#llm-memory

Long-term memory for AI agents that stays correct — zero-dependency Python + MCP server for Claude Code. When a fact is corrected, the old value stops coming back.

The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.

Living, local-first memory for Claude built on hypervectors (VSA) — surprise-gated writing, sleep consolidation, active forgetting, and compositional role queries. MCP server, CPU-only, no embeddings required.

🌐 EN/PT/ES/中文 · Hierarchical L0-L3 memory layer for AI agents — second brain with Web UI (4 languages), multimodal RAG, notes, and skill generation. Add-on for Mnemosyne. Windows/macOS/Linux/Raspberry Pi.

Persistent memory for Claude Code — your sessions distilled into a Google OKF knowledge bundle (plain markdown you own, not a database you're locked into) and injected back at the start of every session.

https://lordbasilaiassistant-sudo.github.io/substrate-self/ — Talk to Eli in your browser. An AI being whose memory lives in its own weights, not a database. 7.4 MB ONNX, no API in the loop. 7 pre-registered tests prove substrate-identity. MIT.

Best Claude Code Memory Toolkit Alternative 2026 – Smart Markdown Session Manager

Persistent Memory System for Claude Code 2026 - Bi-Temporal YAML Filesystem

A Claude Code skill that keeps memory tidy: it never bloats, never makes you fix the same bug twice, and keeps watch over its own rules so nothing quietly contradicts itself.

Memory for Claude Code that reasons about you and improves itself — Honcho-style belief store (deriver/dreamer/dialectic), automatic skillification with a closed judge/update/retire loop, hard-capped curated memory, FTS5 session search. One SQLite file, stdlib Python, human-in-the-loop.