@elementor-i/dsh-agentmemory
agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server
191 results
agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server
LAN mobile gateway for DeepSeek Harness (DSH): isolated Node gateway on 0.0.0.0 reverse-proxying the DSH Web UI with first-visit approval, per-device tokens, rate limiting, and mobile layout injection. 局域网手机安全访问 DSH 的即插即用网关:本机审批、设备令牌、限流、手机端紧凑排版适配。
Deterministic fault injection, autonomous resilience experiments, and machine-readable evidence for the DeepSeek Harness tool pipeline
Yukino (Yukinoshita Yukino) standalone route plugin for DSH: session tree by workspace, task-done voice alerts, no context injection into DSH.
Correctover runtime security for DeepSeek Harness (DSH): CCS 7-dimension verification, command-injection/SSRF/credential-exfil blocking, Ed25519 receipts, audit-first. Install with `dsh plugin add dsh-correctover`.
Structured long-term memory system for DeepSeek Harness -- unit-based brief/full pairs with auto-injection
User preference memory for DeepSeek Harness: persisted user profile with memory_get/memory_update tools and system-prompt injection
Long-term memory system for DeepSeek Harness: two-phase extraction/consolidation pipeline over session logs, with summary injection and memory tools
DSH web plugin: pick skills from a sidebar tab — list every installed skill with global/local badges, LLM-generated descriptions (cached, never touching skill files), and inject the /skill gesture into the current session composer on check.
chat.deepseek.com-style attachments for DeepSeek Harness: official upload icon, DS-style file cards (240x64, 16px radius), drag-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message
Auto-inject user-chosen skills (e.g. caveman, ponytail) into DeepSeek Harness sessions: every prompt or once at session start, with a settings page and a composer indicator. 在 DSH 会话中自动注入所选技能(如 caveman、ponytail):每轮提示或仅在会话开始时,含设置页与输入区指示。
Persistent 5-layer memory system for DeepSeek Harness (entry injection, relevance retrieval, agent tools, and LLM-backed auto-extraction).
GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection
Yunoseek pink skin for the DeepSeek Harness web GUI (pink --dsw-* token layer, yunoseek brand artwork, assistant avatar) plus the Yunoseek system-prompt injection: the identity prompt rendered as the first system-prompt section.
DSH plugin — browse local Hermes skills / MCP servers / chats in the DeepSeek Harness web sidebar, and inject selected skills & MCP config into the active agent (active/passive mode).
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)
Semantic repo index for DeepSeek Harness — tree-sitter symbol index, code search, and a bounded ranked repo map injected into agent context.
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.
Inject WSL/Windows path and shell facts into the DeepSeek Harness system prompt.
Inject custom HTTP headers (user-agent etc.) into DeepSeek Harness LLM provider requests, configured through cordis.yml or the Web UI settings surface.
DeepSeek Harness (dsh) plugin: prune the tool schema and inject a structural preamble on a session's first turn only.
Reusable prompt presets for DeepSeek Harness: manage a preset library in Settings and inject any preset at the start of the composer draft with one click. / DeepSeek Harness 提示词预设库:设置页管理、对话框一键注入。
Agent-driven long-term memory for DeepSeek Harness: scoped memory (global + per-workspace), layered entries (fact/knowledge/episodic), time-bucket compaction (day→week→month→year), associative recall (related chains) + memory_relate navigation (multi-hop BFS closure), auto recall injection on user messages (CJK bigram search, tail append), agent-decided content.