dsh-turn-rewind
Anionex
deepseek harness对话和代码状态回退插件 | DSH — rewind conversation and workspace state, powered by a persistent Change Ledger
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。
22 个项目,匹配「safety」
Anionex
deepseek harness对话和代码状态回退插件 | DSH — rewind conversation and workspace state, powered by a persistent Change Ledger
PerryLink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
openguardrails
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
lxzy-7
Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网(安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析)。
PlutoKeating
dsh-lark-bot:把 DeepSeek Harness (dsh) 桥接进飞书/Lark 的 bot,扫码即用:流式卡片、项目工作区、并行任务、多角色 Agent、跨会话通知、对话内模型/密钥管理与安全网守护(dsh 崩溃后飞书仍可自救)。A scan-to-connect bridge bot connecting DeepSeek Harness (dsh) into Feishu/Lark: streaming cards, workspaces, parallel tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian.
FuRongJun-1999
AGI 的长期记忆基础设施。让 AI Agent 拥有不可遗忘的自我。跨会话记忆 · 持续学习 · 可审计信任(智能论 v3.2)
BlockRunAI
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and 67 models from one wallet, paid per request over x402.
PerryLink
Claude Code /rewind for DeepSeek Harness — git-first workspace snapshots before every mutation, turn-boundary session forks, one-shot /rewind restore. A dsh-plugin capability seam.
PerryLink
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
fatmo666
Compiler-style pre-execution safety analysis for Harness shell actions.
MkaliezZ
Deterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.
SiliconPsycheLabs
PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.
1052326311
Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.
Elaina-real
Tiered auto-review for DeepSeek Harness: static-rule safety net + LLM reviewer + human fallback — auto-allow safe actions, deny irreversible ones, ask a human for the rest.
yyyyolo7a79-sketch
DSH auto-and-safety permission preset: full file access but no delete without user approval
THEWOLFWALKER
Agent- and GUI-controlled DG-LAB Coyote e-stim plugin for DeepSeek Harness: safety-bounded strength, programmable waveforms, DSH-aligned web panel
ZSLlearn
Structured, safety-guarded git tools for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) agent presets — a zero-dependency Cordis plugin (plain ESM, no npm dependencies), hardened through real-repo testing.
cnwutianhao
Safety-first workflow plugin for DeepSeek Harness with task contracts, approval gates, checkpoints, verification evidence, and best-effort rollback. 为 DeepSeek Harness 提供任务契约、审批门禁、检查点和验证能力,让 Agent 工作流更安全。
Raphaelutumn
DeepSeek Harness file-safety guardrail that limits AI coding-agent file edits per turn and prevents too many file changes, with call and UTF-8 byte budgets. 限制 DSH Agent 每轮修改文件数量。
abstudio-cn
DeepSeek Harness TOTP authenticator safety plugin
cnskycn
DSH (DeepSeek Harness) plugin dev workbench: draft/publish/rollback safety
tmpdot
Deliberately inject a small, known bug into a disposable git worktree so learners can practice finding and fixing it. A teaching tool - read the README for its educational philosophy and safety guarantees.