Memory MCP servers

Local persistent agent memory without LLM calls: semantic recall over SQLite with bi-temporal fact tracking.

Two-tier memory (hot cache and cold semantic search) that promotes frequently used patterns, extracts knowledge from Claude outputs and links it in a graph.

Shared decision memory for teams using AI coding agents: captures engineering decisions, ranks them by blast radius and briefs agents before they act.

Local memory middleware: targeted retrieval instead of full-memory loading, rule-based conflict arbitration and one SQLite store shared across coding agents.

On-demand .NET memory profiling with JetBrains dotMemory: detects memory leaks, LOH fragmentation and anti-patterns, and suggests code fixes.

Self-hosted semantic memory for an engineering team's tribal knowledge: the decisions and reasoning behind the code, queryable by the team and its agents.

Persistent memory and drift detection for AI agents across session restarts.

One shared memory for every AI you use, in plain Markdown files you own.

Local-first MCP server for CodeAtlas — AST analysis, codebase intelligence, semantic memory, and A2A orchestration.

Let AI agents interact with debug probes — connect, flash, read/write memory, and reset.

Shared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.

Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.

Bidirectional bridge between Gemini Spark and the Antigravity IDE: coding subagent dispatch, shared memory, local file operations and Spark app orchestration.

Model Context Protocol (MCP) server for LightRAG - 30 fully working tools with complete RAG and Knowledge Graph integration

Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.

Control PSP games via PPSSPP's built-in WebSocket debugger: memory read/write, input, pause and step, screenshots, CPU registers and breakpoints.

Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.

Self-hosted coordination for agent fleets: shared semantic memory, tasks, agent-to-agent messaging, session handoffs and cross-agent knowledge synthesis.

Offline persistent agent memory on SQLite with local embeddings, hybrid semantic and full-text recall, secret detection and contradiction handling.

Persistent institutional memory for AI coding agents. Memory that compounds.

Local semantic code search with AST-aware chunking, hybrid BM25 and dense retrieval, and a code knowledge graph over codebases, docs sites and PDFs.

Project memory and a control plane for AI coding agents, over MCP.

Obsidian vault access with role-based access control, native search, multi-vault support, pluggable embeddings and SLSA provenance.

Manage portable AI agent playbooks, Agent Skills, MCP configurations, personas, and memory.

Code refactoring engine: code analysis, hotspot detection, complexity metrics, persistent memory and automated refactoring plans.

Living knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.

Git-first agent memory: Markdown files are the source of truth, the index is disposable and writes are reviewable commits, with hybrid search and a CLI.

High-performance knowledge graph MCP server for AI coding agents with semantic search.

Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments.

Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.

Persistent memory for AI tools. Local-first knowledge graph with hybrid search.

Self-hosted hybrid agent memory on Qdrant combining vector search, BM25, temporal retrieval and an optional Memgraph knowledge graph via rank fusion.

Local memory for coding assistants: watches sessions and injects a compact summary at the start of each new one, stored in a SQLite file.

Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.

Persistent agent memory in local JSON files: neuron/synapse graph with heat scoring, fact-level search, corrections, secret redaction and team sharing via Git.

Agent memory with a correction channel: supersede or revert stale facts, block restated old values, and prove deletions with signed tombstones.

Convert .eml exports to Markdown with YAML front matter for RAG pipelines: thread splitting, signature stripping, attachment extraction and calendar parsing.

Self-improving skill memory for coding agents: useful skills are reinforced, unused ones fade; local English/Russian hybrid search, tamper-evident history.

Open-source MCP memory server. Persistent, searchable, tiered memory across sessions.

Three-layer agent memory (identity, active, archive) with semantic search, graph relationships and conflict detection.

Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.

Long-term, drift-free cognitive memory engine for AI Agents and Cursor IDE.

Persistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.

Security-hardened Chrome automation and logins with post-quantum encryption, a credential vault, memory scrubbing and audit logging.

Deterministic context selection for AI coding agents. Local memory that compounds across sessions.

Learning sidecar for AI coding assistants: quizzes developers on AI-generated changes and gives agents persistent project-specific debugging memory via RAG.

Agent memory engine — 102 MCP tools, self-hosted, single Rust binary