L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Evidence-backed UI delivery for coding agents working on existing Web products: declared criteria, criterion-bound artifacts, findings linked to declarations, and repair guidance. Evaluator review does not replace human semantic approval.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Run AI coding agents unattended for hours and ship PRs worth merging. Cybernetics-based multi-agent orchestration + cross-LLM peer review for Claude Code, Codex, and Gemini. Engine-enforced gates, fresh agent per checkpoint, cross-vendor review before every PR.

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

Visual Kanban board for DeepSeek Harness: Gitea and GitHub-backed tasks, workflow columns, and a dedicated agent session per task.

Core Goal Addon (Token Budget, Milestones, Git Snapshots & Retrospective Reports) for DeepSeek Harness

Autonomous trading agents for Robinhood Chain, inside hard on-chain limits. Use it from Claude: tell Claude "set up merrymen mcp", or add it in one click at merrymen.dev/claude

Prompt enhancement for the dsh web GUI: rewrite the composer draft into a well-structured prompt through the harness LLM service, preview the before/after, then fill back, copy, or undo. Original draft is always preserved.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

Opinionated AI agent skills for building applications with MotherDuck

A reliable coding agent for complex software engineering tasks.

Lark/Feishu IM bot channel for DeepSeek Harness | 飞书 DeepSeek Harness （DSH）插件

Branch from any answer and keep branching at any depth. Recursively isolated follow-ups that leave the main DSH task untouched.

Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

AI agent skills for Sealos — deploy any project, provision databases, object storage & more with one command. Works with Claude Code, Gemini CLI, Codex.

Claude Code scaffolding and first steps for complex brownfield projects

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

Moteur de recherche libre sur le droit français et européen — jurisprudence et textes (loi à n'importe quelle date), en web, API et MCP. Free search engine for French case law and legislation.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.