Plugins

Installs four multi-agent math-research presets for DSH: v2 (probability-driven pipeline with multi-verifier debate), v3 (paper-style Markdown knowledge base with a planner agent and a reusable method library), v4 (persistent self-organizing residents that message and meet), and v5 (a research institute with an academician who decomposes and assigns work, voting researchers, temp workers, group chat and a compare-and-set task board); all four support checkpoint resume, human intervention, and an optional Lean formal-verification switch (off/encourage/require) whose passing proof turns the vote into a fidelity check of the Lean statements.

Text-first computer use for DSH: background Chromium control via Playwright/CDP plus accessibility-first macOS control; actions stay pinned to the right process and window without taking the user's pointer, ships a Developer ID signed, notarized Universal 2 DMG.

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

aginxbrowser plugin for DeepSeek Harness: fetch JS-rendered / Cloudflare-protected pages as clean markdown, aggregated web search (Baidu/Sogou/WeChat and 11 more), and indexed interactive sessions (click / type / scroll / eval / screenshot) against a host

Block-addressed document editing: an MCP server exposing geml_get / geml_set / geml_check and friends, so an agent reads or rewrites one addressed block of a Markdown or GEML document instead of the whole file. Ships the GEML authoring skill and a code-graph skill that builds and navigates a project call graph as GEML codemaps.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, and a diff of what changed since the last scan

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

Long-term memory for DeepSeek Harness: multi-channel retrieval and an evolving memory store.

Live flowgraph visualization for DeepSeek Harness sessions, including tool calls, parallel groups, subagent branches, and drill-down details.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Connects DeepSeek Harness to Multisim MCP for circuit generation, simulation, diagnostics, design optimization, and experiment report export.

Read any page as clean main content: charset auto-detect (GBK/GB2312/UTF-8/Big5), noise stripping, compact text/Markdown, offset continuation, optional SPA rendering, batch reads and site crawling.

StrataGate gives DeepSeek Harness evolving, local-first long-term memory for user preferences, project decisions, conversations, and tool results across sessions; it layers history with user-tunable time decay, reinforces memories through real answer use, shows workspace-aware usage counts, and keeps recalled evidence traceable to its original messages.

ClearAI: The Epistemic Loop, native to DSH.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

A zero-residence context engine: large tool payloads are evicted from the live context into a queryable store, only pointers stay behind, and any payload can be reconstructed verbatim on demand — so per-turn prompt tokens stop growing with the transcript. It ships four capabilities: zr_recall rebuilds masked originals by tool-call id or session sequence from the persisted session log (the content is not resident, never lost), zr_ledger reports the attention integral and a three-part cost breakdown, zr_compact arms one forced compaction, and zr_fast runs long commands asynchronously and hands back a handle immediately.

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.

The memory organ of Agent-Body: after 2 minutes of silence it enters light sleep and after 5 minutes deep sleep, where deterministic rules distil real experience into memory cards (pitfalls, playbooks, hotspots, unresolved issues, facts). Incoming commands recall related cards by keyword and inject them into context; cards unused for long decay on a half-life and are archived rather than deleted. It also de-noises body-wide homeostasis warnings: repeats inside a window are counted instead of re-printed, and a warning that keeps recurring without ever healing converges into a known steady-state offset and goes quiet. Consolidation and recall make no model calls.

Browse every message you sent in the current session: full-history listing with newest-first sort, text filter, one-click copy, and jump to a message (auto-loads earlier history when the target is not yet loaded).

Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.

Goal lifecycle management for dsh with an interactive kanban board: goals, criteria, attempts and reviews live in the workspace, driven by graph_* tools, with a two-lane board rendered in the conversation view.

Install suites from any Claude Code, Codex, Cursor, Kimi or agent-plugins.org git marketplace repo — skills, MCP servers, hooks and slash commands are injected into DSH sessions at runtime, with a market page in the Web GUI.

Fail-closed password authentication proxy bundle for the DeepSeek Harness Web profile