Memory MCP Servers

Fully local memory for AI agents: zero LLM calls in the write path, runs air-gapped, accuracy parity with Mem0 on published benchmarks.

Shared memory for coding agents. Stop re-explaining your codebase every session. Hosted MCP at https://teamshared.com/mcp with email/OTP Connect.

Your portable context layer — load it into any AI.

Local-first always current memory for AI agents

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

You decide what Claude remembers about you. LocalKeep is a personal timeline you curate—titled, dated, editable banks on your machine—then Claude looks them up via MCP instead of inventing uneditable cloud memory.

Read-only MCP server for bounded exploration of source-grounded project memory with citations, provenance, SQLite/FTS5 retrieval, and optional document and code graphs.

Persistent, searchable project memory for AI agents, over the Model Context Protocol.

Multi-agent context sharing, memory, and status coordination via 10 MCP tools.

Append-only event log for cross-agent context/memory sharing via 3 MCP tools.

Shared company context and governed tools for ChatGPT, Claude, Codex and other MCP clients.

Postgres plus pgvector memory for AI agents, with provenance, trust verdicts and explicit abstention when memory cannot support an answer.

Independent, reproducible benchmark harness for agent-memory backends.

Proof-backed implementation memory for coding agents — search and retrieve verified primitives via HTTP API, MCP adapter guide included.

Shows what is consuming your agent's context window before the conversation starts — skill descriptions ranked by token cost, duplicate skills, memory files and their imports, and every configured MCP server.

Keeps the decisions you've settled, with the why, and serves them back unprompted in whatever AI surface you're in next. Works across Claude, Claude Code, ChatGPT, Cursor, Cline, Kilo Code, opencode, Copilot, Antigravity and Devin Desktop.

Auditable, source-cited memory infrastructure for AI agents with conflict detection, proposal review, and reusable failure memory.

Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.

Cross-tool proactive memory + suggestions for Claude Code, Kimi Code, Cline, Cursor. Teach once, use everywhere.

Search your past OpenCode conversation history before starting new work, via a local read-only FTS5 index — no network calls.

A wiki about your life that writes itself. Save from any AI chat, recall it in the next.

Persistent session memory for AI coding agents - local-first recall, drift detection, and on-device inference.

Local-first, zero-knowledge semantic memory for AI agents with on-device vector search (LanceDB + ONNX) and client-side AES-256-GCM encrypted sync.

Local-first AI memory engine for coding agents with Ebbinghaus decay, bi-temporal facts, and hybrid retrieval.

Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.

Generate random word pairs for the Imposter party game directly via Claude or Cursor. Let AI host your next social deduction game!

Shared, versioned continuation context for people and AI agents, with MCP publishing, review, annotations, identity, and organization isolation.

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP, with a live 3D viewer.

MCP server for project memory — lets AI agents record decisions, pitfalls, and specs as they work, and recall them next session with code context attached.

Shared, versioned context that humans and AI agents can review and continue.