Plugins

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Security-analysis plugin for DeepSeek Harness: 33 tools spanning six security domains, evidence/reporting and toolbox, plus the case lifecycle, routing and tool ledger; a session-bound case workflow with an evidence chain, E-id validation and reproducible findings; 362 on-demand references; three hot-swappable persona profiles; and a four-tab workbench (armor / case / intercept / about) with case-state recovery after context compaction.

Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).

An agent preset for evidence-checked research: every step advances only through system-verified observations, L3+ claims go to an independent evaluator, and the session folds into a replayable ledger that grows into a browsable domain ontology. Requires DSH >=0.1.7-alpha.1.

Per-session long-term memory that fades over time, recalls by evidence score and injects a few entries into the system prompt each turn.

Unified search with evidence verification for agents: 120+ engines with multilingual routing, vertical domains and structured modality cards, 10 MCP tools plus wide_research orchestration, and a fetch-verify loop that backfills evidence scores.

Deterministic industry research reports for DeepSeek Harness — company and industry research flows produce structured, verifiable reports from staged evidence.

Verifiable research-report engine for DeepSeek Harness with a content-addressed evidence ledger, versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory, and retrieval orchestration that reuses the ctx.web and ctx.jobs seams.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Red-team engagement mode: send one target organization name; a planner session runs five execution roles (recon, asset triage, vulnerability discovery, exploitation, internal pivot) with configurable concurrency; preflight checks skills/resources; scoring uses four stages (recon, internet, boundary, internal) with server-side caps and privilege-wins dedup; findings stay in a local SQLite fact base. The persistent right-side console has nine pages and includes asset mapping, agents, sessions/tunnels, findings, score targets, reports, POC knowledge base and skill library. v0.15.2 adds automatic HTTP evidence/action records, batch ingest, scope check, tunnel pivot probe, data proof, cleanup ledger and T0-T3 asset admission to prevent scope drift. 59 redteam_* tools; 38 bundled skills.

Profile-wide DSH governance and routing with a Web Control Center for responsibility and evidence inspection, plus compaction, scoped semantic memory, safety continuity, and verified delivery; compatible with DSH 0.1.5-rc.1.

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with you—no need to start over.

sift-light — Evidence-first search for AI agents.

Knowledge base for DeepSeek Harness: assembles ContextWindow evidence at query time within heading boundaries and token budgets, with follow-up reading around each search anchor; combines BM25/vector search via weighted RRF, MMR and optional local/remote reranking; provides automatic evidence injection, a browser panel for local embedding/rerank/OCR model downloads and health checks, keyword search without model downloads, and in-place rescans of imported directories.

Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin project), hybrid FTS5 + local-vector retrieval fused with RRF, an evidence gate that forces an explicit sufficiency judgement, provenance audit chains, SM-2 spaced-repetition review, consolidation distillation and decay forgetting, and a nine-view "Memory Palace" sidebar panel. 22 narrow-parameter tools, no external service, no API key, no Docker.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.

Reference logged-in Chrome/Edge tabs, authorized local HTML and running Windows apps through a searchable native sidebar or @. Open browser candidates and the webpage sidebar refresh when the extension connects, disconnects or changes tabs, including an unchanged search query. Windows application lists skip protected processes with unreadable identity metadata and preserve other running apps. Read scoped snapshots, batch actions, capture screenshots and use available WebMCP tools; supports authorized uploads, drag/drop and opt-in network metadata. Browser actions preserve failure evidence, accept an explicit post-action observation scope and can check one final visible/text/value/URL condition without replaying effects. Expandable context preserves model content; dockable annotations support a session-bound staging queue with edit/delete/restore, and append to chat drafts without sending. App control prefers a matching installed MCP or approved installation, then Cua Driver with text, hotkeys and paged controls; desktop reads present the window once per connection or when recovery is needed. Background input depends on the app. Requires Chrome or Edge 125+ with the companion MV3 extension manually loaded and paired; installing the plugin does not install the extension.

Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.