#ai-memory

Mirror of

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

One simply siphons the excess thoughts from one's mind, pours them into the basin, and examines them at one's leisure. It becomes easier to spot patterns and links, you understand, when they are in this form.

I gave Claude a mass grave of 200 markdown files and now it remembers my entire project between sessions. No cloud, no API keys, one 10mb Go binary, and private. Stateless Agent Memory Engine is your synapse to the CLI. SAME (Stateless Agent Memory Engine) is persistent memory for AI coding agents. It indexes your markdown notes locally — Obsidian vaults, Logseq graphs, or plain folders — and surfaces relevant context automatically through a 6-gate relevance chain. ~80% of prompts are correctly skipped so your agent isn't drowning in context it doesn't need. 12 MCP tools (9 read, 3 write): semantic search across your knowledge base, filtered search by domain/tag, federated search across multiple vaults, session context with pinned notes and handoffs, save decisions, create handoffs for the next session. SQLite + Ollama embeddings on localhost. Falls back to keyword search without Ollama. No outbound network calls, no telemetry, no accounts. Your notes never leave your machine. Works with Claude Code (hooks + MCP), Cursor, Windsurf, and any MCP client via stdio transport.

Penfield gives AI agents long-term memory that compounds over time. Instead of starting every session from zero, your agent remembers conversations, learns preferences, connects ideas, and picks up exactly where it left off. Core capabilities: - 16 tools covering memory CRUD, knowledge graph, context management, artifacts, and reflection - Hybrid search with tunable weights — BM25 (keyword), vector (semantic), and graph traversal - Knowledge graph with 24 relationship types across 8 categories (evolution, evidence, hierarchy, causation, implementation, conversation, sequence, dependencies) - Context checkpoints for session handoff between agents or channels - Artifact storage for files, diagrams, and reference docs - 11 memory types intelligent filtering - Personality system with configurable personas via the portal Also available as a Claude Connector, Claude Code integration, native OpenClaw plugin (4-5x faster), and direct API.

A MCP (Model Context Protocol) server providing long-term memory for LLMs