chenzheshushi-commits
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
XSJUSTC
DSH (DeepSeek Harness) conversation rewind plugin - rewind to any user message, interrupt a running turn, hide the tail from chat view and model context, cancel freely before sending.
YYTbit
Bridge Claude Code memory, skills, and config into DeepSeek Harness
MichengAI
DSH 一次性只读旁问插件:基于当前上下文回答,独立气泡,不执行工具 · One-shot read-only side-ask plugin: answers from current context in an independent bubble, no tool execution
Starlight-bananice
Know what your agent is doing at a glance — 17-segment configurable status bar for DeepSeek Harness: status/model/context/tokens/TPS/cost/jobs. 一眼看清你的 agent 正在做什么:17 段可配置 DSH 会话状态栏。
labmimors
Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.
zhujunpeng12
Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance
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.
JerryLiu369
Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, ARK) + semantic search (Exa, Parallel) + keyless defaults via MCP, CLI, and DSH plugin.
gezi-wen
File-based cross-session memory for DeepSeek Harness (DSH) — every memory is a plain Markdown file. 纯 Markdown 存储,无数据库、无 worker、无端口;从 Claude Code 无损迁移记忆与人格,带记忆星图与可选的记忆整理。
ZekaiShi
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.
Scorp1o117
Agent memory for DeepSeek Harness | DeepSeek Harness 记忆插件
pure-craft
Manage MCP servers, skills, and tools for your DeepSeek Harness agent — true in-context state and per-session / per-preset switches
yindf
Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.
everclear077
Progressive tool discovery for DeepSeek Harness — tiny stable surface, searchable catalog, real pipeline execution, context cache intact.
Guojiz
Git-native AI learning OS with a GitLearnOS-exclusive DeepSeek Harness panel, targeted practice, local RAG, and learner-owned memory.
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.
nowledge-co
One memory layer for every AI tool and agent, packaged for DeepSeek Harness
PeterTXPan
DeepSeek Harness Bundle for Unreal Engine 5.8 via Unreal MCP
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
Edge-Echo
Curated, verified MCP server bundle for DeepSeek Harness (dsh): one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, with a connectivity verifier and CI checks.
lcestou
Claude Code CLI as an LLM provider for dsh (DeepSeek Harness): live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes
noteflowai
Check Agent Skills before reuse: find missing local resources in browser or CI, review pinned examples, and serve skills through DeepSeek Harness or MCP.