llm 220

MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.

team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.

Free OpenCode Zen models for DeepSeek Harness (DSH): native dsh-llm adapter plugin, no API key.

Per-model LLM call rate limiter for DeepSeek Harness with queue support and a live status panel

Agent plugin — define custom AI agent roles with per-role prompts, models, skills, and permissions

Model policy for DeepSeek Harness (DSH): set_model / list_models agent tools, preset mode with switch_preset / list_presets, a configurable stage-to-model system prompt, plan-mode auto-transition, provider whitelist and context-window guards, active-model

Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).

Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.

DSH 模型检测：对任意 pi-ai 提供方（含 DeepSeek 官方 API 路由），拉取线上最新模型并用 models.dev 自动富化模态/容量/推理后写入；支持手动编辑现有模型参数（多模态、思考档位等）

dsh-yolo-mode —— DeepSeek Harness 双面包插件：当会话处于可写沙箱模式且审批策略为 ask 时，用大模型自动裁决沙箱升权申请，支持内置预设与自定义权限层级，并提供宿主 settings + 自发布设置桥（/yolo-mode）与 Web 客户端 UI。

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

DeepSeek Harness plugin: live account balance/usage panel for every configured LLM provider (draggable floating-ball widget, configurable refresh interval and balance thresholds)

DeepSeek Harness 代理插件：在设置中配置全局 HTTP(S) 代理，或为单个 LLM 提供商单独配置代理 / 直连

Opt-in DSH orchestration bundle for subscription-backed Claude Code and GitHub Copilot delegation.

Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests

DSH plugin: expose Trae Work CN credits as a local OpenAI/Anthropic compatible API for Claude Code, Cursor, Cline and other agents. Ships a DSH web settings page (status, stats, token management, hot-reload config).

DSH 草稿润色：发送按钮左侧 ✨ 一键调用 LLM 润色输入框草稿，可选携带会话上下文帮助模型理解意图；走 DSH llm 渠道，会话进行中也能用

DeepSeek Harness (dsh) plugin: a shell around the dsh-continual-harness self-refinement engine — mounts the engine itself and owns /refine (status / entry browsing / refinement history / one-click rollback / scoped triggers) plus a settings panel; engine

Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a set

Connect your sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok) behind one base URL, with per-key model discovery, usage lookup, global image generation, and a settings page.

Witness — the quality gate for agent-built web apps. Independent browser acceptance testing: CLI, MCP, AI-drafted checklists, visual regression, multi-browser. Agents self-test and pass; real browsers tell the truth.

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

Real-time repetition guard for DeepSeek Harness (DSH): stops generation once the same string repeats >=10 times in a row, with one relaxed threshold for fenced/inline/indented code, table- or module-driven repeat counts, and a derived detection window wri

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key — plus a composer badge showing subscription usage for those routes and for GLM Coding Plan.

Modellix Design, LLM, and Web providers for DeepSeek Harness

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

Capture the literal HTTP request/response of every LLM provider call (by patching globalThis.fetch) and show them in a Wire Trace session tab

Mixture of Agents for DeepSeek Harness: /moa marks a message, multiple reference models assist the main model's summary.

Generative UI for DeepSeek Harness — the agent writes TSX, dsh web renders it live, inline in chat and in a canvas panel

OpenCode Go 动态模型目录插件

保险精算实操专家(算衡)·DSH插件｜真正跑计算：寿险/财险定价、费率与现金价值、利润测试(NBV/VNB/IRR)、偿二代二期准备金(BEL+RM)、EV/NBV、监管报备。Insurance actuary (Suanheng) that actually runs calculations.

DeepSeek Harness provider plugin that delegates ChatGPT subscription access and agent execution to the locally authenticated Codex app server.

Delega tareas, reviews y debates a modelos alternativos (DeepSeek, MiniMax, Ollama, etc.) vía el CLI gateway-companion, sin MCP.

AgentTeams 多智能体团队协作（DeepSeek Harness 插件）：自然语言组队、成员与任务依赖 DAG、信箱通信、右侧栏树状监测 —— 上游 NanmiCoder/dsh-agent-teams 的补充版，新增自定义美术目录、十七厂商头像（十个有厂商 × 岗位全套）与厂商商标徽标。

Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.

LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness

Provider failover for DeepSeek Harness: on rate-limit (429) or quota exhaustion, automatically switch between providers with configurable per-provider models, fall back to the last one (e.g. DeepSeek official), and show a visible notice in the UI.

DeepSeek Harness (dsh) plugin for machine-wide token usage statistics — a Settings page with totals, a contribution heatmap, streaks, and a per-model breakdown. Reads session logs from every dsh home; no cost estimates.

Provider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.

Calendar todo plugin for the dsh web GUI: a sidebar entry plus a week/month calendar where you drag-select time ranges to create tasks, with Eisenhower urgency/importance quadrants, subtasks, pinned execution session + LLM provider, and host-authoritative

Memory plugin with built-in governance for DeepSeek Harness

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

The LLM debug console inside DeepSeek Harness — capture every model call, see everything, replay anything.

A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, adds OAuth/device-code sign-in for subscription providers (C

Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.

Ollama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板

DeepSeek Harness 本地脱敏插件：在 llm/stream 出口拦截发往云端大模型的请求，将密钥、PII、中文实体（姓名/身份证/公司/机关/地址等）替换为占位符后再发送；用户输入与工具结果在写入本地会话日志前同样遮罩，模型回复经入站还原以原值落盘与显示。

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

Provider/model-aware adaptive pacing and visible rate-limit retries for DeepSeek Harness free models.

CodeBuddy LLM provider bundle for the DeepSeek Harness web GUI: registers the `codebuddy` provider route, its Models-page card, and its model picker entries, authenticating against the machine's CodeBuddy desktop-app login, with per-model measured image i