Skip to main content

TrustWeave woven-shield product mark

TrustWeave

Deterministic security evidence for declared AI-agent trust boundaries.
Review the configuration before deployment—locally, without running the agent.

PyPI version CI status Supported Python versions Apache-2.0 license

Quick start · CLI reference · Product contract · Reviewer workflow · Security


The decision TrustWeave helps you make

A configuration change can create a new sensitive path before any application code changes. TrustWeave turns a declared agent manifest, deterministic policy, and optional local review inputs into stable JSON and Markdown evidence a reviewer can inspect, compare, retain, or export.

If you need to answer… TrustWeave gives you…
What sources, tools, capabilities, and flows are declared? An Agent Security Bundle with a deterministic decision for each declared flow.
What changed between the baseline and candidate? A focused bundle diff for declared sources, tools, capabilities, policies, and decisions.
Does the declared policy still satisfy safe synthetic cases? Reproducible local scenario results with allow, deny, and approval-required outcomes.
Does supplied local trace or MCP metadata match the declaration? Privacy-preserving review artifacts that identify mismatches for human follow-up.

Evidence, not enforcement. TrustWeave establishes evidence about the declarations and local artifacts it reads. It does not establish runtime behavior, live MCP-server behavior, authorization correctness, incident conclusions, or that an agent is secure.

Quick start

TrustWeave supports Python 3.11+. Install the published package to inspect the CLI:

python -m pip install --upgrade trustweave
trustweave --help

For a complete, safe first review, clone the repository and run the synthetic example. The workflow reads only checked-in local files; it does not interact with an agent, server, or external system.

git clone https://github.com/MohammadThabetHassan/trustweave.git
cd trustweave
python -m pip install -e .

rm -rf artifacts
trustweave scan \
  --manifest examples/support-agent.manifest.json \
  --policy policies/default-policy.json \
  --output-dir artifacts

trustweave test \
  --policy policies/default-policy.json \
  --scenarios scenarios/default-scenarios.json \
  --output-dir artifacts

trustweave attest --source-revision local --output-dir artifacts
trustweave report --output-dir artifacts
trustweave verify --attestation artifacts/attestation.json

The resulting local evidence is deliberately simple to review:

Artifact Why it matters
artifacts/agent-security-bundle.json Records deterministic decisions for declared flows.
artifacts/security-test-results.json Records fixed synthetic policy outcomes.
artifacts/attestation.json Links local evidence with internal hashes; it is not externally signed.
artifacts/report.md Summarizes the evidence, findings, and limits for a human reviewer.
Optional YAML support

The core workflow has no required runtime dependencies. Safe YAML parsing is optional:

python -m pip install "trustweave[yaml]"

Review workflows

TrustWeave stays small by keeping every workflow local and deterministic. Start with the question you need to answer, then follow the linked contract for exact inputs, outputs, exit codes, and limitations.

Review task Start here What stays out of scope
Map declared trust boundaries scan Agent execution, tool invocation, discovery, and network access.
Check policy behavior in CI test Real customer data, live prompt attacks, and model evaluation.
Compare a candidate configuration diff Undeclared runtime behavior and vulnerability verdicts.
Review policy structure policy-check Approval queues, approver identity, and runtime enforcement.
Review minimized local trace metadata trace-review Message content, tool arguments, trace authenticity, and incident reconstruction.
Review supplied MCP metadata mcp-profile-check Server discovery, HTTP/stdio connection, OAuth, token validation, and tool calls.

For the full command surface—including framework imports, MCP inventory normalization, SARIF conversion, and unsigned local statements—read the CLI reference.

What TrustWeave will never do

TrustWeave is intentionally non-executing. It does not execute an agent, invoke a tool, connect to an MCP server, call a model, access credentials, send network traffic, scan targets, upload findings, or make a deployment decision. This boundary is a core product property, not a mode to disable.

The project also avoids unsupported security claims. A review finding is a deterministic signal about supplied local evidence; it is not proof of an exploit, a production control, or a conclusion about a deployed system.

Documentation that answers the next question

Read this When you need it
CLI reference Exact arguments, outputs, exit codes, and error behavior.
Reviewer workflow Turning an already-recorded MCP inventory into a human-resolved manifest.
Product contract The user promise, evidence model, acceptance criteria, and safety boundary.
Architecture Components, local data flow, invariants, and extension boundaries.
Threat model Assumptions, non-goals, and the limits of review evidence.
Quality evidence The test, compatibility, build, reproducibility, and scoped mutation-analysis controls.
Reproducibility and integrity The exact distinction between stable evidence payloads, volatile provenance, byte reproducibility, and local file integrity.
Local risk management Fingerprints, expiry-enforced baselines and suppressions, severity gates, and reviewer responsibilities for existing local findings.
Maturity plan Verified 9.5+ priorities, release gates, and external proof the repository cannot manufacture.
Focused mutation record The exact Linux-only deterministic-engine mutation scope, result, and re-run procedure.
Supply-chain evidence Workflow-action pinning, OIDC release controls, reproducibility, SBOM evidence, and deliberate non-claims.
Schema and compatibility policy Versioned contracts and migration expectations.
Release guide The evidence and authorization required to publish a package.
0.2.1 release notes Corrected public version contract, material hardening, verification evidence, known limitations, and owner-controlled release status.
0.2.1 owner checklist Owner-controlled pre-merge, artifact-verification, release, and rollback gates.
0.2 migration guide Moving configuration, bundles, and risk-decision documents from 0.1.1 safely before installing an owner-published 0.2.1 artifact.
v0.2.0 audit record Immutable unpublished pre-publication tag evidence; it was never published to PyPI and has no GitHub Release.

Built to be inspected

0.1.1 remains the currently published PyPI release. The corrected source target is 0.2.1, which remains subject to owner-approved production publication, tagging, and a GitHub Release. Annotated v0.2.0 is an immutable unpublished audit tag at 7232fe3a23d92f50a693903c0a6b7cb92d0a1426; it was never published to PyPI and has no GitHub Release. The 0.2.1 release path includes formatting, linting, strict type checks, static source-security scanning, a 95% branch-coverage gate, isolated wheel installation, fixed-epoch wheel reproducibility, dependency auditing, CycloneDX SBOM generation, deterministic repository-reality checks, and cross-platform Python 3.11/3.13 compatibility jobs.

Current inputs retain their documented v1alpha1/v1alpha2 contracts. Generated bundles use trustweave.dev/bundle/v1alpha2; risk decisions use canonical trustweave/fingerprint/v3 identities and generated reviews use trustweave.dev/risk-review/v1alpha2. Historical v1alpha1 bundle and review resources remain available for bounded compatibility rather than being silently redefined. Read the compatibility policy before depending on a schema or review identifier outside the documented contract.

The enforced local suite retains a 95% branch coverage gate. The documented twelve-module mutation diagnostic killed 6,044 of 6,140 mutants (98.44%) and preserves an exact 96-survivor inventory with zero untriaged and zero needs_regression records. The hosted mutation workflow enforces exact survivor-identifier and normalized-diff parity on the reviewed commit SHA; no merge or release action is implied by this evidence.

Contribute, get help, or report a concern

Contributions are welcome when they improve a reviewer’s understanding of declared or pre-recorded local evidence without crossing the non-executing boundary. Start with CONTRIBUTING.md for the local quality suite and contribution checklist.

For installation and workflow questions, begin with SUPPORT.md. For reproducible bugs and bounded proposals, use the repository issue forms. Do not report suspected vulnerabilities in a public issue. Follow SECURITY.md for private reporting and safe-reporting limits. Community expectations are in CODE_OF_CONDUCT.md, while release and maintenance decisions are described in GOVERNANCE.md.

License

TrustWeave is distributed under the Apache License 2.0.

Metadata

Release files for trustweave 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for trustweave 0.2.1
File Size Uploaded
trustweave-0.2.1.tar.gz 188.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for trustweave 0.2.1
File Interpreter ABI Platform
trustweave-0.2.1-py3-none-any.whl Python 3 none any Details

Total release size: 321.2 kB

Release files / trustweave-0.2.1.tar.gz

Download URL trustweave-0.2.1.tar.gz
Size 188.1 kB
Tags Source
SHA-256 checksum
How to use checksums
4766ca12c8223e5e437f928010d8717016ff8221bd3d7bc6a89cb487152d0c6a
BLAKE2b-256 checksum
How to use checksums
9f5b33c7d2955ed2c01ff77130e42af7bd65b00f02ec8812e579cf93f112ccf0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / trustweave-0.2.1-py3-none-any.whl

Download URL trustweave-0.2.1-py3-none-any.whl
Size 133.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
43c41cec7797a031ead8bec17480dff1aefc1474d59c4c4b05fdb990e5d3c51f
BLAKE2b-256 checksum
How to use checksums
6c08c213426bb66f91d3a436dec2f09d5c2e0b6993c3ac78ef8c6937dd520ff4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Release history Release notifications | RSS feed

0.3.0

2 release files

0.2.3

2 release files

0.2.2

2 release files

This release

0.2.1 This release

2 release files

0.1.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page