llm 98

AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

The strongest free web search plugin for coding agents. Plug-in web search, X search, and page fetch for models without native web access. Free out of the box: no signup, no API key (Firecrawl keyless, 1,000 free credits/month)

Use ChatGPT (Codex), Claude, Grok (X Premium), and GitHub Copilot subscriptions as DeepSeek Harness LLM providers, with OAuth login from the web Settings page

Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page card and live model catalog.

Local-first DeepSeek Harness control center for balance monitoring, usage accounting, a 365-day local token ledger, Z.ai Coding Plan quota monitoring, official pricing sync, peak/off-peak status, encrypted multi-account switching, health checks, completio

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse

Tiered model router for DeepSeek Harness: routes auxiliary calls (session title, compaction) and subtasks to light models, escalates hard tasks to strong ones — automatically, per request, across providers.

DeepSeek Harness Web plugin that renders streamed assistant Markdown with markstream-react.

Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.

OpenAI Codex provider for DeepSeek Harness with device-code OAuth, Codex CLI import, token refresh, and a web settings panel.

Command Code provider plugin for DeepSeek Harness (dsh) — works with every Command Code plan including the $1 Go plan; uses the Studio authentication API key over /alpha/generate, not the Provider API

DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, test engineer, code engineer, QA, code reviewer, security reviewer, doc reviewer) that talk through files on disk, with the PM as the

A general-purpose knowledge base plugin for DeepSeek Harness (DSH): import documents (md/txt/json/yml/docx/pdf), organize them in folders, and search with FTS5. 通用知识库插件：文件导入、目录化管理、全文检索、知识库管理 UI。

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

DeepSeek Harness plugin that uses configured model providers for image analysis and context compaction.

OpenTelemetry traces, metrics, and logs for DeepSeek Harness, written straight into GreptimeDB.

Zero-config Exa web search provider for DeepSeek Harness (dsh): keyless anonymous MCP fallback (mcp.exa.ai/mcp) plus keyed REST search — a drop-in WebSearchProvider for the ctx.web seam, no API key required.

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

DSH 模型代理插件：按模型走代理（Clash 等）+ 失败自动重试，设置页实时生效。

DeepSeek Harness plugin: auto-repairs an invalid messages array (orphaned tool_calls / tool messages) to stop 400 INVALID_REQUEST session lock-ups.

Connect a stock DeepSeek Harness install to DSH Cloud: device login plus a 20-model gateway provider. Commercial hosted service by AgentsDance AI — new accounts include 500 free credits.

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.

Tencent CodeBuddy plugin for DeepSeek Harness (dsh).

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.

DSH Web 会话头部大模型余量监控插件：当前模型额度徽标 + 全部提供方详情弹层 + 用量统计页签

Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi

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

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

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.

DSH 模型检测：对任意 pi-ai 提供方，拉取其线上最新模型清单，并用 models.dev 自动富化正确模态/容量/推理后写入该提供方

Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit

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

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.

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

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.

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

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.

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

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

Use OpenCode models inside DeepSeek Harness without a separate provider API key.

DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel

AgentTeams for DeepSeek Harness: durable teammates, task DAG, read-only role isolation

DeepSeek Harness (dsh) plugin that snapshots your workspace at every turn into a shadow git repository, so you can restore the files to any earlier turn. Your own .git is never touched, and plain directories work too.

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

Explicit, evidence-first multi-model consultation for DeepSeek Harness

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

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

Rate-limit plugin for DeepSeek Harness: FIFO queue per provider/model bucket with minIntervalMs and maxConcurrent