Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(research): record the Supermemory security/perf verdict in R8
AkitaOnRails3b514301ef42
diff --git a/docs/research-2026-landscape.md b/docs/research-2026-landscape.mdindex a1244a75..736711b1 100644--- a/docs/research-2026-landscape.md+++ b/docs/research-2026-landscape.md@@ -352,7 +352,18 @@ camp: managed cloud connectors and LLM-required extraction in the **core** - ifconnectors ever land they belong in the companion importer as opt-in, outsidethe trusted boundary, so the file-first / zero-LLM model is preserved (the sameline drawn for multimodal/PDF import: OCR/transcribe to markdown pages, never an-opaque store).+opaque store). On the other two axes the verdict is blunt: **security - nothing+to borrow** (Supermemory is weaker on every axis we chose - opaque store,+cloud-first, LLM-required, `containerTag` isolation vs our 3-tuple + invariant+#16 - so this pass is confirmation of our posture, not a source of borrowings;+the only security-relevant note is defensive: any future importer connector must+cross the existing sanitizer boundary), and **performance - only f16/+half-precision embedding storage is worth *evaluating*** (a stored-format change+with a real recall-vs-size tradeoff, gated on `recall_eval.rs`), while their+"sub-300ms p50" is a publish-a-number contract, not a change we need. Ranked, the+only thing worth actually building is the metadata/tag filter; the eval triple is+worth doing because it de-risks measuring anything else; f16 is evaluate-only;+the rest is hold-or-reject. No implementation is scheduled here.**Deliberately not recommended:** joining the memory-OS camp (agentself-editing its memory - token-expensive, and Letta itself is hedging);