Storage, memory and knowledge management for agents.
Cost-first MCP memory server for coding agents that stop reloading large MEMORY.md, AGENTS.md, and project context files every session. Recalls only task-relevant memory under a hard token budget and returns a savings receipt: baselineTokens vs injectedTo
Loop engineering substrate for coding agents — state, lossless optimization, and hook enforcement: verify-gated loops that can't lie, run away, or go broke. For Claude Code, Codex, Cursor, Gemini CLI, VS Code Copilot, and any MCP client.
Persistent memory for AI coding assistants. Injects context from past sessions into every LLM request.
MCP server that gives your AI writing assistant a constant-size memory of a long document. Chapter 1000 costs the same tokens as chapter 10. Local-only: no account, no API key, no network.
Give your Pi AI agent a semantic memory — bridges tokensave's Rust-powered local graph engine into your coding workflow for token-efficient codebase exploration
Official n8n community node for ContextStream hosted MCP — persistent memory, search, and session tools for n8n AI Agent workflows.
AI-powered changelog generator with MCP server support - works with most providers, online and local models
OpenCodeHub — stdio MCP server exposing code-graph + group tools
One command gives every AI editor permanent memory. Auto-detects Claude Code, Cursor, Copilot, Windsurf, Continue — writes MCP config + memory rules instantly. Free tier, no credit card.
Google Cheap Search — official MCP server for serp.cheap. Real-time Google SERP results (organic + knowledge graph) as an MCP tool.
MCP server enabling persistent memory for Claude through a local knowledge graph
OCD (Omni Coder Dashboard) — An AI memory engine with real semantic embeddings, 21 MCP tools, cross-tool routing, trace auditing, and proactive IDE interception. 100% local, zero API keys required.
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows.
MCP server for ProjectionLab — export, snapshot, and restore financial plans with a built-in FIRE advisor knowledge base.
MCP Reasoner with multiple reasoning strategies including Beam Search and Monte Carlo Tree Search
Zero-config AI project memory with live file watching and MCP integration
Persistent memory for Claude Code via MCP. SQLite + optional semantic search. Zero native deps. Works on Windows/Mac/Linux.
Switch back and forth between Claude Code, Codex, and beyond — every agent's sessions in one searchable place, served to your agents over MCP.
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, transparent reasoning, and multimodal support with file attachments (P
GraphIPO MCP Server — Design-first AI-assisted software engineering methodology. Visual architecture graphs with per-node lifecycle, guided discovery, and tree-sitter AST auditing.