Skip to content

v0.0.4

Latest

Choose a tag to compare

@vornicx vornicx released this 13 Jun 18:07
· 43 commits to main since this release

Everything since 0.0.3 — and the release that lines up with the redesigned README/docs.

Highlights

  • Distillation dial (3 tiers, default no-LLM) — agent-driven distillation (the agent's own LLM, $0 to Midas) + an opt-in local distiller (Memory(distiller=…), OllamaDistiller). Default off; measured honestly (naive distillation does not lift answers — see BENCHMARKS).
  • BEAM benchmark, all 4 tiers (100K→10M tokens) — recall@k 0.56→0.32 vs a 0.00 baseline; first judged answer-rate (BEAM-100K 0.40, LongMemEval ties LLM-ingest SOTA 0.84 — at $0 ingest).
  • Bitemporal recall (recall(as_of=…)), pinned standing directives, background auto-maintain, multilingual embedder option, opt-in ANN for huge stores.
  • TypeScript port (npx -y midas-memory-mcp) — same tools/schema, shares one DB file live with the Python server.
  • Fix: belief revision now persists on SQLite-backed stores.

Install: pip install "midas-memory[local]" · uv tool install "midas-memory[mcp,local]" · npx -y midas-memory-mcp

Full changelog: CHANGELOG.md · benchmarks incl. the measured negatives: BENCHMARKS.md