jidekaixin2dian
DeepSeek Harness(DSH)插件:对话内右键 Agent 文件,预览图片和视频缩略图,打开、定位、复制路径与引用。
bychance6600
养一条会自己长大的鱼:没有人格设置,人格只能通过事件流长出来。DSH 插件 · 三层记忆 · QQ / B站私信 / 抖音 三个真实渠道。
dryw
Elephant-Goldfish Model (EGM) for DeepSeek Harness - npm: dsh-egm (repo dryw/dsh-egm). A context-rich session drafts a design spec, then fresh, read-only Goldfish reviewers stress-test it before implementation.
justhalfbit
DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.
Asher-2000
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation
54xkeee
Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory
YYTbit
Bridge Claude Code memory, skills, and config into DeepSeek Harness
Jackbessaliuz
给 meow-memory 记忆系统加一层语义检索:让"记过的"变成"想得起来的"。只读记忆库,绝不写入上游。
fan56
Topic memory for LLM agents — edited, not accumulated: a topic keeps the starting question, conclusion, impact and dependencies; process is not memory. OKF bundle for dsh, local-first, git-traceable, budgeted LLM-free injection.
bbqisbbq
This plugin has no description yet.
Noelune
Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
KLRSL
记住你的偏好和决定,换个会话它自己会想起来;数据只在本机,随时能查能改。Remembers your preferences and decisions and brings them back in the next session; data stays on your machine.
zhujunpeng12
Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance
deepseekv41flash
给 DSH 模型每轮回填宿主实测的上下文占用,并阻止"上下文快用尽"的错判被压缩摘要继承。
qwe225380
Task-level reliability layer for DeepSeek Harness - decide when to intervene, prepare context, verify evidence, recover from failure. Reuses existing Skills/Tools/Plugins.
tonytanglab
Delegate long-running work to DeepSeek Harness from any MCP agent—and monitor it to completion.
yangyu666
Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction
Guojiz
Git-native AI learning OS with a GitLearnOS-exclusive DeepSeek Harness panel, targeted practice, local RAG, and learner-owned memory.
Max-Null
Cross-session plaintext memory for DeepSeek Harness: model-written, effective immediately, searchable across the workspace chain, budgeted every-turn recall · 跨会话明文记忆:模型写入即生效、明文可审计、沿工作区链检索、常驻注入带预算
yailPeralta
Correctness-oriented MCP server and batch CLI for compact structural reads and reviewed TypeScript/JavaScript edits.
baitouwuya
DeepSeek Harness (DSH) plugin that publishes the running Harness as a Model Context Protocol (MCP) server for other agent harnesses.
GooDAnDReaDY
DSH plugin for AST context compression, test log filtering, and token budget guard
xiseliuli
Expose a running DeepSeek Harness as an MCP server, so Claude Code, Codex or any MCP client can drive its workspaces, sessions, files, shell and agent tools, and read token usage and cost receipts.
ciskonc
Claude Code-style @path imports for DeepSeek Harness: expands @imports in AGENTS.md/CLAUDE.md and injects referenced files into context at session start