Plugins

Evidence-first conclusion gate that cross-checks first-hand claims against a durable per-session tool-activity index, blocks unverified guesses and tracks blocked-versus-converted metrics.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Persistent identity layer for DSH: editable kernel, evidence-based traits, on-demand memory, mood, bond, energy pacing, autonomy and empathy — QQ is one optional channel.

Full upstream REA 6.4.0 integration over the official DSH MCP bridge: all 170 tools, the version-matched reverse-engineering skill, and the six original MCP prompts with argument completions reachable from the composer / menu, all sharing one REA process and complete structured Evidence. External analysis engines are bring-your-own.

Real browser tools for DeepSeek Harness: browse and extract web content, fill forms, manage multiple tabs, and execute multi-step tasks, with incremental DOM, session isolation, screenshots, action-result checks, and archived evidence recall.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Evidence-backed inspector for DSH Web built-in capabilities: runtime/config provenance, compatibility and drift diagnostics, plus fail-closed controls for nine reviewed UI leaves.

Static codebase analysis for onboarding: scans a project, builds a dependency graph, and writes evidence-cited architecture, module, key-flow and getting-started docs, plus project-level Q&A over a local retrieval index (no network or LLM by default; LLM narrative is optional and off unless enabled).

Data asset attestation plugin that generates certification-level data quality reports with evidence chains.

Zotero skill for DeepSeek Harness: page-anchored Q&A, full-text translation and close reading, native highlights and Chinese notes, bilingual PDF and paragraph Markdown, evidence comparison tables, and reviews with citation tracking; finds papers on OpenAlex or Crossref, imports Chinese CNKI export files, classifies the library into research-direction folders, surfaces research gaps, and runs a ranked daily digest of new papers. Python-based (basic library management uses the standard library; the reading workflow downloads its PDF/OCR components on first use); writes need a one-time Zotero authorization, and daily scheduling is Windows-only. Adapted from the OpenAI MIT Zotero plugin.

Spec-Driven Development pipeline for Odoo: 15 tools take a request from an immutable spec through architecture to module code or live configuration, then require a persisted verdict backed by evidence from a real Odoo instance, with fail-closed gates, human-approved batches in a declared environment, Odoo's own CSV/Excel importer, and a journal that reverses the data written through the plugin.

Modular execution discipline and autonomous steward for DSH: evidence-first routing across 44 canonical skills, durable state planning, verification gates, fail-streak recovery, and interactive web dashboard.

Adds local PDF reading, a durable paper library, traceable evidence records, and cross-paper comparison and synthesis tools.

Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.

Logged-in browser automation with 170+ site adapters as deterministic one-shot commands (requires the OpenCLI CLI, npm i -g @jackwener/opencli, and its BrowserBridge browser extension) — action-evidence verification (no silent failures), site knowledge & health cards, watch monitoring, trace replay, provenance reports, and a write-approval gate.

Read-only trajectory review in a resizable conversation sidebar, with rule analysis, optional model explanations, evidence navigation, and same-range run comparison.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Skill that types the request before it searches: it splits a question into premises, definitions and analysis units, decides which report skeleton fits (verdict, explainer, causal mechanism, comparison, survey map, metric card), confirms the direction and runs a feasibility check, then emits that skeleton instead of forcing every question into a true-false verdict — in Chinese or English. Evidence gathering never trusts model memory: it searches domestic and international ecosystems in parallel, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster, food safety, science, education, sports, entertainment, judicial, and more), fetches primary pages, grades sources by type, re-searches with debunking keywords, and keeps every statement bound to a full URL and citation position. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Local-first Agent Experience Network for DeepSeek Harness, distilling task-level experiences from traces and live manifests, grading by H0-H4 evidence, discovering by compatibility, and promoting only after explicit review.

A fifth DeepSeek Harness work mode that requires a falsification design (at least two pieces of evidence that could disprove the plan) in every plan and tags each factual claim with its source (\[文件]/\[检索]/\[记忆]) or \[未知]; evidence grading follows the project's AGENTS.md.

Engineering intelligence for coding agents — persistent, evidence-aware, project-isolated engineering memory with unified hybrid search (memory + RAG documentation) for DeepSeek Harness.

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.