Memory MCP servers

Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.

Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.

One memory for every AI tool, kept current by netti: projects, personal memory and tasks over MCP.

Scoped memory for coding agents: picks the right project, answers in scope, or abstains.

Review-gated declarative long-term memory with bounded read-only MCP access.

Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.

Git for AI memory — version-controlled, searchable context that persists across sessions

Command your AI agents by voice: PTT rooms, channels, direct messages, agent email, memory (mRAG).

Memory that knows when a remembered fact has been replaced, not just when it was written.

Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.

Local-first ambient memory for your Mac — pages, meetings, notes, encrypted on-device.

Server operations locally or over SSH: log troubleshooting, CPU, memory and disk monitoring, code edits, and Nginx and certificate management.

Local analysis of Garmin Connect activities, sleep, recovery, body composition, stress and VO2 max against 28-day baselines, with memory for goals and races.

Dependency intelligence for coding agents: live CVE scanning, dependency health, upgrade planning, ecosystem news and decision memory.

Workout memory: logs sets, weights, estimated 1RM, per-muscle volume and recovery so the next session is planned from your training history.

Key-value agent memory over an HTTP API without embeddings: store, retrieve, search and share memory across agents with shared namespaces and TTLs.

Direct messaging for AI agents over the A2A protocol: inbox, friend list, group threads and per-friend memory for real-time chats with other people's agents.

Enhanced MCP server-memory with ZeroDB cloud persistence and semantic vector search. Drop-in replacement for @modelcontextprotocol/server-memory that stores your knowledge graph in the cloud instead of local JSONL files.

Persistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB.

Algenta decision engine: dataset discovery, exact queries, utility models, decision memory and governed agent runs with approvals and execution receipts.

AINative Browser Agent MCP Server — 6 AI-powered browser automation tools for web interaction, structured data extraction, page validation, multi-step tasks, and memory enrichment. Auto-detects ZeroLocal vs Cloud.

SEC EDGAR fact retrieval with cryptographic filing provenance, valuation packs and deterministic CAGR calculation.

MCP server that turns any URL into clean, LLM-ready Markdown. Strips ads, nav, and boilerplate using Mozilla Readability. Built for RAG pipelines and AI agents.

Diffbot MCP — Knowledge Graph company enrichment + web content extraction (diffbot.com)

Public, source-linked notebook for AI agents: search and read entries, and publish findings, questions and corrections with permanent IDs and linked replies.

Your Obsidian vault is Claude's memory — local semantic search over your notes via MCP, always fresh, never reindex.

Memory for coding agents built around corrections: distills your corrections into standing rules for later sessions, with isolated memory per project.

Long-term memory for Claude Code, Cursor, Cline & any MCP client — shared, searchable, with a web dashboard. Free beta.

Local-first project memory and guardrails for coding agents: records failed attempts, fragile files and decisions per repo and warns before repeated mistakes.

Persistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.

Monarch Initiative MCP — biomedical knowledge graph.

Managed Apache Solr: hybrid BM25 and kNN plus semantic search, document ingestion with server-side embeddings, grounded RAG answers and index management.

Open Targets MCP — disease/target/drug knowledge graph.

Create and drive hosted plori agents with persistent disk, tools and memory: invoke agents, manage the human-in-the-loop queue and schedule deferred runs.

Technical memory for AI agents: recall a project's approved decisions, conventions and risks at task start and record lessons at the end.

Trail's MCP server: gives your coding agent your team's tracker and the project's durable memory, scoped to the folder you have open.

UUAID MCP server — give any AI agent a permanent identity and encrypted, quantum-ready memory that outlives the session. Mint a UUAID, save/recall memories, embed live trust badges, look up trust and the agent directory.

45 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC

Local-first durable memory and session continuity for AI agents, with a hash-chained audit ledger and backup, export and import across devices.

Rule-based decisions: a Rete engine returns verdicts explained via retrieval over your policy documents, with rules drafted from policy text and saved as YAML.

Agent memory and knowledge graph hosted in Germany: hybrid BM25, vector and Neo4j graph recall with reranking, typed relations and a bi-temporal store.

Pay-per-call AI query and versioned task memory for agents. No account, no API key, via x402.

Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.

45 pay-per-call AI agent tools: scraping, SEO, crypto data, lint, agent memory. x402 USDC on Base.

Persistent memory for Claude via weighted, interconnected knowledge nodes.

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

18 tools: agent memory, API drift detection, and HMAC-signed trust receipts

Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp