Skip to content

QWED's infrastructure is attested by Docker, Snyk, CircleCI, Netlify, Mintlify, Sentry, Cloudflare, CodeRabbit, NVIDIA Inception, Buildkite, GitLab, Heroku, Atlassian.

Open source · Nothing passes unproven

Don't trust AI output. Verify it.

QWED is the open-source AI verification infrastructure for LLMs and AI agents

A model is a fluent stranger. It will hand you the number you were hoping for, in the voice of someone who counted. QWED is the open-source AI verification infrastructure that stands between that voice and your production system — recomputing the claim, replaying the tool call, inspecting the agent's next move. Nothing passes on charm. The layer is fail-closed by default: what cannot be proven does not ship.

Arithmetic · Logic · Code · SQL · Tool calls · Agent state

VERIFY
Probabilistic — a distribution over answersDeterministic — one answer, or none
Exhibit AStats engine · pandas + Pandera
Unverified model output

“Revenue grew by 15% compared to last quarter.”

The dataset says −2.3%. Fluent, confident, and off by a direction.

Verified

“Revenue declined by 2.3% compared to last quarter.”

Counted again from the rows, and returned with a hash you can check.

Two products, one architectureQWED Verification · QWED Security

The verification infrastructure and the GitHub-native application

QWED Verification is the platform. QWED Security is the developer-security application built on it.

QWED Verification is the foundational open-source layer. It translates model intent into structured claims or actions, runs defined verification engines, returns structured diagnostics and evidence, and supports downstream admission decisions.

QWED Security is a GitHub-native application built on QWED's verification architecture. It checks pull requests and release boundaries for defined code, secret, PII, policy, and artifact risks, then reports explicit outcomes in GitHub Checks.

How they connect: QWED Verification is the foundation; QWED Security is a developer-facing GitHub application that applies that foundation to pull requests and release workflows.

Platform

QWED Verification

Open-source verification infrastructure for AI outputs, tool calls, code, schemas, and agent state. Deterministic engines, evidence, and fail-closed outcomes.

Explore engines
GitHub Application

QWED Security

Deterministic security verification for pull requests and release boundaries. Context-aware classification, AST analysis, secret detection, and explicit BLOCK / WARN / INFO / UNVERIFIABLE outcomes in GitHub Checks.

The core problemCounts I–IV

The distance between fluent and true

An assistant is allowed to be wrong sometimes. A system that prices, approves, executes or advises is not.

A model speaks in probabilities and never says so. A production system runs on certainties and cannot ask. Between those two sentences there is a gap no amount of prompting closes, and nearly every AI incident of the last two years has happened inside it. AI hallucination prevention, put plainly, is not a prompting problem — it is a checking problem, and a check that is not deterministic is only a second opinion.

This is not a flaw in the model. It is a missing piece of architecture — the same way a bank vault is not a criticism of cashiers. Something must stand outside the model and check its work.

  1. ICount

    Probability, not proof

    A model returns what is likely, not what is true. Likely is a weather forecast. Your ledger is not weather.

  2. IICount

    One wrong answer is the whole story

    In finance, legal, infrastructure and agent workflows, accuracy is not an average. A single wrong output is an incident with a date on it.

  3. IIICount

    Words became actions

    Once a model can call a tool, approve a payment or write to a system, a bad sentence stops being a bad sentence and becomes an event.

  4. IVCount

    No evidence, by default

    Most AI stacks ship decisions with nothing behind them. When someone finally asks how you knew, silence is the answer you have prepared.

“Nobody signs off on a probability. They sign off on a verified outcome.”

RulingOn the source of trust

Trust was never in the model.

It was always in what you could check.

Put a deterministic verification layer in front of every output, tool call and state change — LLM output verification, applied before anything acts — and three qualities you used to argue about become things you can simply look up.

Security

Depended onprompt quality

Now: whether the call passed the gate.

Reliability

Depended onconfidence scores

Now: whether the value was re-derived.

Compliance

Depended onmanual review alone

Now: the ledger entry the check wrote.

They stop being things you hope about. They become things the system knows.

ArchitectureOrder of proceedings

Four steps, and only two of them count

The layer sits between the model and your production system, and belongs to neither.

Every output arrives as a rumour and stays one until an engine that cannot be charmed re-derives it. Every state change an agent proposes stays a proposal until a governed check lets it through. Nothing is trusted because it sounded right. Named plainly, that is verified tool calls and verified agent state, both settled before either one reaches your systems.

  1. 01

    Someone asks

    A person, a workflow, or an agent with a schedule and no supervisor.

  2. 02

    The model answers

    Probabilistic

    Intent becomes a draft: a number, a query, a plan. Fluent, immediate, unproven.

  3. 03

    QWED re-derives it

    Deterministic

    Deterministic engines compute the claim again from scratch, or read the tool call line by line.

  4. 04

    Passed, blocked, or corrected

    Production safe

    Only what was proven continues. Everything else fails closed — quietly, completely, on the record.

Two jurisdictions. One governs what a system is allowed to say; the other governs what it is allowed to remember.

1

Output verification

v6.0.0
  1. LLM output
  2. → Math / Logic / SQL / Code / Stats verifiers
  3. → VERIFIED / UNVERIFIABLE / BLOCKED
  4. → DiagnosticResult + sha256 proof_ref
2

State governance

v6.0.0
  1. Agent state proposal
  2. → AgentStateGuard: structural + semantic check
  3. → Atomic commit, or BLOCKED
  4. → Nothing partial is ever written
Core philosophyStep through it

Treat the model as an interpreter, not a witness

Useful. Fluent. Not under oath. The proof is the source of truth; the model is only the draft.

A court will happily use an interpreter and still check the transcript. That is the whole posture: whatever the model says is a draft in another language, and the draft gets read against the record before anybody acts on it.

Your application sends its prompt to the provider and waits, the way anyone waits for a translator to finish.

Your app

Production environment

The untrusted translator

LLM — OpenAI / Anthropic

The trusted verifier

SymPy / Z3 / SQLGlot / CrossHair

App → LLM → QWED → App

Verification stackSchedule of engines

Twelve engines, none of them guessing

Each one owns a single domain, and each one defers to an authority older than the hype cycle. Install the ones your risk actually lives in.

  1. 01SymPy

    Math & finance

    Calculus, matrices, and financial formulas solved symbolically — the algebra done, not approximated.

  2. 02Z3

    Formal logic

    A theorem prover looking for the counterexample: quantifiers, bit-vectors, contradictions you would not have found.

  3. 03SQLGlot AST

    SQL armor

    The query is parsed into a tree and read as structure — injection caught, complexity capped, schema honoured.

  4. 04CrossHair

    Code security

    Multi-language AST analysis with symbolic checks. eval, exec, and a leaked secret never reach the runtime.

  5. 05JSON Schema

    Schema verifier

    Shape checked deterministically, with any computed field handed to the math engine rather than trusted.

  6. 06pandas · Pandera

    Statistics

    pandas and polars run sandboxed, under schema validation and strict isolation. The numbers are recounted, not quoted.

  7. 07TF-IDF

    Fact verifier

    Deterministic term and keyword analysis. No second model in the loop, and therefore no second thing that can hallucinate.

  8. 08Triples

    Knowledge graph

    Claims broken into triples and matched against a structured graph — checked against what is recorded, not what is plausible.

  9. 09Multi-VLM consensus

    Vision verifier

    Metadata verified outright; for semantic claims, several models must agree before anything counts.

  10. 10Multi-provider

    Consensus

    For claims no formal method can settle: agreement scored across providers, and the disagreement kept visible.

  11. 11CoT · IRAC

    Reasoning

    The steps of the argument validated as a process — chain-of-thought and IRAC — with results cached.

  12. 12Rule sets

    DSL logic

    Your own policy and business rules, written down once and enforced identically every time they are asked.

Benchmarks215 critical tasks

Two hundred and fifteen chances to be wrong

Run without a verification layer, the best models still fail where failure costs something. Not often enough to notice, and never on a schedule you could prompt around. The bars below are the same tasks with the gate closed and with it open.

Financial accuracy

100%

error detection with QWED

Verified

73% · raw LLM

Detecting all mathematically verifiable errors within scoped financial domains.

Logic contradictions

0%

leakage rate with QWED

Verified

85% · LLM pass-through

Z3 detects logical contradictions within formally defined reasoning scopes.

Code security

100%

blocked threats with QWED

Verified

60% · unverified

AST analysis detects dangerous imports, eval injections, and leaked secrets.

Exhibit BConsumer finance

The $12,889 rewards error

An LLM told a customer their card held $12,889 in rewards. It did not. The number was never looked up — it was written, in the same flat, certain tone a true number would have arrived in. That is the part worth sitting with: nothing about the sentence looked wrong.

Without verification

A balance that never existed reaches a customer, becomes a complaint, and then becomes a legal file. Nobody can say where the figure came from, because no step in the system was ever capable of saying.

With QWED

The finance engine counts the balance again from source data, refuses the invented figure, and hands back a result that can be defended — carrying a proof_ref that will still mean something in a deposition two years from now.

The audit ledgerv6.0.0 · DiagnosticResult

Every check leaves a line you can cite.

Three verdicts, and no fourth. A VERIFIED result cannot be constructed without a proof reference — that is enforced by the type, not by convention, which is why the unverifiable rows below have no digest. An auditable AI agent is not one that explains itself afterwards; it is one that wrote the line down at the moment it decided, which is the entire job of AI compliance middleware.

Illustrative audit ledger entries showing the shape of a QWED DiagnosticResult.
proof_refClaimVerdictEnginems
sha256:9f2c…a41dQ3 revenue declined 2.3% quarter over quarterVERIFIEDstats41
sha256:4e19…2fc7IRR of the payment schedule is 12.4%VERIFIEDmath64
sha256:1b83…07e2∀x. premium(x) → ¬eligible(x) ∧ eligible(customer_7)BLOCKEDlogic12
sha256:c04e…5db9SELECT * FROM accounts WHERE id = '1' OR '1'='1'BLOCKEDsql3
sha256:77a1…be60exec(user_input) inside the request handlerBLOCKEDcode8
Market sentiment is improvingUNVERIFIABLEfact19
Agent proposes a state write via an unregistered toolBLOCKEDAgentStateGuard2

Example entries, with digests truncated. The columns are the real ones.

Disclosed against ourselvesPublished, fixed, filed

CWE-95 · CVSS 8.8

SymPy expression injection

An authenticated remote code execution path through parse_expr(). Closed in v5.1.2 by safe_parse_expr() and get_safe_symbol(), with Redis failing closed on error.

CVE-2026-24049 · Critical

Sentinel Edition hardening

Disclosed and fixed in v4.0.0 alongside 19 Snyk findings, RAGGuard, ExfiltrationGuard, MCP Poison Guard, SovereigntyGuard and ToxicFlowGuard.

ComparisonFive approaches

Everything else improves the odds. One thing settles them.

RAG, guardrails and fine-tuning all make a good answer likelier. None of them can tell you whether this answer is right.

  • QWED verification

    Deterministic

    Correctness · Proof-backed checks · Production AI and agent actions

  • Guardrails

    Probabilistic

    Structure · Validation rules · Formatting and output contracts

  • RAG (retrieval)

    Probabilistic

    Knowledge · Better context · Private docs and recent information

  • Fine-tuning / RLHF

    Probabilistic

    Behaviour · Probabilistic improvement · General model behaviour

  • Prompt engineering

    Probabilistic

    Prompt quality · None · Fast iteration and demos

SecurityClauses §1–§4

Nothing leaves. Nothing is assumed.

Zero trust is not a posture here, it is the default value. Every critical output has to earn its way out.

For teams whose data cannot travel and whose decisions have to be explainable a year later: run the layer inside your own walls, keep the sensitive fields masked before the model ever sees them, and attach signed evidence to every verification that matters. The same boundary does the unglamorous half of AI agent security — taint analysis is prompt injection defense with a proof attached, because it follows the untrusted sentence all the way to the place it would have done the damage.

“Do not trust the generated output. Verify it.”

Written for regulated environments, where “we think it was right” is not an answer.

  1. §1

    It runs where you are

    Docker, Kubernetes, or an air-gapped rack in a room with a lock. The verifier never needs to cross your boundary to do its work, so it doesn’t.

  2. §2

    The sensitive parts stay home

    Mask PII before the model ever sees it. The policy that decides what counts as sensitive lives inside your boundary, in a file your own reviewers can read.

  3. §3

    Your data trains nothing

    QWED verifies; it does not learn. There is no model here that gets better because you used it, and therefore no quiet incentive pointing the other way.

  4. §4

    Every pass leaves a receipt

    A VERIFIED result carries a sha256 proof_ref. It is the difference between remembering that something was checked and being able to show it.

Apache 2.0 licensedOpen to inspection

A gate you can’t inspect is just another thing to trust

The layer standing between model output and production execution has to be readable by the people whose names are on the release.

We are asking you to stop taking a model’s word for things. It would be strange to then ask you to take ours. So the whole deterministic verification layer is Apache 2.0: inspectable, forkable, and deployable in your own environment, with nothing in it you are required to believe.

“You cannot ask teams to trust a black-box verification layer.”

  1. 01

    Read every check

    A gate you cannot see inside is just a rumour with a logo. The logic, the proof paths, the reasons for refusal — all of it is on the page.

  2. 02

    Test the determinism yourself

    Anyone can claim reproducibility. Here you can run it twice and diff the output, which is a different kind of claim entirely.

  3. 03

    Deploy it anywhere

    Self-hosted, private, air-gapped. Regulated teams do not get to send their data somewhere hopeful, and open source is what makes staying home possible.

  4. 04

    Belong to no one

    Verification should be a portable layer under every model and stack — a standard, not a feature one vendor gets to price.

PackagesEight verticals

Eight places a wrong number costs money

QWED is not a single tool. It is a modular verification layer spanning finance, legal, infrastructure, and AI agent workflows — one core, and eight sets of rules for the domains where being confidently wrong is expensive.

Each package knows one domain’s arithmetic and vocabulary. Take the ones you need, leave the rest.

  • qwedCore

    Core 12-engine verification protocol

  • qwed-mcpAgents

    MCP tool-call and server verification

  • qwed-open-responsesAPI

    Verified OpenAI-compatible responses

  • qwed-financeFinance

    Banking, interest rates, ISO 20022

  • qwed-legalLegal

    Contract deadlines and citations

  • qwed-taxTax

    Tax compliance and withholding

  • qwed-infraInfra

    IaC verification — Terraform, IAM

  • qwed-ucpCommerce

    E-commerce transaction verification

SDKsFour languages

One line, then a gate

Model-agnostic and unbothered about whose API you are calling. Installed in seconds, answering in milliseconds.

  • Python

    PyPI

    qwed

  • TypeScript

    npm

    @qwed-ai/sdk

  • Go

    Go modules

    qwed-go

  • Rust

    crates.io

    qwed

VisionWhere this goes

A sentence can be corrected. An action cannot.

Output → execution

The interesting moment is not when a model writes something wrong; it is when a model does something wrong. The same deterministic verification layer that refuses a bad answer today is what will govern automation nobody is watching tomorrow. That is what AI agent security has to mean once agents transact with each other: not a policy document, but a gate every action has to pass.

  • Agents

    Agent workflows

    An agent calling tools and approving its own next step is a loop with no adult in it. Every action needs a policy check and a verdict.

  • Money

    Finance operations

    Underwriting, reconciliation, risk. The arithmetic has to be done — actually done — before anything moves.

  • Counsel

    Legal review

    A clause extracted wrongly reads exactly like a clause extracted correctly. The reasoning has to be checkable, and the trail has to survive.

  • Machines

    Machine commerce

    When software buys from software, nobody is reading the confirmation email. Verified execution becomes the only handshake left.

“If software can act, its actions must be verifiable.”

AdoptionState of record

Ready

CI workflows
Sits in the pull request, where a refusal is cheap

Portable

Container deployment
Same image on a laptop, a cluster, or a network with no way out

Available

Python and JavaScript
Published where your application already looks for things

Growing

Infra ecosystem
Built to sit beside the security, CI and hosting tools you already run
StandingMission · Vision
Mission
Make what a model says safe enough to act on, by proving it first.
Vision
Be the deterministic verification layer standing between AI reasoning and the real world.
FiledApache 2.0

Read the checks. Run them yourself. Then decide what to trust.

InterrogatoriesEight questions

Questions put to the record

Eight things people ask before they trust a gate with their production traffic.