ouroboros
Q00
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
14 个项目,匹配「eval」
Q00
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
edonadei
Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.
yj-liuzepeng
Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
PolinniZhong
面向 DeepSeek Harness 的任务上下文检索:根据当前对话,从项目工作区找到最相关的上下文,组织为主要 / 辅助 / 相关内容,并通过 Knit 面板与 knit_docs 提供给人和 Agent。纯本地、确定性、零模型调用、零网络。 Task-aware workspace context retrieval for DeepSeek Harness. Knit finds the project context most relevant to the current task, organizes it into primary / supporting / related context, and exposes the same context to humans a
morluto
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
lizhiyao
OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.
BiBoyang
DSH 插件评测工具:YAML 用例驱动真实 agent 回归评测 + baseline 对比 PASS/WARN/FAIL 门禁|Regression eval harness for DeepSeek Harness plugins
timwhitez
Evidence-first, crash-resumable self-evolution engine for DeepSeek Harness and Harbor.
KirschBluteX
Evidence-driven engineering workflows for Codex and DeepSeek Harness, backed by deterministic routing and behavior evaluations.
Apageoflove
DeepSeek Harness 插件:同一个任务下对比多个模型配置,跑完给出 Pareto 排名和实验报告
Leeaoyin
Structured, reusable skill modules for AI coding agents — covering engineering workflows, reliability evaluation, and production readiness.
Web0926
DeepSeek Harness plugin that validates and ranks 3/5 independent coding-agent patches before approval-gated apply.
LYRA-88
dsh的跨会话记忆管理插件,让agent记住每一个任务的内容和进度。包含命题图、三层内存漏斗、混合向量 + 词法检索(RRF)以及浏览器端审查面板。 | Cross-session memory management for DSH — lets the agent remember the content and progress of every task while executing. Includes a proposition graph, three-layer memory funnel, hybrid vector + lexical retrieval (RRF), and a browser-side review panel.
tkwkeven
Simulated-restart testing for DeepSeek Harness plugins: verifies plugins survive restart (module eval → apply → smoke → dispose) in isolated subprocesses, with a resident auto-watcher and agent feedback loop