Plugins

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a distributable conformance suite.

Scheduled coding runs in fresh agent sessions with auditable history.

AGI long-term memory base: multi-agent spatiotemporal memory graph, self-evolving knowledge flywheel, self-cognition, and auditable trust guardrails.

Context injection audit: token costs of instruction chains / skill catalogs / tool schemas, duplicate and conflict detection.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Local security audit: config, plugin origins, sessions, network exposure — read-only redacted risk report.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

Portable Agent Skill for developing and auditing DeepSeek Harness plugins, with an optional profile-installable DSH bundle adapter.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Remote host tunnel manager: runs dsh web on a remote Linux server (systemd supervision, no root needed) behind an auto-reconnecting SSH tunnel; allocates and registers remote ports on the server, multi-user safe, with an audit view.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.

GEO brand audit skill bundle: AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/豆包/DeepSeek/Kimi/文心一言).

Lightweight OMDSH Runtime and Profile Pack toolkit for auditable DSH composition, signing, candidate installs, and rollback

Rust dev domain plugin for DeepSeek Harness (dsh): verification pyramid fmt→clippy→build+test→miri+audit(+semver) as model-facing tools + graph-layer governance (anti-Goodhart 8 rules incl. #[allow] density / deleted tests, blind-spot via Cargo.toml & pub