeek Harness, verified against real PTY captures
Track Bridge: embedded task-management engine for DeepSeek Harness — decision-point protocol, capture wall, and Linear-shaped issue store over session events + storage KV
OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry with backoff.
dsh bundle: register ywleeo/browser-mcp (a local MCP server driving a real Chrome to search, capture, and automate any logged-in site) as native dsh MCP tools (mcp__browser__*).
dsh-plugin-appshot — a DeepSeek Harness plugin for macOS and Windows context screenshot capture.
Cross-session node reference (cue) for DeepSeek Harness: pick another session's user nodes and inject their captured context as a wrapped reference
One memory layer for every AI tool and agent, packaged for DeepSeek Harness with startup context, prompt-time recall, Mem MCP tools, and DSH thread capture.
agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server
Standalone screen capture for DeepSeek Harness (dsh): browser hotkeys plus an agent-facing capture+read tool. Forked out of @liustack/modlens#48 (upstream declined the feature).
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
Model-bound custom HTTP headers for LLM requests: llm/stream capture + ALS + fetch injection (soft-replacement: host half + settings.section UI)
dsh-doctor: self-healing watchdog for the DeepSeek Harness web profile. Recovers from plugin-induced boot failures within 60s, captures every tool error, and watches all live sessions for stuck turns.
Native DeepSeek conversation capture, requirement analysis, and DSH Desktop handoff.
DeepSeek Harness bundle for a Windows desktop UI context picker and MCP server for Codex, DeepSeek Harness, and AI agents
The LLM debug console inside DeepSeek Harness — capture every model call, see everything, replay anything.
失败账本 — DeepSeek Harness 工具失败记录、签名聚类与失败感知重试拦截（含 Web UI 面板）。Failure ledger for DeepSeek Harness: capture, cluster, persist and learn from failed tool calls, with a failure-aware retry guard and a Web UI panel.
Capture AI web conversations to local JSON + SQLite, and port selected messages into agent harnesses as live, continuable sessions.
macOS Vision OCR tool plugin for DeepSeek Harness: read text from screen capture, clipboard images, or image files (zh-Hans + en-US). Unofficial community project.
Local vision 'eyes' for DeepSeek Harness (DSH): screen tool (capture screen or image -> local OpenAI-compatible VLM description) and ocr tool (Windows built-in OCR, zero model / GPU / cloud).
OmniVision for DeepSeek Harness: an OmniParser-powered GUI agent plugin — screen capture, element recognition, click/type automation and a browser vision dock with recognition history, diffing and summary
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.