Tenure | Persistent, Governable, Scoped State for AI Systems Mobile VSCode VSCodium Teams Overview Shared Memory AI Governance EU AI Act Compliance Docs GitHub Writing Benchmark Paper Install Free

Helm chart · OIDC / SCIM · MIT licensed · No call-home telemetry

AI memory shouldn't<br>be all or nothing

Different memories deserve different trust.

Explicit memory boundaries. Full traceability.

Explore Memory Modes Get Started<br>1.0* Retrieval precision<br>Retrieval latency<br>0.00 Drift score<br>0 Workflow changes

Team Local

$ helm repo add tenure https://charts.tenureai.dev<br>$ helm repo update<br>$ helm install tenure tenure/tenure \<br>--create-namespace \<br>--namespace tenure

✓ Tenure running in cluster<br>✓ OIDC endpoint ready<br>✓ SCIM provisioning active<br>✓ Audit trail enabled

$ curl -fsSL https://raw.githubusercontent.com/tenurehq/tenure/main/scripts/install.sh | bash<br>Pulling tenurehq/tenure:latest...<br>Starting container on :5757...<br>✓ Tenure is running

Bearer token:<br>sk-tenure-••••••••••••••••

✓ Change your endpoint to localhost:5757/v1<br>✓ Extraction on. Injection off. Observe first.

30 seconds. That's it.

The core problem AI does not need more context.<br>It needs state.

Context windows reset. Vector search guesses. Neither knows what it does not know.<br>State persists with versioned beliefs, provenance, and hard scope boundaries.<br>Tenure gives AI systems deterministic knowledge instead of probabilistic recall.

Memory systems<br>Semantic recall<br>Similarity search<br>Hidden drift<br>Soft boundaries<br>Overwrites<br>Context stuffing<br>"Hope it remembers"

Tenure<br>Governable state<br>Structured beliefs<br>Provenance<br>Hard scope isolation<br>Supersession<br>Typed state<br>Auditability

Memory drift Drift is invisible until it is not.

Memory drift is the AI-era equivalent of configuration drift. It accumulates silently, degrades output quality, and is almost impossible to diagnose after the fact. Tenure makes it visible and gives you the tools to prevent it.

Context bleed<br>Yesterday's topic surfaces in today's session. The model has no way to tell you why.

Cross-project contamination<br>Customer A's decisions influence Customer B's responses. Probabilistic filters are not boundaries.

Stale knowledge<br>Outdated decisions never truly disappear. Without supersession, they keep competing with the truth.

Tenure scores 0.00 on drift. Mem0 scores 0.94. Agentmemory scores 0.81.<br>See the benchmark

Govern what AI knows Not dashboards. Not policies.<br>Actual runtime control.

Every belief has an origin, a scope, a version, and a history. Nothing in Tenure is inferred after the fact. The record is written as it happens.

Scope isolation<br>Engineering beliefs stay in engineering sessions. Project A never bleeds into Project B. Hard structural boundaries, not probabilistic filters.

Belief versioning<br>When you change a decision, the old one is retired, not deleted. It never gets suggested again, but the record stays for audit.

Audit trails<br>Every request is logged with identity, timestamp, and the exact query that triggered retrieval. Not reconstructed. Recorded as it happened.

Provenance<br>Click any belief to see every session it was injected and the query that surfaced it each time. The record is complete.

Injection visibility<br>See exactly which beliefs were in context for every turn. Not inferred. Per-turn injection log, written at the time it happened.

Supersession chains<br>Beliefs are superseded, not overwritten. The full chain of what was known and when is always recoverable.

Retrieval precision 1.0 precision. Because the right belief should surface. Only the right belief.

Other memory tools dump entire chat histories or loose vector clusters into the context window and let a capable downstream model sort it out. You pay the latency and token cost for every irrelevant belief that arrives.

It is the difference between querying your database and filtering in application code. One belongs in production.

Everyone else<br>-- retrieve everything<br>SELECT * FROM beliefs

-- hope the model sorts it out<br>-- 18 results injected<br>-- precision: 0.05

Tenure<br>-- query at the source<br>SELECT * FROM beliefs<br>WHERE scope = 'project:api'<br>AND alias_match('redis')<br>AND status = 'active'

-- 1 result. precision: 1.0

Every irrelevant belief in context is tokens you're paying for and latency you're waiting on.<br>tenure

1.00<br>supermemory

0.43<br>zep

0.09<br>mem0

0.06<br>hindsight

0.06

Results are reproducible. Dataset on HuggingFace.<br>Run it yourself

Trust the process Observe before you commit.

Run with extraction on and injection off for a week or two. See exactly what Tenure learned about how you work before it ever changes a single response. No risk. No behavior change. No surprises.

Week 1-2 -- Observe<br>Extraction on. Injection off.

Tenure watches your sessions silently. It extracts decisions, preferences, facts, questions, and blockers into a structured belief store but injects nothing. Your AI responses are completely unchanged.

!inject off # nothing changes yet

When you are ready -- Turn it on<br>Open the...