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
Stop sending your whole codebase to the AI every prompt.
MemStrata is the local context layer for AI coding tools. Median user: 42% fewer input tokens vs. RAG, $14 per month back in your pocket.
Free and open-source core. Money back if Pro savings don’t exceed your subscription.
Dashboard — Money tab
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
How it works
Three steps. Under 60 seconds to first savings.
Install MemStrata locally
pipx install memstrata-pro memstrata init
~60 seconds, fully local
Code as you normally do
MemStrata builds a graph of your codebase and compresses context per AI request — automatically, in the background.
Watch your savings tick up
Live dashboard shows tokens and dollars saved per turn, with the four-metric breakdown.
Telemetry
We measure what we save you
All four numbers are on your local dashboard. No “up to X%” — only your actual telemetry.
42%
Tokens saved vs. RAG
Median across active users. Your dashboard shows your exact number.
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 per turn — entities AI referenced that were in our context.
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 precision
Median per turn — entities we delivered that the AI actually used.
High precision means focused context, not padding. Low precision shows up as higher token costs — caught and surfaced in the dashboard.
Full methodology →
73%
24h edit survival
Median per session — AI-suggested edits still in the repo 24 hours later.
Tracks whether AI-suggested edits survive the next day of development. A proxy for suggestion quality — bad suggestions get reverted quickly.
Full methodology →
Integrations
Does it work with your stack?
Honest coverage matrix. Caveats included — we don’t oversell closed ecosystems.
| 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.
Money-back guarantee
Auto-credited if savings < subscription cost
We only profit when we save you money
At the end of every billing cycle, we add up your measured savings from the dashboard. If they’re less than your subscription cost, we credit the difference to your next invoice. No forms, no support tickets — it’s automatic and shows up on your receipt.
If you don’t use MemStrata for a month, you owe zero. We only profit when we actually save you money.
Privacy
Your code never leaves your machine
The license server checks your subscription via a signed token — nothing else.
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
Simple, honest pricing
Free and open source forever. Paid tiers add the active harness and money-back guarantee.
Free
Open source $0 forever
The MIT-licensed open core. Yours forever.
- Open-source MIT core
- Local MCP server
- Local dashboard
- Browser extension — chat capture
- Community support (GitHub)
Most popular
Pro
$14.99 CAD /mo
+ tax
The active context harness + the 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
+ tax
Everything in Pro, plus V7 tool generation.
- Everything in Pro
- V7 tool autogeny — auto tool gen + JIT routing
- Earliest access to new engines
- Priority support
Use the free, open-source core forever — no account required. Full comparison →
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.