ai-agents 44

A DSH plugin for fiction, short-drama, interactive-game, and video-recap production

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

A persistent agent team for long-running collaboration in DeepSeek Harness

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration (single-package edition)

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh), with multi-agent DAGs, live execution, recovery, and Feishu integration

Harness-neutral reliability infrastructure for AI coding agents: reversible destructive actions, pre-emission redaction, recovery evidence, and a shared Decision Protocol with optional native adapters.

Sabi inference adapter bundle for DeepSeek Harness (DSH).

Use AI agents from the DSH session UI.

DeepSeek Harness adapter for Koma Miko Agent Specs.

dsh「专家团」bundle：一句自然语言组建角色化多智能体「数字员工」团队，按九阶段门控流水线协作交付，实现者直接改代码并产出持久工件；带 live 团队浮层。 · Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out.

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill toggles, zero tools, zero-cache-miss | DeepSeek Harness 插件：DietrichGebert/ponytail 懒人 senior 模式与七阶梯子完美移植，6 个技能描述双语自由切换

DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph

DeepSeek Harness Web plugin for visualizing, arranging, branching, merging, and summarizing AI agent sessions on an interactive graph canvas

Run Pi extensions as agent-scoped DeepSeek Harness plugins

DeepSeek Harness plugin for Braid: background agent graphs, bounded loops, live updates, and execution progress

MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.

Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).

Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness

Generative UI for DeepSeek Harness — the agent writes TSX, dsh web renders it live, inline in chat and in a canvas panel

Model pricing and capability board for DeepSeek Harness: compare per-1M-token prices, find the cheapest route, and see coding/agentic/vision tags for every LLM you can connect — in the DSH settings UI.

MasterGo Canvas MCP bundle with a managed local sidecar for DeepSeek Harness

A structured work-state protocol for DeepSeek Harness agent handoffs

OpenRouter image, video, and speech generation as dsh tools, shipped as an out-of-tree profile bundle

Rename project conversations into clear, content-based Category｜Topic titles.

Expert Orchestrator — multi-agent orchestration agent preset for DeepSeek Harness (dsh): triage → PM planning → delegate implementation to domain experts via a merged roster (summon_expert), dependency-DAG taskboard, file message bus, tiered delivery gate

Evidence-backed, human-approved project memory for DeepSeek Harness

Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.

Managed, isolated DeepSeek Harness runtimes over OpenSSH with a native Web control surface.

Canon channel plugin for DeepSeek Harness

NeevSandbox execution providers for DeepSeek Harness

Review-first batch automation for DeepSeek Harness: evidence-backed Code to Spec plus safe bulk file organisation with complete manifests, reviewed sidecars, and deterministic ZIP delivery.

A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.

Deterministic fact producers for security auditing: which deleted code came from a security fix, and which changed symbols no test ever executed.

Doco knowledge-base native plugin for DeepSeek Harness (dsh) — search, read, outline and save-draft your Doco KB with block-level addressing. Provides the `doco` service consumed by doco-memory-dsh.

Deterministic fault injection, recovery, and side-effect auditing for DeepSeek Harness agents.

Local HTTP API for DeepSeek Harness: expose DSH session control to other agents

DeepSeek Harness plugin: role-based model routing — both roles default to deepseek-flash (V4.1 Flash, native multimodal) until V4.1-Pro launches.

DeepSeek Harness plugin for Readproof: stable readproof:// identity, freshness policy, snapshots, per-run manifests, diff, byte-exact replay, and evidence bundles as model-callable tools.

Local AI memory for DeepSeek Harness: remember, search, and context tools over a built-in SQLite store

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

DSH 对抗多智能体三层失效的防御插件：读取台账去重度量(read-ledger)、免疫压缩规则区+完成机械门禁(immutable-core+completion-gate)、低成本审查lane(role-router)。零外部依赖，注入即用。

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable