Plugins

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

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.

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.

Remote & mobile security gateway: zero-modification Tailscale/LAN access with QR pairing, RSA encryption, brute-force defense and mobile style snippets; auto-yields the shared pairing service to other remote plugins so coexistence never crashes startup.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Cross-session memory with zero-token deterministic recall (bigram-Jaccard fused with FTS5 BM25 via RRF, Chinese-aware tokenization), reinforcement that strengthens repeated observations, and procedures crystallized into SKILL.md files refined in place through an active-stale-archived lifecycle with reversible archive and rollback. Ingest and disposal each expose a user-chosen autonomy tier; conflicts and high-importance writes always go to human review, and nothing is ever auto-deleted. Requires Node 22.5+.

Tool-output repair layer for DeepSeek Harness — JSON schema enforcement, parameter mapping, and JSON repair for tool calls.

WebUI authentication enforced at the HTTP/transport layer: four-layer login gate (resources, plugin bundles, /api, WebSocket), server-side sessions with HttpOnly cookies.

Novel-writing guardrails: 20 novel_* tools enforce fact-ledger consistency, phase and chapter gates, machine audit with deterministic metrics, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, polish, proofread, continuity checks and batch drafting, and a bypass engine runs internal steps off the main conversation.

Hardening guard for mcp__omni__parse in DeepSeek Harness: a tools/pre-execute listener that denies private/reserved host URLs (SSRF), enforces an allow-list or ask (consent), and is fail-closed when allowedRoots is empty.

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Pause / resume / cancel the in-flight conversation task from the composer area: forced pause interrupts immediately and remembers the interrupted tool, safe pause lands after the tool or reasoning finishes, resume asks for confirmation, and the default pause granularity is configurable in the settings.

Multi-machine sync: keeps multiple dsh replicas consistent through one private GitCode repository — skills, sessions, settings and plugin manifests each with an independent switch; changes go through branch, PR and merge, remote-only additions are pulled back before every push so nothing is deleted, and an AI smart-align step semantically merges files both sides changed (plus one-click conflict resolution); private repos enforced, pull never overwrites local edits.

Brain-inspired cognitive plugin: episodic, semantic, procedural and emotional memory with reinforcement-learning signals, a goal stack with time triggers, curiosity-driven autonomous web research and proactive initiatives.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

All-in-one UI plugin for DSH Desktop (Windows): conversation-width slider with fullscreen preview and follow-window mode, thinking-block enhancements (forced Chinese, expand/collapse, Markdown rendering), an Open With header button, UI label localization, a resizable settings dialog, session delete, and workspace tabs.

Runs AItelier pipelines from DSH over MCP: 39 tools (22 read, 17 write) to generate, run, inspect, edit, export and import multi-step SkillFlow pipelines. The steps execute in AItelier rather than in the DSH session and are polled by run_id, pause at engine-enforced checkpoints answered with answer_checkpoint, and leave per-step traces and step outputs to read afterwards; add_provider / map_model / edit_role point an individual role at a local or cheaper endpoint. Bundles an aitelier-pipelines skill.

Task control for DeepSeek Harness: one-click emergency stop and force-termination of stuck downloads and tool calls, download progress, stuck detection, pwsh activity monitoring, and append-condition / pause / resume with invisible recovery.

Engine-enforced guardrails for DeepSeek Harness agent swarms: quality gates reject half-done work, crash-safe checkpoints resume in place — keeps AI teams from breaking, not just running.

Plugin trust pipeline for DeepSeek Harness: deterministic static scan with verdicts, opt-in runtime guard with honeypot lures, agent audit-protocol skill, and a browser shield status light. Alarm-only, never an enforcer.