probity

mcp
Security Audit
Warn
Health Warn
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Open tools that check claims about AI agents against evidence you pin: an offline verifier with replayable decisions

README.md

Probity

CI
PyPI
Downloads
Monthly
Licence
Stars

Open tools that check claims about AI agents against evidence you pinned: an offline verifier, an observer that records agent runs, and the tools around them. The conformance corpus, vocabulary and admission rules live in https://github.com/probityai/agent-evidence-vectors.

A report.txt of six passages, one fewer than its source. A reader that sees only the report finds nothing to flag and thinks it fine. probity-verify lays the same report over source.html, pairs each source passage with its record passage, finds that the fifth has nothing to pair with, and returns contradicted, reason selected_span_missing_from_record.

It's for auditors, incident reviewers and relying parties who need a decision they can replay, and for tool authors who want their records checked the same way.

Install the released verifier: uv add probity-verify==0.3.0, or pip install probity-verify==0.3.0.

Verified by Probity (github.com/probityai/probity). The probityai command line is released: uv add probityai==0.1.1, or pip install probityai==0.1.1.

Quick start

Check a sample claim with the released package. You need Python 3.12 or newer and uv; there is nothing to clone:

samples="$(uvx --from probity-verify==0.3.0 python -c 'import importlib.resources as r; print(r.files("probity_verify") / "samples")')"
uvx probity-verify==0.3.0 "$samples/case.json" --policy "$samples/policy-june.json"

It prints a decision packet that opens:

Probity decision packet v1
Case: "source-coverage-demo"
Claim: source_text_coverage/v1
Decision: contradicted
Reason: selected_span_missing_from_record

A selected passage is in the source capture but missing from the stored report. Swap in policy-april.json for not_established, or case-complete.json with policy-complete.json for supported.

Status

Two name families, on purpose. agent-evidence-* is the neutral evidence layer: formats and checks any tool can pin without adopting ours. probity* is the product built on it. Each package keeps its own version and release tag, <name>-v<version>.

layer package what it is install
evidence agent-evidence-mcp offline, read-only MCP server: checks a claim against evidence bytes and replays the conformance vectors pip install agent-evidence-mcp==0.2.5
evidence agent-evidence-observer records what an agent run did as pinned evidence pip install agent-evidence-observer==0.2.0
evidence agent-evidence-admission checks an artifact has the digest its SBOM or attestation names (in agent-evidence-vectors) pip install agent-evidence-admission==0.2.0
evidence agent-evidence-vocabulary versioned terms for claims about agent execution evidence (in agent-evidence-vectors) pip install agent-evidence-vocabulary==0.8.0
evidence agent-evidence-vectors conformance corpora and reference verifiers pip install agent-evidence-vectors==0.32.1
product probityai the probityai command; probityai verify today pip install probityai==0.1.1
product probity-verify offline verifier: supported, contradicted or not_established pip install probity-verify==0.3.0
product probity-ratchet signed, replayable receipts for improving an agent against held-out cases pip install probity-ratchet==0.3.4
product probity-ratchet-cases agent task cases graded on final state: a simulated company, tool faults, exact graders pip install probity-ratchet-cases==0.2.0
product probity-effects keeps one effect per agent tool call when its reply is lost, records the trail, tests it against lost-reply scenarios pip install probity-effects==0.2.0
product evaluator-replay-kit replays a lab's agent action record and flags a changed or missing step pip install "git+https://github.com/probityai/[email protected]#subdirectory=packages/evaluator-replay-kit" (not on PyPI)

The Claude Code and Cursor plugins ship from harnesses/agent-evidence-plugins.

Work on the repository

uv sync --all-packages --all-extras
uv run python -m pytest

Documentation

page read it for
probity-verify the verifier, its adapters and its recipes
Repository layout the workspace, the probityai command seam, CI and releases
Agent instructions commands to run before a change
Contributing reporting a problem and opening a pull request

License

Apache-2.0, per directory: each member carries its own LICENSE.

Reviews (0)

No results found