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.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

DeepSeek Harness session cost meter plugin: session/daily cost, budget, history, OpenCode Go quota, official & custom-provider balance, Codex-like token heatmap, peak/off-peak pricing with pre-switch popup & system-notification alerts, official price sync, 90+ model pricing catalog, Coding Plan quota queries (7 vendors), bilingual zh/en UI

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.

Trace Compare & Live Maze for DeepSeek Harness: visualize agent exploration (main path, detours, backtracks) from session logs or live sessions

Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱：成本/用量监控 · 自动更新 · 定时任务

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

VibeSkills is a general-purpose Skill that automatically routes local Skills and intelligently orchestrates harness workflows.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费，峰时正好是上班时间。

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.