LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
Local Markdown wiki as long-term memory for DeepSeek Harness — RRF-fused retrieval (keyword + wikilink graph + temporal), token-budget injection, auto-capture. Ported from llmwiki.
See your DSH conversation's fork history as a git graph — coloured branch lanes in the session header, click to jump. A pure-derivation DeepSeek Harness Web plugin.