948 results
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.
Feynman learning-mode plugin for DeepSeek Harness: /learn on|off, structured lesson cards, rich HTML teaching.
Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and licensed MIT.
Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets
Tensorlake sandbox execution providers for DeepSeek Harness
Give DeepSeek Harness agents live control of your ComfyUI canvas (local or cloud): embed it as a split-screen tab, then read/edit/run workflows, debug errors, fetch output images, and batch-sweep parameters straight from the chat. Ships the ComfyUI-side bridge node.
DeepSeek Harness bundle plugin: makes the existing bash tool run Git Bash on Windows and disables pwsh (Reasonix-style, token-frugal)
DSH host plugin that detects when the DeepSeek Harness service has restarted and wakes the main agent at boot with a notice, so interrupted work can be resumed.
CodeGraph for DSH — registers native `codegraph_*` tools (core surface: status/init/sync/explore; full surface adds query/node/files/callers/callees/impact/affected/index/uninit) wrapping the `codegraph` CLI, plus a prompt front-load hook that steers structural CodeGraph context into structural prompts, so the DSH agent can bootstrap, maintain, and query a pre-indexed code knowledge graph without grepping files.
dsh-skillport — every skill you already have (Claude Code, Codex, Cursor, Gemini CLI) works in DSH: Agent Skills SKILL.md discovery across .claude/.agents/.dsh/.gemini + extraPaths, Tier-2 conversions (cursor rules, claude commands, context files), find_skill search, and a skills doctor
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 only voice to the user.
DSH split-pane conversation plugin: PiUI-style multi-pane conversation surface — split/stack panes, per-pane sessions, sidebar session drag & drop, single-row fused header. No core patch required: each pane runs the core's own slot renderer against a pane-scoped host.
Hard gate for self-modification restarts: a green-build credential bound to the git HEAD, checked before any restart of the running instance
Codex-style desktop pet for the DSH web GUI: a floating animated sprite driven by the agent's running state
Click any UI element in your running dev page to jump to its Vue / React / Svelte / Angular source in the DSH chat. A click-to-source inspector for DeepSeek Harness, compatible with dsh-better-sidebar.
Claude Code outputStyles-equivalent runtime output-style switching for DeepSeek Harness
Remote Host Tunnel Manager for dsh: allocate and register remote ports, run dsh web on a remote Linux server via systemd, and keep a resilient SSH tunnel from this machine to it.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
Multi-agent orchestration for DeepSeek Harness: assign work, review results, and run DAG workflows between live sessions — without you as the messenger.
Hook DeepSeek Harness into your Hermes pipeline: dispatch-spec template, model-tier routing, quality gates, git single-writer rule — as an installable skill pack.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
DSH extension suite: runtime injector, task-aware reasoning-mode routing preset, cross-session mailbox, agent teams, model delegation, skill manager, and plugin-manager UI.
Prompt enhancement for the dsh web GUI: rewrite the composer draft into a well-structured prompt through the harness LLM service, preview the before/after, then fill back, copy, or undo. Original draft is always preserved.
Gives the DeepSeek Harness agent a configurable humanized whale-girl maid persona (address, self-name, speaking mode), an immersive no-plugin-meta rule, and a lightweight layered memory with query-triggered recall.