01
What is temporal validity in AI agent memory?
It is knowing which facts are still true after knowledge evolves. MemStrata retires contradicted values with a deterministic supersession rule — no similarity threshold, no LLM on the read path.
Open Source · Local-First
Schluss damit, den ganzen Code bei jedem Prompt an die KI zu schicken.
MemStrata ist die lokale Kontextschicht für KI-Coding-Tools. Median-Nutzer: 42% weniger Eingabe-Tokens als RAG, $14 pro Monat zurück in der Tasche.
Kostenloser Open-Source-Kern. Geld zurück, wenn die Pro-Ersparnis dein Abo nicht übersteigt.
Dashboard — Tab „Geld“
live
Saved this month ▲ +12% vs last
$14.62
Tokens vs. RAG 42%
Recall 87%
Precision 64%
24h survival 73%
Works with the tools you already use
Cursor Claude Code VS Code Windsurf Cline JetBrains Aider Copilot Cursor Claude Code VS Code Windsurf Cline JetBrains Aider Copilot
Capabilities
Built like a research product. Feels like magic.
Bento layout of the moat — hover any tile for a spotlight interaction.
Temporal validity ~0% stale-fact error
RAG has no model of time. We do.
Deterministic (subject, relation, object) supersession retires stale facts in a bi-temporal ledger — AUROC 0.59 proves cosine cannot tell contradiction from duplicate.
Explore Local-first 100% local index
Your code stays here
SQLite + DuckDB on-device. License check is a signed JWT only.
Explore Latency ~2.1s retrieval
Embedding floor, not LLM tax
No model on the read path. ~2.1s vs 16–18s for rerankers.
Explore Token economics 42% vs naive RAG
Median 42% fewer input tokens
Compress context per turn. Watch dollars tick up on the local Money tab — money-back if Pro savings fall short.
Explore Integrations 11+ tool surfaces
Cursor · Claude Code · VS Code · more
MCP, harness, and extension paths — honest coverage matrix, no oversell.
Explore Research P1–P5 portfolio
Five papers. One temporal spine.
From arXiv temporal validity through SWE-bench longitudinal, value-change ceilings, detect-and-flag logic bulk, and world-knowledge generalization.
Explore Scrollytelling
Scroll the story of temporal memory
Sticky visual layer · glass panels · research-backed answers
02
Why does RAG serve stale facts?
When a fact changes, old and new embeddings sit next to each other (cosine AUROC ~0.59 for contradiction vs duplicate). RAG retrieves both and has no structural way to choose the current value.
03
How is MemStrata different from Mem0 or Graphiti?
Same-stack local 7B tests show MemStrata’s CERTAIN spine at 1.000 on supersession and TEMPO axes. We optimize for never confidently wrong on evolved knowledge — not just long-dialogue recall leaderboards.
04
Does this cut AI coding token costs?
Yes. Median users see ~42% fewer input tokens vs naive RAG, with live savings on a local dashboard. Pro includes a money-back guarantee if measured savings fall short.
Workflow
So funktioniert’s
Drei Schritte. Unter 60 Sekunden bis zur ersten Ersparnis.
MemStrata lokal installieren
pipx install memstrata-pro memstrata init
~60 Sekunden, vollständig lokal
Code wie gewohnt
MemStrata erstellt einen Graphen deines Codes und komprimiert den Kontext pro KI-Anfrage — automatisch, im Hintergrund.
Sieh deine Ersparnis steigen
Das Live-Dashboard zeigt eingesparte Tokens und Dollar pro Runde, samt Aufschlüsselung der vier Metriken.
Telemetry
Wir messen, was wir dir sparen
Alle vier Zahlen stehen in deinem lokalen Dashboard. Kein „bis zu X%“ — nur deine echte Telemetrie.
42%
Eingesparte Tokens vs. RAG
Median über aktive Nutzer. Dein Dashboard zeigt deine genaue Zahl.
Computed per AI turn: actual tokens sent ÷ what a naive top-5 BM25+embedding RAG pipeline would have sent. 42% is the cross-user median.
Full methodology →
87%
Retrieval-Recall
Median pro Runde — von der KI genannte Entitäten, die in unserem Kontext waren.
After each turn, MemStrata parses the AI response for referenced symbols/files and checks how many were in the context it provided.
Full methodology →
64%
Retrieval-Präzision
Median pro Runde — gelieferte Entitäten, die die KI tatsächlich nutzte.
High precision means focused context, not padding. Low precision shows up as higher token costs — caught and surfaced in the dashboard.
Full methodology →
73%
24-h-Überleben von Edits
Median pro Sitzung — KI-Edits, die nach 24 Stunden noch im Repo sind.
Tracks whether AI-suggested edits survive the next day of development. A proxy for suggestion quality — bad suggestions get reverted quickly.
Full methodology →
Integrations
Funktioniert es mit deinem Stack?
Ehrliche Kompatibilitätsmatrix. Mit Vorbehalten — wir überverkaufen geschlossene Ökosysteme nicht.
| Tool | MCP | Harness | Extension |
|---|---|---|---|
| Cursor | — | ||
| Windsurf | — | ||
| VS Code | — | ||
| Claude Code | — | ||
| Cline | — | ||
| Continue.dev | |||
| JetBrains AI | — | — | |
| GitHub Copilot Chat | — | ||
| Aider | — | — | |
| Codex CLI | — | — | |
| Zed | — |
No tools match your search.
Geld-zurück-Garantie
Auto-credited if savings < subscription cost
Wir verdienen nur, wenn wir dir Geld sparen
Am Ende jedes Abrechnungszyklus summieren wir deine gemessene Ersparnis aus dem Dashboard. Liegt sie unter deinen Abokosten, schreiben wir die Differenz deiner nächsten Rechnung gut. Keine Formulare, keine Tickets — automatisch und auf deinem Beleg sichtbar.
Nutzt du MemStrata einen Monat nicht, zahlst du nichts. Wir verdienen nur, wenn wir dir wirklich Geld sparen.
Privacy
Dein Code verlässt nie deine Maschine
Der Lizenzserver prüft dein Abo über ein signiertes Token — sonst nichts.
Your machine — all local
AI tool
Claude Code, Cursor, VS Code…
Core
MemStrata harness
localhost:8080
compresses context
Your LLM provider
Anthropic, OpenAI, Ollama…
Local SQLite + DuckDB
· index.db · telemetry.db — your code stays here
License server
memstrata.dev/lic
Pricing
Einfache, ehrliche Preise
Für immer kostenlos und Open Source. Bezahltarife ergänzen das aktive Harness und die Geld-zurück-Garantie.
Kostenlos
Open Source $0 für immer
Der MIT-lizenzierte Open-Source-Kern. Für immer dein.
- Open-source MIT core
- Local MCP server
- Local dashboard
- Browser extension — chat capture
- Community support (GitHub)
Am beliebtesten
Pro
$14.99 CAD /mo
+ Steuer
Das aktive Kontext-Harness + die V6-Memory-Engine.
- Everything in Free
- Active context harness — all AI tools
- VS Code + browser augmentation
- V6 memory engine — verified retrieval
- Money tab — full savings metrics
- 60-day money-back guarantee
Pro+
$16.99 CAD /mo
+ Steuer
Alles aus Pro, plus V7-Toolgenerierung.
- Everything in Pro
- V7 tool autogeny — auto tool gen + JIT routing
- Earliest access to new engines
- Priority support
Nutze den kostenlosen Open-Source-Kern für immer — ohne Konto. Vollständiger Vergleich →
Research
Backed by science — not vibes
Temporal validity, marker-free evaluation, and a five-paper program on agent memory under knowledge evolution.
0.59
Cosine AUROC
~0%
Stale-fact error
0.95–1.0
Evolving accuracy
~2.1s
Retrieval latency
1 Published arXiv preprint · cs.CL / cs.AI
Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge
Deterministic supersession that RAG cannot match by construction
RAG gives agents access to accumulated knowledge but has no model of time. When a fact changes, cosine similarity surfaces both stale and current values nearly equally (AUROC 0.59 for contradiction vs duplicate). MemStrata stores facts like RAG, then retires contradicted values with a deterministic (subject, relation, object) supersession rule in a bi-temporal ledger — no similarity threshold, no LLM on the read path. Across six local benchmarks with a 7B model, MemStrata ties RAG on static knowledge and reaches 0.95–1.00 accuracy on evolving knowledge where RAG reaches 0.20–0.47. Stale-fact-error drops from 15–40% (RAG, when forced to answer) to ~0%.
- Cosine AUROC 0.59 — similarity cannot separate contradictions from duplicates
- Evolving knowledge accuracy 0.95–1.00 vs RAG 0.20–0.47
- Stale-fact-error ~0% vs RAG 15–40% when required to answer
- Retrieval ~2.1s (embedding floor) vs ~16–18s LLM-rerank baselines
temporal validitystale-fact errorbi-temporal ledgerRAG
Blog
All 10 posts → Explainers that drive SEO & understanding
Product + research
8 min read Paper 1, 2
Cut AI Coding Token Costs with Local Context Compression (Without Sending Your Repo Upstream)
MemStrata is the local context layer for AI coding tools: median 42% fewer input tokens vs naive RAG, money-back on Pro, and research-backed temporal memory so cheaper context is still correct context.
token costs AI coding local-first
Competitive analysis
11 min read Paper 1, 4, 5
MemStrata vs Mem0, Graphiti, and Letta: Same-Stack Comparison on Temporal Axes
Apples-to-apples local 7B evaluation: MemStrata’s deterministic supersession hits 1.000 on MemArch supersession/poisoning/TEMPO axes where flat RAG and several agent-memory systems still serve stale values.
Mem0 Graphiti Letta
Paper 2
8 min read Paper 2, 1
SWE-bench Longitudinal: Temporal Memory Beats RAG on Real Code Histories
On 130 marker-free scenarios extracted from SWE-bench Lite/Verified buggy→fixed histories, MemStrata temporal_v6 hits 0.908 accuracy vs ~0.57 RAG — with stale-fact-error 0.023 vs 0.262.
SWE-bench code agents benchmarks
Ship more. Spend less on tokens.
Install in under a minute. Keep coding the way you already do. Watch the savings compound — with research-backed temporal memory underneath.