Storage, memory and knowledge management for agents.
MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.
Graph MCP server wrapping LadybugDB for causality-based requirement graphs
Reasoning orchestration MCP - Tree of Thoughts with multi-agent evaluation. Fork of Anthropic's sequential-thinking with string coercion fix.
AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions
Engram — a self-hosted team knowledge wiki with semantic search, served as an MCP server. Propose-and-approve knowledge flow (human gate), shared data with the Engram desktop app.
Learn as you build. Build with intent. — A multi-platform agentic engineering system for Windsurf, Claude Code, Cursor, OpenCode, Gemini CLI, and Codex: 57 spec-driven workflows, 17 specialist agent personas, integrated learning, and production-grade desi
MCP server exposing the ReCall local version control engine — checkpoint, rollback, undo, redo, diff, and branches as MCP tools for AI agents.
Betty — an assistant layer for agentic platforms. Email, calendar, tasks, contacts, notes, memory, and skills, stored in your own file storage.
CarpeOS CLI and local MCP server — capture context, compound knowledge.
Give Claude Code superpowers — parallel multi-model queries, smart routing, and image/video generation across OpenAI (GPT-5, o-series, GPT Image), Gemini (Imagen 4, Veo, Nano Banana), DeepSeek, Kimi, Grok, and 12+ providers
Stops your AI coding agent from repeating the same mistakes. OpenCode plugin that consolidates failure modes, patterns, and preferences from every session into a persistent knowledge base injected into future sessions automatically.
MCP server with an integrated ReAct mini-agent that autonomously uses tools. Includes AnySearch integration for web search and multi-model LLM communication via MCP sampling.
Unicode-aware, session-based MCP server for structured reasoning
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%
Agentic workflow kit for any AI coding harness: graphyloop swarm + memory (plugin + MCP server), chadi squad agents, 5-gate workflow. Install via npx.
An LLM wiki your coding agent writes — agent memory you can open and read. The agent does the writing; easymem does the storage, full-text search and knowledge graph. No embedding model, no vector database.
Codebase memory MCP server - persistent, evolving knowledge for AI coding agents
MCP server for Shotpipe — hosted, SSRF-safe, cached screenshots and Open Graph images for AI agents. No headless Chrome to run.
Read-only local MCP server for explaining Microsoft Intune assignments.
Memory and workflow automation for MCP, Codex, and Claude Code. Reuse repeatable developer operations through skills and explicit feedback.