DeepSeek Harness Plugins
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
Seamlessly connect DeepSeek Harness to your local Obsidian vault, enabling agents to search, read, write, and manage Markdown notes directly via the file system without extra servers.
A local usage and billing dashboard for DeepSeek Harness, featuring token tiers, multi-vendor pricing, price-hike comparisons, and shareable stat cards.
A layered distillation memory plugin for DeepSeek Harness that automatically captures, distills, and injects relevant context before model inference.
Independently assign models for the main conversation, subagents, and plan execution in DeepSeek Harness, eliminating frequent switching and automatically restoring the main model afterward.
Seamlessly routes DeepSeek Harness's built-in web search and fetch tools to Firecrawl, providing secure cloud-based scraping, JS rendering, and anti-bot handling without altering the model's tool usage.
Quickly view, search, and jump to all your sent messages in ultra-long conversations, featuring full history retrieval and one-click auto-scrolling.
Adds a Photon-hosted iMessage transport to DeepSeek Harness, allowing users to send prompts and receive AI responses via a bound phone number.
Connects Garmin fitness and health data to the AI agent, enabling queries for activities, sleep, and heart rate, while offering personalized running coaching and FIT file downloads.
Enhances the DSH @ menu by integrating multiple reference sources—including commands, files, sessions, local and external AI conversations, and cloud drives—into a single searchable interface.
Automatically distills your explicit corrections, constraints, and workflows in DSH into reviewable native Skill drafts, saving them for future reuse only after your confirmation so your experience never fades with the session.
A testing engineering skill framework for AI agents that empowers them to act as senior QA engineers, executing end-to-end testing pipelines from requirement analysis to test case generation and automation.
Automatically appends the x-opencode-session header to model requests targeting opencode.ai, with a stable per-conversation value that persists across restarts and requires no extra state.