Plugins

Pair a second model that passively reviews each turn and injects notes.

Usage statistics settings panel: 26-week activity heatmap, daily token trend with a cache hit-rate curve, per-model donut and breakdown, time-range filters, summary cards, one-time historical backfill and lossless rebuild.

Idle session reminder: prompts to archive sessions untouched for N hours, with a snooze window after each refusal, using the official archiveSession API.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

Fills in what the official pi-ai adapter leaves out on the Models page: gateway reachability probing with latency, one-click pull of the gateway model catalog with checkbox write-back into settings, DeepSeek balance and provider quota shown in place, the protocol and endpoint each provider is actually wired to, and a model dropdown that lists only what works right now — a dead key, an empty balance or an exhausted quota is hidden until you fix it, and comes back on its own.

Edit a sent message to rewind and branch the conversation from that turn, switch versions with a counter under the bubble, and browse every branch in a turn-level version tree.

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

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

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.

Learning mode that explains each agent step (WIP).

Per-model appearance for the DSH Web UI: an ordered rule list matched against the current session model name, each rule carrying its own wallpaper, theme colour, layout mode, framing and wallpaper opacity and blur, plus per-surface opacity and frosted-glass blur for the main background, left panel, right panel, cards and panels, input and controls, settings panel, conversation text frame and trajectory view.

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, fetch/pull/push sync, branch and remote management, git init, multi-repo switch, color-coded file status, file-type icons), an editor view that opens every file reached from the chat, the file tree or source control (Markdown/HTML/PDF/image previews, 15-language syntax highlighting, hunk-level diff editing, Ctrl+S save), file operations (new/move/copy/delete, reveal in file explorer), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), and commit messages generated from the staged diff by a host-configured model.

AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.

DeepSeek Harness (DSH) Cordis plugin exposing aflare workflow tools

Per-event sound notifications: turn completion, approval, question, plan-review, goal-blocked, and task-failure each get their own sound and volume, configurable in the Web UI (built-in synth, mute, or local audio file).

Better streaming text animation for DeepSeek Harness.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Seven agent-preset modes for DeepSeek Harness, each with a fixed tool boundary, per-mode model routing and fast/deep omd_task delegation tiers, plus a plan-to-execute loop (/mode, /start-work, goal-backed /ulw) and a settings page that remaps models per mode and per tier.

A polished floating whale desktop pet for the DeepSeek Harness Web UI with 95 categorized transparent animations, state-aware event reactions, customizable actions and triggers, click interactions, dragging and screen wandering.

Embeds Copree (formerly AIsChat) into the DSH web UI as a native sidebar board. Copree is an open-source framework for AI group chat and programmable worlds: the AIs are residents, not tools — each has its own memory, state and personality, they talk to each other on their own, and you can watch or join in. Group World goes further: every group chat can bind a living world (its own web page + world AI + code + clock) that the world AI builds and edits through DSH workspace tools. This plugin ships the native sidebar board (contacts, pinned DMs and groups), real-time chat over a same-origin HTTP/WS proxy, Markdown/LaTeX rendering, group invites and image messages, immersive full-frame pages, and one-click mirroring of your worlds into DSH workspaces (folder + DSH session + world_* tools). Front end only: it proxies to a Copree backend you run yourself (default 127.0.0.1:5228, same repository).