Plugins

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.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

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.

Honcho memory plugin by Plastic Labs: injects the user profile, session summary and relevant conclusions at session start, uploads each turn to Honcho in the background with secrets redacted, and adds honcho_search / honcho_chat / honcho_remember tools plus a /honcho status command; configured through the ~/.honcho/config.json shared with the other Honcho integrations, against hosted honcho.dev or a self-hosted instance.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Finishes 头歌 (EduCoder) homework over the platform JSON API, with no browser automation. educoder_sweep scans every course for homeworks that still have unfinished challenges — complete homeworks are skipped without reading a single challenge, so a full-account scan costs no model tokens — and can finish them; multiple-choice challenges also cost no model tokens, because the platform returns the answer key in any submission response, while code challenges are generated by the model, uploaded with evaluate:0 and graded once per challenge, then retried using the error report the platform returns. Three tools: educoder_sweep, educoder_homework, educoder_account.

Native side-by-side chat beside the main conversation: an independent archived DSH session with full native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application.

Persistent five-layer memory system with relevance injection, LLM auto-extraction, profile rotation, and six agent tools.

Drives a locally installed Moli headless browser from DeepSeek Harness with two tools: rendered fetch, JavaScript evaluation, Markdown, semantic trees, screenshots and PDFs. Installs Moli when it is missing; verified on Windows and Linux.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Bridges a local MATLAB MCP server into DSH: evaluate MATLAB code, run .m scripts and tests, and inspect installed toolboxes via mcp__matlab__* tools. Requires MATLAB and the MathWorks MATLAB MCP Server binary, and a path edit after install — the plugin on its own registers no tools.

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes you can open in Obsidian; query your history, browse recent reads, or search your own Obsidian vault and link related notes to a reading record. Nine tools, a /codevault command, and a code-reading skill.

Runs 3 or 5 coding-agent candidates in detached Git worktrees, validates their patches with project commands, ranks only passing candidates, and requires separate approval before applying the winner.

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel

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

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Proactive scheduling: an adaptive heartbeat plus a value network (urgency, relevance, interruption cost) decides when the agent should speak unprompted.

Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Dual knowledge-graph RAG for Markdown notes with half-life memory decay: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight-feedback loop — a native Cordis plugin, npm-installable as @eqman00003/knowlp-rag.

A dsh-better-sidebar tab that statically parses Qoder Canvas `*.canvas.tsx` files into structured pages in the DSH right sidebar (the source is never executed: no eval, no bundler, no sandbox iframe), with a file-viewer takeover for `.tsx` and a bundled Skill for authoring the format.