638 results
Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval-gated handoffs and a shared timeline that survive DSH restarts.
Native Cordis WeShop canvas, tools, skills, and Web UI for DeepSeek Harness
OOMOL Connector integration for DeepSeek Harness: connect apps and call Actions through progressive MCP discovery.
Matt Pocock's skills for the DeepSeek Harness: grilling, writing-for-agents, wait-what and more — adapted from https://github.com/mattpocock/skills
Wanjiqi (6657 live room) meme Skill for DeepSeek Harness (DSH): 22,771 real barrage memes distilled into an AI skill - wanjiqi-style barrage memes, CS x DOTA cross-memes, player roasting and casting banter. / 玩机器(6657直播间)烂梗 Skill：22771 条真实弹幕烂梗蒸馏成 AI 技能——玩机器式弹幕烂梗、CS×DOTA 双料梗、选手锐评与解说吐槽。
DSH agent preset: chief coordinator + 17 domain-expert subagents with taskboard scheduling, quality gates, and real inter-expert communication bus (专家模式)
Oh My DSH: bounded autonomous orchestration and dynamic Cordis self-extension for DeepSeek Harness
Reduce large agent tool output by what it means, not by where it was cut.
Edit ~/.dsh/AGENTS.md (global rules) from the web settings panel.
Live Agent Teams task, communication, subagent, and Workflow topology for DeepSeek Harness
Interactive pi-tui terminal front door for DeepSeek Harness agents
Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
OpenViking retrieval, resource management, auto-recall and session memory for DeepSeek Harness.
Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client
Standalone DeepSeek Harness plugin: continual harness self-evolution. The agent persists and refines reusable prompt notes, memories, skill contracts, and subagent specs through small evidence-backed edits, with automatic refinement gates, rollback, and prompt injection.
DeepSeek Harness-native publicity toolkit: turn any long-form source into a source-grounded, platform-native promotion matrix.
Browser4 skills bundle for DeepSeek Harness — AI-native browser automation (browser4-cli) for autonomous agents, intelligent extraction, and large-scale web automation. Registers the Browser4 skills (browser4-cli, browser4-experience, browser4-plugin, scent-miner) into the DSH skill registry.
Model-selectable subagents and guided model routing setup for DeepSeek Harness
Codex-style drag-drop for DSH web GUI: drag any file, it lands in ~/.dsh-dropbox, and the path lands in the composer as a whole blue chip (the mandatory .b64 suffix is display-hidden; the real path serializes on submit). Hot-pluggable: install with `dsh plugin --profile web add ./plugins/file-upload`, no dsh source changes.
Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.
Runtime requirement drift guard for DeepSeek Harness — keeps long-running agents aligned with user intent while they work.
Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. DSH plugin host; Python stdlib + Markdown core. Zero database / vector service / external service dependencies.
DSH peer link — point-to-point messaging between dsh agents and other local agent sessions (e.g. Claude Code) over unix sockets. Independent plugin: register as a peer, receive messages into agent context, reply with peer_send, list peers with peer_list.
Route DeepSeek Harness agent requests by role: planner model in plan mode, default model otherwise, subagent model for subagents.