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

DSH 自定义模型思考等级管理与偏好记忆插件：原生设计语言、全档位思考配置与无感隔离式跨会话偏好记忆。

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.

A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log, live-reload. No cloud, no build step.

Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

Unified capability menu for DeepSeek Harness: manage exposure level (context footprint) and execution mode of MCP tools & skills via Exposed/Progressive/Blocked tiers.

Semantic code searcher and codebase utility

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Your First LLM-Wiki Conversation Knowledge Base

Your AI agent, fluent in Australian tax. MCP server with cited answers from 34,500+ ATO documents, the income tax and GST Acts and 4,900+ rulings, plus deduction, depreciation, BAS and audit-risk tools that know your tax profile.

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法

The AI-coding operations layer that makes "done" require evidence — persistent memory, evidence-gated completion checks, and clean handoffs for any AI agent (Claude Code, Codex, Cursor). State lives as plain files in your repo. CLI + MCP, 0 runtime depend

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Turn local files into searchable context for AI agents.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

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

Import Claude Code sessions and skills into DeepSeek Harness, and sync DSH sessions back to Claude Code

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Where data access meets operational intelligence

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.

Claude Code scaffolding and first steps for complex brownfield projects