Plugins

Import chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness

技能创作器：教 agent 按 agentskills.io 规范编写高质量 SKILL.md 技能（frontmatter、渐进式披露、触发描述）。改编自 Anthropic 官方 skill-creator（Apache-2.0）。

DeepSeek Harness community Bundle for local, evidence-backed Agent Memory

A single project operating map for DeepSeek Harness.

DeepSeek Harness (dsh) connector for OpenAgentNetwork (OAN): Gofer messages land in a connector-managed inbox and the agent answers them with oan_* tools. Join with one command.

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Paddock: constrained local filesystem MCP server for agents — text read/write, directory ops, filename and content search confined to configurable zones, with zero runtime dependencies and a dsh bundle.

Doctrove: versioned library documentation retrieval MCP server for coding agents — catalog lookup, version selection and focus-ranked doc extraction, with zero runtime dependencies and a dsh bundle.

Local-life toolkit for DSH agents: budget planning, bill splitting, unit-price and discount math, common unit conversions (jin/li/chi, C/F, L/gallon), and trip checklists.

Education toolkit for DSH agents: lesson-plan skeletons by grade band, quiz scaffolding and answer-key validation, analytic rubrics, Anki/markdown flashcards, and readability levels.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.

Manage DSH rules from the web settings panel — edit global/project AGENTS.md, or auto-split pasted rules into layered AGENTS.md and skills via LLM.

Un poste de travail de projet et d'IA façon bureau pour DeepSeek Harness.

Budgets par tour à échec fermé pour les étapes, appels d'outils et tokens de fournisseur, pour DeepSeek Harness.

Agents planifiés par cron : exécutez un prompt selon un planning et recevez le résumé là où vous êtes déjà, avec des valeurs de sécurité par défaut pour le chevauchement, les exécutions manquées et les délais dépassés.