evidence-bundles

Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend required.

🚀 Agentic Agile V Scaffold - Production-ready template for verifiable AI-augmented engineering. Structured briefs, evidence bundles, CI gates, and automated traceability. Build trustworthy software/hardware with AI agents following the Agile V™ framework.

Trusted autonomy T&E runtime that links mission needs, hazards, scenarios, telemetry, evidence, verification reports, and hash-chained ledgers so AI/autonomous decisions can be reviewed instead of merely trusted.

Source-available governed AI cognition architecture for bounded episodic execution, reality-corrected world modeling, evidence-gated skill synthesis, transfer challenge, replay validation, and human review. No AGI claims.

Governed AI engineering control plane: federated workload identity, delegated least privilege, pre-dispatch MCP/API authorization, human approval, revocation, and cryptographically signed authority receipts with tamper/replay/rollback detection and independent verification. AI proposes. Humans decide.

Experimental Proofline Go backend for encrypted incident capture, authenticated APIs, encrypted storage, evidence bundles, and read-only review.

Source-available, measurement-first pulsed-energy testbed for tri-sector storage/discharge control, derated storage, phase authority, sensor-truth checks, energy accounting, kill criteria, evidence bundles, and human-reviewed scale-up gates.

Architecture-complete green-hydrogen validation repo: safety-gated bench testing, gas verification, carbon/source accounting, BOMs, assembly walkthroughs, Gankyil-A A/B tests, and evidence receipts.

A Python stdlib-only scaffold that turns AI-assisted development into verified engineering: structured task briefs, evidence bundles, risk levels L0–L4, and active quality gates (interface contracts, test quality, time allocation). Conversation discovers intent; artifacts control implementation; evidence controls acceptance.

Regulatory evidence and audit toolkit that builds verifiable bundles with decision lineage, checksums, and checklist gating.

QS-DMSS Studio: evidence-first simulation lab for reproducible runs, evidence bundles, campaign comparison, and research-object exports.

Public HREVN EB1 v2 trust-architecture notes, including the design review prompted by Coinkite’s COLDCARD disclosure.

Engineering case study: Hyperledger Fabric document vault with PKI signing and triple-source integrity proof (S3 Object Lock + MongoDB + Fabric).

MIRROR public evidence-bundle reference release

Mechanistic interpretability that ships: MAIR-backed evidence bundles, receipts, and comparison packets.

COSMOS-CQA research-source workbench for citizen-assisted cosmology artifact QA: https://cosmos-cqa.org

Public-safe stock analysis workflow kit for shortlists, macro overlays, evidence bundles, and market-data adapters.

Archived non-canonical ProofRelay documentation snapshot; use the live server card for current contracts.

Evidence-backed release decision compiler with bounded reproducibility probes