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.

GeneXus 18 MCP server — read, edit, and analyze GeneXus knowledge base objects (transactions, web panels, procedures, SDTs) directly from Claude, Cursor, and other AI agents over the Model Context Protocol.

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)

MCP server for AI image generation

Deploy static websites from AI agents. Start with the hosted endpoint at mcp.shipstatic.com — no install, no signup, no API key — or install this package to deploy folders from your own machine. The same fifteen tools either way.

The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.

Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust

Notion MCP server for Claude, Cursor, ChatGPT, and Claude Desktop — connect AI agents to Notion via the Model Context Protocol. Create pages, query databases, append blocks, upload files, and more in natural language.

Vestige gives AI agents sharp memory: a local-first Rust MCP server that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

A Context-Aware Multi-Agent Orchestration Engine

High-reliability Feishu/Lark bridge for DeepSeek Harness — QR one-click auth, multi-mode agents, card-based commands, zero-loss outbox, media in/out, session-log doctor, reusable DSH Web GUI

법제처 국가법령정보를 LLM에서 바로 조회하는 MCP 서버. 법령·판례·조례 검색과 인용 검증 | MCP server for Korean law — search statutes, precedents, and ordinances, and verify citations

The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~14 ms local semantic search, ~2 KB payloads, 19 tools.

Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.

Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory, and Epic/Marathon autonomous loop mode. The pill that turns one freelancer into a squad.

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

Open-source MCP server for comparing products and asking the buyer before purchase.

L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Pith is the hook that makes Claude Code sessions last 3x longer.