Skip to content

jev 43

  • jevcore-dsh v0.4.1 Verified 102

    TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

    dsh plugin add jevcore-dsh
  • dsh-jev-interceptor v0.8.0 Verified Web UI 31

    Millisecond System-1 judgement for every tool call in DeepSeek Harness: Jev-powered risk classification and evidence-gated auto-approval, fail-closed by construction.

    dsh plugin add dsh-jev-interceptor
  • dsh-jev-tools v0.1.13 Verified Web UI 14

    Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

    dsh plugin add dsh-jev-tools
  • dsh-subagent-registry v0.19.1 Verified Web UI 8

    dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch, ask_agent follow-ups, the /registry-config management command, and the opt-in codemode (jev + store

    dsh plugin add @aiwayds/dsh-subagent-registry
  • dsh-macos-computer-use v0.3.2 Verified 6

    AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus, apps, set-of-mark screenshots, on-device OCR, verified actions, and optional Jev (TypeSafe System One) semantic guards — 1

    dsh plugin add dsh-macos-computer-use
  • dsh-jev-prune v0.1.1 Verified 5

    Jev-judged context compaction for DeepSeek Harness. Two layers: prune stale tool results (semantic instead of size-only), and replace spent tool-call ranges with a deterministic receipt instead of a model-written summary.

    dsh plugin add dsh-jev-prune
  • dsh-jev-decide v0.1.2 Verified 4

    DSH 插件:把 TypeSafe Jev(System One 决策模型)注册为 agent 工具 jev_decide。调用 https://api.typesafe.ai/v1/systemone,让 agent 在路由/分级/guardrail 等场景拿到带校准概率的结构化判定(noul/choice/score),而不是让大模型瞎猜。

    dsh plugin add dsh-jev-decide
  • dsh-set-model v0.3.1 Verified Web UI 3

    A DeepSeek Harness (DSH) plugin: through the TypeSafe Jev decision model (it reads each turn's instruction, classifies the task and picks a preset) or through its own tool calls, the agent switches model presets and thinking depth on its own, following th

    dsh plugin add dsh-set-model
  • dsh-jev-advisor v0.2.1 Verified Web UI 3

    Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op

    dsh plugin add dsh-jev-advisor
  • dsh-fact-check v2.0.1 Verified 2

    Fact-checking and evidence-based research skill for DeepSeek Harness: it types the request first (verify / explain / causal / compare / survey / metric), confirms the direction and runs a feasibility check, then emits a report skeleton that matches the re

    dsh plugin add dsh-fact-check
  • dsh-typesafe v0.1.0 Verified Web UI 2

    TypeSafe Jev (System One decision model) for DeepSeek Harness: typed decisions in three question primitives, confidence-gated routing, a cost meter, and an automatic prompt-injection guard over untrusted tool results.

    dsh plugin add dsh-typesafe
  • dsh-jev-subagent-dispatch v0.8.0 Verified Web UI 1

    Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)

    dsh plugin add dsh-jev-subagent-dispatch
  • dsh-plan-checkup v0.1.1 Verified Web UI 1

    Plan Checkup for DeepSeek Harness: checks each step of a plan with Jev or a local LLM before you approve it, and marks the results on the plan review card.

    dsh plugin add dsh-plan-checkup
  • lgtm-dsh v0.2.7 Verified Web UI 1

    DeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.

    dsh plugin add lgtm-dsh
  • dsh-plugin-jev-router v0.1.0 Verified 1

    Per-turn model and reasoning-effort routing for DeepSeek Harness -- one Jev choice question per turn

    dsh plugin add dsh-plugin-jev-router
  • dsh-jev-guard v0.5.9 Verified 1

    Pre-execution safety valve for DeepSeek Harness: a TypeSafe Jev question decides whether a shell command/script would irreversibly delete or overwrite real data. Four states (allow/revise/block/escalate), mounted on tools/pre-execute. Zero dependencies; W

    dsh plugin add dsh-jev-guard
  • dsh-plugin-jev-compaction v0.1.0 Verified 1

    Jev-scored context compaction for DeepSeek Harness -- keep the messages that matter, compact the ones that do not

    dsh plugin add dsh-plugin-jev-compaction
  • dsh-jev-verify v0.9.0 Verified Web UI 1

    Jev (TypeSafe System One decision model) for DeepSeek Harness — seven tools: jev_decision (up to 25 typed questions in one parallel call, measured median 266-484 ms), jev_choose (rank 2-10 approaches), jev_batch (one set of up to 5 judgments over 1-20 tex

    dsh plugin add dsh-jev-verify
  • dsh-typesafe-ai-skill v1.0.1 Verified 1

    把 TypeSafe / Jev(System One 判断模型)的构建技能注册进 DeepSeek Harness 的全局技能层:分类、路由、打分、抽取、置信度门控这类「让 AI 做判断」的任务,每个会话都能直接调用。不含任何密钥,API key 由使用者通过 OPENROUTER_API_KEY 环境变量提供。

    dsh plugin add dsh-typesafe-ai-skill
  • dsh-quality-lens v0.1.2 Verified Web UI

    为每个 DeepSeek Harness 回答做质量与话题关联体检,并给出可复制的提示词改进建议。只观测不改写,默认本地评分,可选 Jev 精评。

    dsh plugin add dsh-quality-lens
  • dsh-jev v0.2.13 Verified Web UI

    决策模型原生工具插件:70ms 极速结构化决策、意图分流与状态打分。可直接下拉选择 dsh 已配置的提供商与模型(接口地址与 API Key 由提供商配置解析),也可手写 baseUrl / API Key / 模型 ID;决策模型按 /v1/models 的 modality 字段、静态 modality 与 classifier 协议识别;默认仍为 TypeSafe Jev 官方地址,支持 /v1/systemone 与 /v1/decisions 端点。

    dsh plugin add @weniatall/dsh-jev
  • dsh-jev-mcp v0.2.2 Verified Web UI

    Run the Jev MCP server inside DeepSeek Harness. Typed judgment tools (verify, screen, find, review, gate, and the rest) register as mcp__jev__*. Provider keys stay in DSH credentials. Jev is not a chat model.

    dsh plugin add dsh-jev-mcp
  • typesafe v0.7.3 Verified Web UI

    TypeSafe AI's Jev decision provider for dsh-ai-providers.

    dsh plugin add @dsh-ai-providers/typesafe
  • dsh-jev v0.1.1 Verified

    Jev (TypeSafe System One) as a Cordis service for DeepSeek Harness: one headless decide() call, no tools, no policy.

    dsh plugin add @wowyuarm/dsh-jev
  • dsh-decision-engine v1.8.0 Verified Web UI

    dsh-decision-engine: a cheap judgement layer for DeepSeek Harness — a small decision model answers structured questions before the main model acts, so calls can be allowed, escalated, rerouted to a cheaper model, or skipped. All eight decision points (too

    dsh plugin add dsh-decision-engine
  • dsh-approval-review v0.6.4 Verified Web UI

    Codex-style auto-approval for DeepSeek Harness. An independent reviewer decides allow/deny, fail-closed, with a rationale for every decision. Engine: an LLM route, or TypeSafe's Jev (`reviewer.engine`). · DSH 插件:独立复核器裁决,引擎可选 LLM 路由或 Jev。

    dsh plugin add dsh-approval-review
  • dsh-decision-jev v0.2.2 Verified

    Jev (TypeSafe System One) adapter for the dsh decision layer

    dsh plugin add @techs/dsh-decision-jev
  • dsh-jev-guardrails v0.1.1 Verified

    DeepSeek Harness plugin: Jev-backed guardrails for prompts, tool calls, tool results, and model responses.

    dsh plugin add @codebam/dsh-jev-guardrails
  • dsh-auto-model-routing v0.7.1 Verified Web UI

    DeepSeek Harness plugin: independent Jev capability and effort decisions, enforced fresh-child routes, decision visibility and allocation feedback

    dsh plugin add dsh-auto-model-routing
  • dsh-jev-loop v0.1.3 Verified

    Jev (TypeSafe System One) judgments at the DeepSeek Harness agent-loop gates: pre-step, pre-execute, post-execute, and turn-stopping. No UI dependencies; mount it in any Harness composition.

    dsh plugin add dsh-jev-loop
  • pi-jev-find v0.2.1 Verified

    Semantic find tool for the pi coding agent and the DeepSeek Harness — a cascade-search port of jegrep / oh-my-pi jfind

    dsh plugin add pi-jev-find
  • dsh-typesafe v0.1.5 Verified

    TypeSafe (System One / Jev) decision primitives as a host service: typed noul/choice/score judgements through one named-question registry, with credential-reference key resolution, bounded timeout, retry, circuit breaker, cache and decision logs. Other pl

    dsh plugin add @khorsheed/dsh-typesafe
  • moqi-jev-loop v0.1.3 Verified

    The /JevLoop control panel for moqi: gates and API key from dsh-jev-loop, rendered through moqi's tuiHost seam.

    dsh plugin add moqi-jev-loop
  • effort v0.1.2 Verified Web UI

    dsh Web-only plugin: jev System One lowers reasoning effort to low for simple turns, with a dismissible composer hint

    dsh plugin add @dsh-jev/effort
  • dsh-run-watchdog v0.1.3 Verified Web UI

    Purpose-aware monitoring for DeepSeek Harness long-running commands

    dsh plugin add @mskyurina/dsh-run-watchdog
  • dsh-jev-compaction v0.2.4 Verified Web UI

    Jev/System-One semantic pruning of stale tool results for DeepSeek Harness; keeps conversation text verbatim and forgets stale tool output before summary compaction is needed

    dsh plugin add @yadsh/dsh-jev-compaction
  • dsh-jev v0.1.4 Verified

    Jev (TypeSafe System One) as a Cordis service for DeepSeek Harness: one headless decide() call, no tools, no policy.

    dsh plugin add @contexera/dsh-jev
  • dsh-jev-ultrafast v0.1.0 Verified Web UI

    Drive a browser from one natural-language goal: TypeSafe Jev picks the next operation and target from an indexed element table, so a DeepSeek Harness session spends one tool call instead of one turn per click.

    dsh plugin add dsh-jev-ultrafast
  • jev-review v0.0.103 Verified

    TypeSafe Jev approval review for Pi and DeepSeek Harness

    dsh plugin add jev-review
  • dsh-subagent-custom v0.1.1 Verified Web UI

    Subagent model control for DeepSeek Harness: pick a subagent model by hand per session, or let Jev assign one per task — both enforced on the subagent's own request.

    dsh plugin add dsh-subagent-custom
  • dsh-agent-dispatch v0.3.0 Verified

    dsh plugin: Jev-guided dispatch advice — before a turn starts, a TypeSafe Jev call decides whether the task belongs to a registered agent and which one, then injects a four-line, ignore-if-unsuited recommendation. Jev-optional: no key means silence.

    dsh plugin add @aiwayds/dsh-agent-dispatch
  • dsh-jev-progress v0.5.5 Verified Web UI

    JeV 思维链外显:将 DeepSeek 的任务规划、进度与阶段小结呈现为聊天正文,支持轻量摘要、原生翻译及父子任务流程图,不改主模型上下文

    dsh plugin add dsh-jev-progress
  • dsh-session-prefix v0.1.1 Verified Web UI

    Auto-classify DeepSeek Harness sessions via Jev decision models or Agent tools, displayed as title emoji prefixes (wip 🚧, review 👀, done ✅). dsh-session-prefix:基于 Jev 决策模型或 Agent 工具为会话自动分类,并将任务阶段直观展示为标题前缀 Emoji。

    dsh plugin add dsh-session-prefix