ldclabs/KIP

Hindsight: Agent Memory That Learns

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

Agent Skills as a Memory Layer

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Evidence-backed memory for AI agents: local-first recall, temporal history, tested skills, and gradual migration.

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.

Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append-only thought chains plus a Git-like skills registry, letting skills evolve with experience through versioned, integrity-checked updates and fast retrieval.