dsh-context
A DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.
352 results
A DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
Composable three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, guarded strategies, WebUI, and headless tools.
Install the full dsh-mnemon integration from the Mnemon repository.
Previewable cross-preset session migration for DeepSeek Harness with bounded, fixed-schema handoffs
Visual conversation map for DeepSeek Harness: an infinite whiteboard where every session is a card — drag to arrange, double-click to start a chat in place, draw an edge to fork a new session with injected context. Built for ADHD-friendly spatial memory. · DSH 可视化对话地图:会话即卡片,双击即聊,连线分叉带上下文的新对话。
Native Rapid-MLX provider for DeepSeek Harness — teaches DSH what the local server already knows (memory-fitted context via max_model_len), plus model-management tools and a /rapid-mlx overview.
DeepSeek Harness Desktop 用量小宠物:用逐帧角色动作反馈运行状态,并展示上下文、终身 Token 用量与历史趋势。
DSH diff-viewer plugin: PiUI-style visual diff surface (split/unified, change bars, real file line numbers, word-level marks, collapsed context, windowed rendering) replacing the stock DiffBlock for write/edit tool calls. Registers into the ui-tool keyed toolview slots.
DSH 上下文注入审计插件:统计 AGENTS.md 指令链 / 技能目录 / 工具 schema / MCP 工具的 token 成本,检测重复与冲突;原生 Context Doctor 面板 + context_audit 工具。
MCP bridge: lets ChatGPT Web create, view, continue and control DeepSeek Harness (DSH) agent sessions through the official MCP protocol. The bridge only connects; DSH keeps its session, agent, tool, approval and workspace security model.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
DeepSeek Harness plugin: incremental file mounting with read dedupe, version-aware invalidation, and a mounted-files view (host half + web client half)
OOMOL Connector integration for DeepSeek Harness: connect apps and call Actions through progressive MCP discovery.
A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance
Reduce large agent tool output by what it means, not by where it was cut.
Provider Model Configurator for DeepSeek Harness: view, create, edit, copy and delete model entries (context window, max output, modalities, reasoning efforts) across your configured providers, with quick-fill from the pi-ai preset catalog.
DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys 閳?plus sliding-context awareness (compaction summaries join recall/search, a compaction notice with one-click /compact fill) layered on the ordinary composer draft only.
Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.
Miraculous Standard — unified anchored agent preset for DeepSeek V4 Pro/Flash (official API & opencode-go). Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, unified context gate, epoch-aware catalog management, rc7-ready shell handling.
OpenViking retrieval, resource management, auto-recall and session memory for DeepSeek Harness.
DeepSeek Harness plugin bundle: optimize raw instructions into professional Role / Task / Context / Format prompts through the harness llm service