1118 results
Named subagent library for DeepSeek Harness: a settings-driven roster of role subagents (model + persona + tool filter), exposed to every session through the list_subagents and delegate tools, a /subagent command, and a Settings page.
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
Sync opencode-go models from https://models.opencode.ai/api.json into llm-pi-ai provider opencode-go-autosync (one-click create/update in settings).
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Token usage statistics for DeepSeek Harness: last-7/30-day per-model daily and total consumption (bar chart + donut), plus a GitHub-style contributions heatmap over the last year.
Cross-platform Web UI launcher plugin for DeepSeek Harness: webui_start/stop/status/open model tools, a /webui slash command and a Settings-page launch card.
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
DeepSeek-dealt blackjack for the DeepSeek Harness: a 21-point table where the model deals and trash-talks as one of two personas, with event-sourced rounds. A dual-face dsh bundle: host service + browser sidebar UI, installable from GitHub.
Enhanced subagent delegation tools for DeepSeek Harness: per-call model/provider/persona/toolFilter overrides, @preset: references, and provider/model composite ids — zero patches, bundle.
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
Fail-closed microsandbox microVM provider and model-facing guest tools
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
Offline QR code generator for DeepSeek Harness (dsh): pure-JS, no network, no shell, cross-platform. Model tools (qrcode + barcode) with SVG/PNG/ASCII output.
Skill Radar for DeepSeek Harness (dsh): scan the current session's visible skills, score their relevance against the recent conversation, and recommend which skill to load. Model tool + optional interactive panel.
DSH recap plugin: distills every model request (turn:step) of a session into one sentence, appended incrementally with a cache-friendly prompt (history sentences first, new delta last). Side-effect-free for the agent loop.
Ollama native protocol (/api/chat) provider for DeepSeek Harness: llm-ollama settings namespace, serving LlmAdapter, /api/tags model discovery, and a whole-page Ollama settings section.
DSH plugin: Sisyphus agent orchestration — star topology, single-line blocking, 7 specialist sub-agents (Hermes/Explore/Librarian/Looker/Hephaestus/Prometheus/Oracle) with per-type model binding, go_work/continue/need_help/forward communication tools, Web UI tree panel and settings.
Manage OpenCode Zen free-tier and Go-tier models in settings.yaml: live model listings from opencode.ai, configured-versus-live drift per route, add/remove through four agent tools plus an OpenCode Models settings section.
Per-message delete for DeepSeek Harness — a trash icon beside the copy button on every chat message that removes that message from the derived model context (and the visible transcript) via the official surface-replace contract
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.
Cost dashboard for DeepSeek Harness - model spend, tokens and cache usage across all sessions (settings section). DSH 费用看板：汇总全部会话的模型输入/输出/缓存 token 用量并按价格表计费。