Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
98 plugin trovati
dsh-permission-matrix
zhang8019/dsh-permission-matrix
Organizza i permessi DSH in 9 preset selezionabili (3 modalità sandbox × 4 livelli di approvazione), con classificazione del rischio tramite regole e LLM su quattro livelli; le operazioni ad alto rischio richiedono approvazione con password e sono registrate in un audit log JSONL.
dsh-snippets
taxueseek/dsh-snippets
Cassetta di strumenti minimale di snippet e comandi per DSH: cinque strumenti su un unico file JSONL modificabile manualmente, zero UI, zero database, zero rete, memoria esplicita in sola scrittura.
dsh-sms-webhook
huaxiren6/dsh-sms-webhook
Webhook di inoltro SMS per DeepSeek Harness. App per telefono (SMS Forwarder, Tasker o qualsiasi HTTP POST) inviano messaggi a un endpoint HTTP locale; il plugin li memorizza come JSONL ed espone strumenti sms_recent / sms_search così che l'agente possa leggere i codici di verifica SMS durante i task. Estrae automaticamente il primo OTP di 4-8 cifre da ogni messaggio, supporta il filtraggio per parole chiave e funziona su LAN o Tailscale.
dsh-session-recovery
coprexist/dsh-session-recovery
Recupera dal disco grezzo le sessioni dsh eliminate o corrotte (session.jsonl.zstd) e la memoria (memory.db), e ripara le sessioni ricostruite che non riprendono tramite il comando /session-repair nella UI web.
dsh-egress-guard
tancheng33/dsh-egress-guard
Cancello di sicurezza a runtime sulla pipeline degli strumenti: nega le chiamate che nominano host fuori da una lista di uscita consentita, redige le credenziali nei risultati sul valore canonico e non solo sul contenuto renderizzato, e aggiunge ogni decisione a un log di audit JSONL; viene fornito in modalità solo monitoraggio.
dsh-assistant-message-forge
anweat/dsh-assistant-message-forge
Crea/modifica/inietta messaggi di test dell'assistente e importa/ripara log di sessione session.jsonl(.zstd) in nuove sessioni.
dsh-logger-panel
linglambda/dsh-logger-panel
Pannello dei log a runtime per DeepSeek Harness: vista dei log live via SSE nelle Impostazioni più file JSONL con rotazione limitata per data/dimensione
dsh-wechat-draft-gate
dingchenhui0618-arch/dsh-wechat-draft-gate
Two-stage approval gate for outbound WeChat replies in DeepSeek Harness: every reply is staged as an editable local draft that keeps the quoted original and its voice-transcription source/confidence; only a panel confirmation or /send <id> releases it through a configured bridge, and unconfirmed drafts expire with a recorded reason. Dry-run by default, JSONL audit, zero dependencies. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-del-chat
slz2025/dsh-del-chat
Adds a Delete archive item to the sidebar Session menu for archived Sessions. A confirmation dialog shows the JSONL log size and projection cache state first; confirming removes the Session JSONL log, projection cache and Workspace record from disk. Unarchived Sessions never offer it, and attachments plus the cost ledger stay untouched. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-node-monitor
qingshuiliuyun/dsh-node-monitor
Multi-node DSH monitor and control hub: per-node status and read-only sessions, zero-config LAN networking via UDP discovery, one-click/embedded access to a real DSH UI, cross-network remote hub via outbound push, serverless invite links/IPv6, and opt-in plugin toggle/restart behind dry-run, confirmation and a JSONL audit log. By default it listens on :: / 0.0.0.0 for LAN discovery, with token-protected status and control routes; its HTTP routes have no DSH access check.
dsh-conversation-log
imcaibaicai/dsh-conversation-log
Mirrors every session to a standalone readable Markdown file plus a JSONL twin whose name carries date, time and topic, keeps a searchable index beside them, and adds a settings-page search and a model recall tool.
dsh-search-pull
studentbuilding-studio/dsh-search-pull
Adds a static prompt section that makes the agent call the built-in web_search before answering questions about existing libraries, versions, errors or selection, plus an optional JSONL audit trail.
dsh-team-toolkit (team-ext)
dreamperday/dsh-team-toolkit
Observation-only audit for DSH Agent Teams that records per-request cache usage and prompt-prefix rewrites to JSONL, with no tool or prompt changes.
companion-memory
1326007879-sys/companion-memory
Local long-term memory core for DeepSeek Harness with plain-text notes, a bounded index, five tools, optional host-model consolidation and auditable evidence. It appends every user and assistant message under 32,000 characters to ~/.companion/cold/<date>.jsonl in plain text, with no built-in cleanup, and adds a short index of its notes to every system prompt; the optional model-based consolidation is off by default and, once on, sends those messages to the session's model.
dsh-session-recovery
liuhange789/dsh-session-recovery
Checkpoint-and-resume for interrupted runs: when a conversation reaches a key step — two consecutive successful file writes/edits, or one successful test command — it appends a lightweight record (timestamp, step type, tool, ≤200-char argument summary, result status) to a local JSONL file, keeping the newest 50 and pruning after 24 hours. After DSH restarts, the session_recovery tool lists unfinished sessions and resuming one creates a new session whose system prompt carries only the last three checkpoints (≤500 characters) instead of the full transcript.
dsh-memlite
risense-ai/dsh-memlite
DSH plugin: persistent local memory powered by @rsrsai/memlite (respire-aligned prompt/recall/wrap-up logic; JSONL causal tree, git sync, data-compatible with Rust memlite; four-view memory browser with conditional writes, receipts and status).
dsh-approval-audit
wojiao42/dsh-approval-audit
Forces every active session into the full-access permission preset (this disables the approval gate) and appends approval, sandbox and tool-call events to a local JSONL for after-the-fact review. Audit path is configurable; it never uploads anything.
dsh-ps-preflight
dingchenhui0618-arch/dsh-ps-preflight
Grades every PowerShell command an agent is about to run before it runs: deletion, overwrite, network download and credential access are four required classes, plus dynamic execution, system and privilege changes. Verdicts are a pure deterministic rule function — no model call, no network, sub-millisecond — with two escalation rules (download+execute, credential+exfiltrate) that jump straight to high. High risk stops the tool call for a second confirmation (in-panel queue or the native approval), deny or timeout means it never runs; medium is logged but never blocked. Every command and its verdict, including the redacted command text, is appended to a local JSONL audit log. Quoted danger strings are treated as data, -WhatIf is respected, -EncodedCommand is decoded and analysed again. Host + client halves, zero runtime dependencies, 55 rules, 136 tests.
dsh-analyze (dsh-analyze)
monsp/dsh-analyze
Local dataset analysis tools for DSH: ingest CSV/JSONL once, then head, schema, stats_describe, transform_agg, list, export and rm against a workspace store under .dsh-analyze/ through a path-confined dsh-analyze CLI. Needs that Rust CLI installed separately (prebuilt on GitHub Releases for Windows x64, macOS, Linux x64) on PATH or via DSH_ANALYZE_CLI_PATH; without it no tools are registered.
dsh-skill-radar
dingchenhui0618-arch/dsh-skill-radar
Skill usage radar for DeepSeek Harness: records every skill hit from the skill tool and /name gestures into a local JSONL ledger, ranks skills by hits in the last 7 days, greys out zero-hit skills with an archive suggestion, and expands a row into time, session, trigger and prompt. Ships a conversation-view panel with frontmatter model-invocation toggle, skill creation, and a recoverable .trash archive/restore. 52 zero-dependency tests; loopback-only, no external network.
dsh-pua-receipt
dingchenhui0618-arch/dsh-pua-receipt
Measured /pua for DeepSeek Harness: every pressure message gets a receipt comparing the last N completed model steps with the next N — tool calls, verification-class steps, repeated-call peak, failed calls and text volume — with a three-way verdict (changed approach / merely restated / no change) and a daily ranking of which sentence moved the work. Ships a conversation-view panel, a /pua command with list/status/receipts/rank/off, append-only local JSONL receipts (no tool arguments, content or session ids), 38 node:test tests and a zero-dependency build. Reports observed differences, not causality. Inspired by MichengAI/dsh-pua (independent code); it registers the same /pua command, so it cannot be installed alongside dsh-pua.
dsh-foxy-memory
kun-fox/dsh-foxy-memory
Connects DSH Foxy to Foxy Memory for cross-platform recall, with local JSONL fallback, platform filters, and a memory browser. Requires dsh-foxy.
dsh-chat-search
xvbenny/dsh-chat-search
Full-text search over DSH conversation history: decompresses the persisted per-session session.v4.jsonl.zstd logs, matches user/assistant message text, and opens a hit at the matching message (archived sessions are unarchived first). Also binds Ctrl+F.
dsh-continuity
nannan-first/dsh-continuity
Long-task continuity for DSH: every turn end writes a breakpoint (what it did, which tools it used, and — when the turn did not finish cleanly — what is still unfinished; the manual continuity_breakpoint tool can record the next step), injected as a snapshot when the same workspace starts a fresh session so work resumes instead of restarting. It also stores SHA-256 fingerprints of persona or config files so you can verify afterwards whether anything was altered. Four tools (continuity_breakpoint, continuity_breakpoints, continuity_ledger, continuity_attest), plain JSONL under <workspace>/.dsh-continuity/, zero dependencies, no network calls. Note: nothing writes ledger.jsonl yet — continuity_ledger only reads it.