Memory MCP servers

Inject, parse, and strip [N] citation markers in RAG outputs.

A claims memory for agents: assert beliefs, let them decay, surface contradictions.

Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking

Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.

Cloudflare Workers AI inference: LLM chat completions (Llama, Qwen, DeepSeek), BGE text embeddings and Flux image generation.

Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.

Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster

MCP server for persistent, semantic memory across AI sessions

Coordination for AI coding agents: declare plans, catch design conflicts early, share team memory.

Persistent AI memory + codebase knowledge graph MCP server. Works across Claude Code, VS Code Copilot, Google Antigravity, Codex CLI, Hermes Agent, Claude.ai, and ChatGPT.

Context Engineering Engine. Provides cognitive tools, memory structures, and agent patterns.

MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.

Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.

Local desktop context capture: screen OCR, voice transcription, keyboard and mouse activity and clipboard, with activity history and semantic memory.

Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.

Memory for coding conventions and standing instructions that persists across sessions.

CWI Discovery Engine: read-only music-catalog MCP — semantic search, sync lookup, knowledge graph.

Deploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory.

Private local memory for your AI. Gives Claude, Cursor, and ChatGPT context about your workday — no cloud required.

Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.

AI session memory: the brief your AI reads before every session so no session starts cold.

Document hosting and encrypted agent memory with multi-tenant persistence.

Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.

Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.

Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.

Japan business regulations, compliance, travel, protocols, memory — 10 knowledge domains, 23 tools.

Engram — Persistent Memory Cortex for AI coding agents. Gives agents session continuity, change tracking, decision logging, and project intelligence across sessions.

An MCP server that gives LLMs persistent, searchable semantic memory

Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.

Family Office Knowledge Graph: read-only MCP door over the public record. Agentic KG Holdings.

Essential MCP server: HTTP, web search, downloads, Wolfram|Alpha, shell, JS, file I/O, memory.

MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.

Text extraction, keyword extraction, language detection, and chunking for RAG

Design transformer LLM architectures and report their parameters, FLOPs, memory and cost

Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.

Agentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.

Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.

MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history

Audit architecture, security, memory, and code quality in Flutter, Laravel, Node, Python, & Vue.

Bounded tools for rendering, extraction, RAG, enrichment, local discovery and review analysis.

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.

Your memory in every AI app: each fact with the line it came from, or a plain "nothing stored".

Context engineering for AI coding agents: product context, project missions, and 360 memory.

Pay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning.

Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.

Version-controlled golden datasets and RAG evaluation, no API key needed.

Persistent memory for AI agents. Search, store, and recall across sessions.