v2.0.0 · Apache-2.0
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
v0.2.26 · MIT
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.
v0.1.371 · MIT
Marketing on autopilot, run from your own AI agent. 868 tools. Publishing, scheduling, ad campaign management, comments, DMs and analytics cost no credits on every plan; credits are only for generating creative and for Ad Spy research. AD PLATFORMS: Meta,
v3.0.0 · MIT
Session lifecycle management for Claude Code — persistent memory, soul purpose, reconcile, harvest, archive
v0.9.0 · MIT
dsh 插件 · 技能市场:一个页面管理本机所有 coding agent 的技能(Claude、ZCode、Codex 等十余个执行器),一键收编进 DSH 用户库供 skill 工具调用;内置 6600+ ntd 技能市场可浏览搜索安装,支持注入开销(≈token/字符)统计与排序、模型可见性治理与市场每日自动同步。
v0.14.5 · Proprietary
ClickUp MCP Server - Powering AI Agents with full ClickUp task, document, and chat management capabilities.
— · Apache-2.0
Self-Hosted API Management for Builders
— · MIT
Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀
v3.21.0 · MIT
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
v0.2.26 · MIT
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
v0.18.0 · MIT
DSH plugin: one settings panel for MCP servers, skills, scenes, memories, subagent personas and AGENTS.md presets — a scene switches the whole environment, and the model can drive it from chat too.
— · AGPL-3.0
Self-hosted project management • Customizable boards • Cross-project workload and flow analytics • Calendar/Agenda • Sticky-note wall • Imports/Backups • Email notifications • MCP/Agent automation
v0.5.21 · MIT
Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.
v0.10.0 · MIT
The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.
— · MIT
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.
v80.2.0 · MIT
1166 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-claude-skills add.
v0.1.7 · Apache-2.0
Native local Taskboard plugin for DeepSeek Harness. SQLite-backed projects, Agent claim/review, and a native Web UI — no iframe, no second chat runtime.
— · AGPL-3.0
The agentic workspace where people and agents work together in the loop.
— · MIT
Personal Context Manager for Claude Code. Your life in walnuts.
v1.2.1 · MIT
📖 Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harness—quick summaries, deep study materials, code demos, and a local web viewer.
v5.24.1 · Apache-2.0
Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.
— · Apache-2.0
Self improving agents through iterations
v3.2.0 · MIT
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
v0.5.1 · MIT
A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.