#persistent-memory

Persistent memory for Claude Code built on computational neuroscience, not just retrieval. 36 cited brain mechanisms consolidate what matters, keep it current as your project evolves, and reconstruct the right context at the right time — a living memory, not a flat RAG. Says "I don't know" when unsure, flags contradictions. Local-first · MCP · MIT.

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 40-70× cheaper code questions.)

World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

Persistent memory for AI agents

An open-source terminal coding agent runtime and CLI for real project work.

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). AGPL.

Persistent graph-native memory for coding agents — works with any MCP agent. SQLite + FTS5, model-agnostic.

AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 120+ MCP tools. Persistent sessions, lessons learned, semantic search, Team Brain, managed Valkey/Redis. Free tier.

Persistent memory for pi — learns corrections, preferences, and patterns from sessions

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.