CcopyleftdevBenchmarks & research

jev-labs

Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

Explore repositoryVisit website

How it uses Jev

Never confidently wrong. A consensus kernel around a probabilistic oracle, tested the way you would test a database: model-checked in TLA+, contract-generated into Rust, and run through 1,680 simulated pharmacy decisions under seeded chaos against the live Jev API.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jev-labs

Browse all
jevmory project preview

jevmory

Benchmarks & research
Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.
RMade byromiluz139
agent-jev project preview

agent-jev

Benchmarks & research
AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
MMade bymalevrigns286
snbt-jev-bench project preview

snbt-jev-bench

Benchmarks & research
Jev on Indonesia's SNBT 2025 university entrance exam, whose papers are never released: 159 questions reconstructed from memory by volunteers, 156 of them scored, every response published.
MMade bymisaalya0
ai-cli project preview

ai-cli

Integrations
Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.
VMade byvercel-labs813
jev_jsonschema project preview

jev_jsonschema

Applications
Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
KMade byKiln-AI7
jev-kit project preview

jev-kit

Browser & computer use
Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.
JMade byjonathanavis9625
stingray project preview

stingray

Agent tooling
A Claude Code Stop hook for the turn that ends half-done — nothing done, an announced action never carried out, a promise to watch CI with nothing running — or in the wrong language. Every judgement is made by TypeSafe Jev.
NMade byNanako01295
jev-tetris project preview

jev-tetris

Games & simulations
A visual TypeSafe demo where Jev chooses verified Tetris placements.
MMade byMachineLearning-Nerd0
verdict project preview

verdict

Applications
turn any llama-server into a jev system one endpoint
KMade bykhimaros7