Plugins

Evidence-first guard: warns the agent when it claims success without a matching tool-execution record in recent context.

Boîte à outils de médecine traditionnelle chinoise : diagnostic aux huit axes et recherche de paires d'herbes.

Portes de vérification par calcul réel : simplification mathématique, preuves logiques, validation regex, FOL par E-prover, vérifications de machine à états et réparation de code, adossées à des binaires compilés en Go avec exécutables Windows prêts à l'emploi.

Un coffre Obsidian partagé pour tous les agents : cœur Python sans dépendances (recherche/promotion/arbitrage/oubli), modèle de coffre, plugin dsh (memory_search/show/submit/status).

Rappel de mémoire par mots-clés basé sur BM25.

Runtime extension suite for DeepSeek Harness: cross-session mailbox with wake cold-start, agent teams (captain + members + dependency task board + team_wait), subagent spawn policy with escalation approval, task-aware routing preset, plugin market, skill manager and runtime injector.

Memory Lake as a persistent memory layer for dsh: memory_search, memory_remember, and memory_forget tools over the memorylake CLI, a session status line, and guided setup/diagnostic skills, sharing one ~/.memorylake identity and memory set with the Claude Code and Codex plugins.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Coffre de mémoire inter-sessions : outils remember / recall / forget, injection de prompt par tour, et un navigateur d'entrées accessible depuis la page de réglages.

DeepSeek Harness (DSH) plugin for local-first automatic Wiki memory and native Skill generation.

DSH Web taskboard plugin with workspace-scoped Agent sessions, staged human review, delivery confirmation, and durable archival

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.