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.
Código abierto · Local primero
Deja de enviar todo tu código a la IA en cada mensaje.
MemStrata es la capa de contexto local para herramientas de programación con IA. Usuario medio: 42% menos tokens de entrada frente a RAG, $14 al mes de vuelta en tu bolsillo.
Núcleo gratuito y de código abierto. Te devolvemos el dinero si el ahorro de Pro no supera tu suscripción.
Panel — pestaña Dinero
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
Cómo funciona
Tres pasos. Menos de 60 segundos hasta el primer ahorro.
Instala MemStrata localmente
pipx install memstrata-pro memstrata init
~60 segundos, totalmente local
Programa como siempre
MemStrata construye un grafo de tu código y comprime el contexto en cada petición a la IA, automáticamente y en segundo plano.
Mira cómo sube tu ahorro
El panel en vivo muestra los tokens y dólares ahorrados por turno, con el desglose de las cuatro métricas.
Telemetry
Medimos lo que te ahorramos
Las cuatro cifras están en tu panel local. Nada de «hasta X%»: solo tu telemetría real.
42%
Tokens ahorrados vs. RAG
Mediana entre usuarios activos. Tu panel muestra tu cifra exacta.
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%
Cobertura de recuperación
Mediana por turno: entidades citadas por la IA que estaban en nuestro contexto.
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%
Precisión de recuperación
Mediana por turno: entidades que entregamos y la IA realmente usó.
High precision means focused context, not padding. Low precision shows up as higher token costs — caught and surfaced in the dashboard.
Full methodology →
73%
Supervivencia de ediciones 24 h
Mediana por sesión: ediciones de la IA que siguen en el repo 24 horas después.
Tracks whether AI-suggested edits survive the next day of development. A proxy for suggestion quality — bad suggestions get reverted quickly.
Full methodology →
Integrations
¿Funciona con tu stack?
Matriz de compatibilidad honesta. Con sus advertencias: no exageramos los ecosistemas cerrados.
| 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.
Garantía de devolución
Auto-credited if savings < subscription cost
Solo ganamos cuando te ahorramos dinero
Al final de cada ciclo de facturación sumamos tu ahorro medido en el panel. Si es menor que el coste de tu suscripción, abonamos la diferencia en tu próxima factura. Sin formularios ni tickets de soporte: es automático y aparece en tu recibo.
Si no usas MemStrata durante un mes, no debes nada. Solo ganamos cuando realmente te ahorramos dinero.
Privacy
Tu código nunca sale de tu máquina
El servidor de licencias verifica tu suscripción mediante un token firmado: nada más.
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
Precios simples y honestos
Gratis y de código abierto para siempre. Los planes de pago añaden el harness activo y la garantía de devolución.
Gratis
Código abierto $0 para siempre
El núcleo abierto con licencia MIT. Tuyo para siempre.
- Open-source MIT core
- Local MCP server
- Local dashboard
- Browser extension — chat capture
- Community support (GitHub)
Más popular
Pro
$14.99 CAD /mo
+ impuestos
El harness de contexto activo + el motor de memoria V6.
- 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
+ impuestos
Todo lo de Pro, además de la generación de herramientas V7.
- Everything in Pro
- V7 tool autogeny — auto tool gen + JIT routing
- Earliest access to new engines
- Priority support
Usa el núcleo gratuito y de código abierto para siempre, sin cuenta. Comparación completa →
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.