myeline

Governed, self-hosted memory for AI agents: writes queue until an authorized approver signs off.

Enables AI agents to search, retrieve, save, forget and give feedback on plain-Markdown memories that carry sources, dates and trust levels, while holding agent-written memories in a human review queue. Also supports session handoffs, entity and topic lookup, and audit history so learned context persists and stays verifiable.

Review-gated knowledge base for LLM agents that ensures durable memory via human-approved writes, compiling a wiki with verified citations.

Gives AI agents a single governed place to read and write company knowledge: hybrid search with citations, a shared memory where agents propose facts and humans approve them, and an email loop whose reviewed edits feed autonomy gates. Every answer and draft is logged with its sources and human verdict, so retrieval quality, grounding and edit rates are measured rather than assumed.