400 results
dsh-docker — typed, guarded container control for DSH: structured docker/compose tools, project-aware targeting, an approval gate for destructive ops, service-health context, and a replayable status-table renderer
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
Claude Code-style `paths:` rule injection for DeepSeek Harness (DSH): inject rules from ~/.dsh/rules, <project>/.dsh/rules and <project>/.claude/rules into the model context.
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
元压缩：模型自己决定何时、如何压缩自己的上下文——列 surface、选区间、以自写文本替换；替换走官方 compaction 事务（检查点、配对平衡、可重建）。Meta-compaction: the model directs its own context compaction through the official compaction seam.
Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement
MCP adapter for DeepSeek Harness — one proxy tool instead of dumping every MCP schema into context.
把 git 状态与仓库规范动态注入 system prompt：分支/脏文件数/最近提交 + 仓库规范指引（官方 system-prompt section/context/variable 缝隙插件）
TabNexus for DSH：轻量的本地任务、分类、网页资料与流程管理插件。
DeepSeek Harness bundle: inject the user's IDE context (open editors + current selection) into each turn, via the Claude Code IDE WebSocket bridge (IntelliJ IDEA & VS Code).
Load MCP servers for the DeepSeek Harness from the mcp.json of Claude Code, Kiro, OpenCode, and Codex, with user and project layers and live reload
Visual percentage and token settings for official DeepSeek Harness compaction
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have
Token usage dashboard for DeepSeek Harness: cache, context, efficiency, per-step details, and cross-session comparison
Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.
Data-provider MCP server for football: results, stats, odds, standings, form and head-to-head for 18 European leagues (1993-94 →) and 8 cup competitions, for any MCP client. Also a DeepSeek Harness (dsh) plugin.
DSH Desktop Operator: safe Windows Computer Use, desktop automation, UI Automation, and MCP tools for DeepSeek Harness
Mid-turn user steering for DeepSeek Harness: /steer (visible) and /inject (quiet context notice) slash commands, a model-facing mid-turn guidance prompt section, and an always-visible injection bar above the composer.
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
DeepSeek Harness dynamic context pruning plugin (model-driven context management)
Zero-dependency MCP stdio server template with an out-of-the-box A-share (Chinese stock) data toolkit. Key-free, NDJSON protocol, drop-in dsh bundle.
A search tool for DeepSeek Harness that learns to pick between quick and thorough search strategies using a contextual bandit (Thompson sampling).
Windows MCP Hub for DeepSeek Harness: scan MCP servers configured in Claude Code / Codex / CodeBuddy, probe real connectivity via stdio & streamable-http initialize handshakes, enable/disable from a /mcp popup panel or the settings page.