— · Apache-2.0
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.
v1.8.0 · MIT
Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.
v1.4.6 · MIT
查看、搜索和恢复已归档会话，支持按工作区批量归档、备份导入导出与回收站管理。
v1.4.15 · MIT
Usage billing dashboard plugin for DeepSeek Harness: sidebar cost metrics, real usage aggregation from session logs, current multi-provider pricing catalog
— · Apache-2.0
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
— · MIT
Free, open-source SQL Server and Postgres performance monitoring. Collectors, real-time alerts, graphical plan viewer, MCP server for AI analysis. Supports SQL 2016-2025, Azure SQL, AWS RDS, Postgres, Aurora Postgres.
v1.1.2 · MIT
DSH 个人配置:Token 用量统计 / 成本估算 / 自定义指令 / 外观全局字号 / 桌面宠物(含会话状态概览),纯本地不联网。Personal center for DSH: usage stats, cost estimation, custom instructions, global font size & desktop pet with session overview — all local & offline.
v0.2.2 · MIT
DSH 会话管理插件：删除（回收站恢复/彻底清除）、统计、继续/暂停、打开日志目录、对话顶部抽屉、工作区分组与排序、上下文压缩阈值设置。DSH session manager: delete with trash/restore/purge, stats, continue/pause, log folder, header drawer, workspace grouping, context compaction threshold.
v0.7.0 · MIT
Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, a Settings panel, and a managed memory dashboard. Data lives under ~/.dsh/mnemosyne.
— · MIT
Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
— · no license
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.