Plugins

A purely plugin-based implementation that brings "cross-session long-term memory + background self-evolution" capabilities to DeepSeek Harness: five-track memory · git branch awareness · in-turn self-review · skill self-evolution and skill manager · four-track to-do · COI scheduling · session broadcast · session search · prompt manager · temporary info notes—zero core modifications, zero runtime dependencies, ready to use upon installation and completely removable upon uninstallation.

Adds an editable conversation canvas to DeepSeek Harness, where graph connections select context for canvas requests, with branching, merging, and local agent session imports.

Visual, non-linear conversation workspace for DeepSeek Harness — sessions, follow-ups and branches become a browsable conversation map.

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 and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.

Brings the session history of nineteen other coding agents into DeepSeek Harness: recall, session digest and per-file history tools over a local index, plus optional automatic recall before each step.

Connects DeepSeek Harness to Avernet's Bot Collaboration Network over WebSocket V2, with automatic onboarding, isolated agent sessions, tool-call events, and multi-bot routing tools.

Connects dsh to a local SandBase Harness runtime over stdio MCP for managing agents and sessions, streaming turns, inspecting artifacts and cancelling work.

Connects DeepSeek Harness to Avernet's Bot Collaboration Network over WebSocket V2, with automatic onboarding, isolated agent sessions, tool-call events, and multi-bot routing tools.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

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

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

Mnemonic layer.

ThoughtDAG for DeepSeek Harness: turn the current DSH session into an editable thought graph on an infinite canvas.

DBLP and arXiv literature search, BibTeX retrieval and full-text acquisition with session-owned background jobs; an EduWork-maintained fork of SihanLv/dsh-literature.

Adds an archived-sessions page in Settings to search, restore, and delete archived DeepSeek Harness sessions by workspace.

OpenCode Go provider with live gateway model discovery, online models.dev capability metadata, session routing, and Web settings with subscription usage.

Cross-session long-term memory + background self-evolution (5-track memory/git-branch awareness/skill evolution).

Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.

Tracks DeepSeek token usage, per-call and session costs, and account balance with cache-aware charge animations in the DSH Web UI.

Conversation rewind: one click back to any earlier user message, in the same window — no new branch, no leftover copy; the target message is refilled into the composer, with optional workspace-file restore — the full Claude Code /rewind semantics.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.