GITHUB TOPIC
30projects include this topic
The "approval" topic on GitHub groups 30 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-auto-review with 198 GitHub stars. dsh-auto-review — 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). Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
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).
PerryLink
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
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.
dsh-plugins
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness auxiliary model plugin: provides independent model routes, tools and system prompts for vision understanding, context compression, approval review, sub-agents, session titles and image generation, never touching the main conversation model.
KLRSL
Biomimetic memory system plugin: Biomimetic memory for DeepSeek Harness — transparent Markdown memory, approval-gated writes, frozen snapshot injection
SeverusZh
dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)
ang-XWBWZ
AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.
SiriLee
Per-edit approval gate for DeepSeek Harness — red/green line diff review before write/edit/stream operations · DSH plugin: per-operation approval gate with red/green line-level diff review before write/edit/stream
doncelee229-cmyk
System-level notification alerts for DeepSeek Harness approvals/choices, showing workspace name, click to jump, multi-language. Approval & decision alerts with native notifications for DeepSeek Harness.
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.
nicecx
DSH plugin: relay approval & question requests to any chat channel — iMessage, Email, WeChat built-in; Telegram/DingTalk/Feishu/Slack via a common adapter contract (src/channels/types.js)
SiriLee
Approval-panel hotkeys for DeepSeek Harness — Enter approves once, Esc rejects · DSH plugin: approval panel hotkeys, Enter approves once, Esc rejects
azazo1
按单命令前缀自动放行 DSH 沙箱提权请求, 含管道与链式的命令一律转人工审批.
azazo1
Cap how long one DSH tool call may wait: a global default wait limit in Settings, plus a per-session raise the model can request from the user.
azazo1
DSH web plugin: take over the native approval window so a reject can carry a description the model will see.
ddtcorex
Host-only safety gate for DeepSeek Harness: approval store, secret redaction, permission policy, waterfall pre-execute integration.
DNAlec
DeepSeek Harness auto-approval plugin: keywords + review-model approval table.
picsky
Don't hand over the whole machine, just the decision blocking it: an unattended DeepSeek Harness (DSH) run's tool-call approvals and ask_user_question prompts reach your phone as Feishu cards — desktop first, outbound only.
puesite
DSH/EAC Telegram notification + chat + remote approval plugin
shifan3
Approve-for-me mode for DeepSeek Harness: LLM safety auto-approval for approval requests; high-risk destructive commands still ask the user.
wangxing-git
DeepSeek Harness workspace management toolkit: view, create/register, rename, delete workspace records (registry only, does not touch disk directories); destructive operations (delete registration, change registered path) go through user approval, fail-closed.
xiyuepcl
DSH approval Chinese localization — DeepSeek-powered plugin that auto-localizes dsh approval dialogs (approval dialog auto-translation for DeepSeek Harness)
AnakinCao
DSH Web GUI plugin: session-scoped "Allow for this session" option in the approval dialog (per-mode standing grants, localStorage) + right-panel auto-open guard
GoshawkGGGG
AI tool approval plugin for DeepSeek Harness: uses AI to review the compliance of Agent tool calls and decide whether to execute, with customizable review criteria.
jalllychun
Codex-inspired managed approval for DeepSeek Harness
jyd1230
DeepSeek Harness approval popup wind chime alert plugin (Windows): plays a crisp ~3-second wind chime each time an approval popup requiring manual confirmation appears.
PerryLink
Shared zero-runtime-dependency toolkit for PerryLink DSH plugins: a pluggable Provider registry seam, fail-closed approval and adaptive session-event gates, mechanical verify scripts, shared sanitize/pricing/judge modules, and a new-plugin skeleton.
PerryLink
Multi-channel decision & remote-control bridge for DeepSeek Harness: pushes any workspace's approval/question cards to IM channels (WeChat iLink first) and answers them from chat, with a session console, per-channel security, and an open push service.
trentswd
Escalation-only LLM reviewer for DeepSeek Harness: reviews sandbox escapes only, keeps the sandbox, fails closed.
zhang8019
Permission matrix for DeepSeek Harness: 3 sandbox modes x 4 approval strategies = 9 presets, with global and LLM-robot defaults, three-tier risk policies, audit log and git checkpoint.