Plugins

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Pont runtime entre DSH et le moteur Godot : lancez et pilotez un jeu Godot 4.x en cours d'exécution via son serveur d'interaction TCP intégré au jeu — 8 outils (inspection de scène/UI, évaluation GDScript, simulation d'entrées, captures d'écran, opérations statiques headless, validation de script), remplace godot-mcp.

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.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

A web-novel writing engine for DeepSeek Harness: parallel drafting, outlining and brainstorming with a separate DeepSeek key, lore and foreshadowing management, semantic vector retrieval, a corpus library, usage ledger, mechanical proofreading, and a local serialization plan.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Évaluateur d'expressions mathématiques sécurisé, avec un analyseur syntaxique à descente récursive sans dépendance.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Harness d'évaluation pour les plugins DSH : des cas au format YAML pilotent de vraies exécutions d'agent en mode headless, avec des assertions sur les appels d'outils, les arguments, les résultats et l'utilisation des tokens, ainsi qu'une barrière de référence pour la non-régression en CI.

Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

RAG à double graphe de connaissances pour notes Markdown : graphes de prérequis + de similarité (parcours P/S-Agent), découpage par paragraphe, recherche hybride n-gramme/embedding et boucle explicite de retour de pondération — via MCP.

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Surveys local code and GitHub/npm for reusable implementations before development, evaluates reuse versus rewrite, and checks architecture coupling.

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

Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.

Biomimetic memory system for DeepSeek Harness: plain-Markdown data layer, memory tools, frozen-snapshot injection, graded approval gating, structured audits, memory metabolism (dream), memory pins, semantic recall, /memory command, and cross-session retrieval.

Un plugin de méta-agent natif au modèle pour DeepSeek Harness : le modèle synthétise à l'exécution des workflows spécifiques à la tâche à partir de cinq patrons de workflow agentique (chaînage de prompts, workers parallèles, routeur, superviseur, boucle d'évaluation) et coordonne les outils et les sous-agents.

Génère des packs de base de connaissances auditables (SQLite FTS5) à partir de md/txt/docx/pdf, avec récupération déterministe et lecture du texte original.