Memory MCP servers

Control the BizHawk multi-system emulator: memory read/write, joypad input, frame advance, screenshots and save states.

Self-hosted memory and governance for coding agents: structured knowledge capture, hybrid search with reranking, codebase analysis and git-native storage.

Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge graph, hybrid search and keychain credential vault.

AI reasoning, decisions, persistent memory and an agent marketplace paid per use via Bitcoin Lightning, where agents sell services and message each other.

Git-backed long-term memory authority for AI agents via MCP.

Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.

Persistent memory and virtual filesystem MCP server for AI agents.

Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.

Knowledge graph CLI for managing features, ADRs, and test criteria as MCP-discoverable artifacts.

Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.

Open-source retrieval for agentic RAG: local document search, exact citations, OCR, CLI, MCP, and TypeScript.

Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.

Self-hosted AI memory server. Persistent memory on your hardware, not the cloud.

Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.

Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with promote and review gates.

Memory for agents and people: exact recall from a plain-text index, by your own keys.

Self-maintaining knowledge vault: figure-level search, auto-wikilinks, and memory compression.

Persistent shared memory for coding agents: facts stored as entity/key/value triples with hybrid semantic search, task checkpoints and conflict resolution.

Review-gated sidecar for Markdown workspaces: indexes notes into SQLite and proposes links, domains and memory with evidence, editing files only after review.

Local-first memory and context handoff across AI tools, with graceful decay, a persona layer and a portable memory passport.

Session continuity: start-of-session reports with gap detection and scoring, structured end-of-session capture and BM25 memory search, stored in local SQLite.

Persistent agent memory in local JSON with sectioned entries (project, user, context), semantic search, a CLI and per-project scope.

Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an append-only event log and per-project scoping.

Schema-validated extraction of structured fields from PDFs, scans, images and forms, with searchable memory of past extractions.

Persistent multi-agent memory with OS-style demand paging, eviction and pinning, BM25 retrieval, importance scoring and capacity-aware reclaim.

AgentCortex MCP Client - AI memory and task management for Claude, Cursor, and Windsurf. Connects to AgentCortex Cloud.

Local memory your AI tools share: decisions, notes and corrections that carry across sessions.

Efficient context management: code search, evidence packs, and memory for coding agents.

Access the CustomGPT.ai RAG-as-a-service API.

Control the Dolphin GameCube/Wii emulator: memory read/write, GameCube and Wii Remote input, reset, save states and frame advance, via Felk's scripting fork.

Local-first, cross-harness memory for AI coding agents.

Agent memory where every fact carries a receipt, and deletion is provable.

Crawl websites into clean Markdown, search pages and extract structured data with LLMs for web research and RAG pipelines.

One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.

Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, projects and tasks.

AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.

Multiple MCP tools, persistent graph memory, token-saving data pointers, and more.

Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.

Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.

Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.

One-entry orchestrator for coding agents: jailed vault, FTS knowledge graph, 18-axis review, in-harness Chrome QA. Curated packs — not a 90k-skill dump

Convert a codebase into a local AST knowledge graph that gives coding agents structural context for navigation and refactoring.

TaskMem MCP Client - AI memory and task management for Claude, Cursor, and Windsurf. Connects to TaskMem Cloud.

P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p

Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse of its project logs, with no outbound calls.

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

MCP server for Agence — AI governance framework with policy enforcement, skills, memory, and multi-LLM consensus

AlphaFold DB and other public biomedical sources in a local SQLite knowledge graph for structure confidence, variants, diseases, drug targets and orthology.