Plugins

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

Graphe de mémoire spatio-temporelle multi-agents avec persistance inter-sessions et rappel filtré par importance.

Auto-évolution continue : un état de harness versionné, auditable et sûr en cas de retour arrière (prompts, mémoire, skills, spécifications de sous-agents), affiné à partir des trajectoires de session, avec des points de contrôle de revue et des skills rechargés à chaud.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Suite d'agents de recherche : contrôle d'objectifs à long horizon avec des chaînes de preuves auditables, planification cron, équipes d'experts multi-agents, mémoire de recherche auto-évolutive (rappel FTS5 + RRF), espaces de travail par projet, et une UI d'espace de travail personnalisée.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

DeepSeek Harness plugin and bundled Skill for safely evolving Cordis Candidates with Harbor.

KiroCrew bridge for DeepSeek Harness: let your dsh agent delegate to a persistent, self-evolving KiroCrew workspace over ACP (JSON-RPC 2.0 over stdio).

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.