Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25519, ROS2/MCP/MAVLink bridges, OWASP ASI coverage
-
Updated
Apr 4, 2026 - TypeScript
Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25519, ROS2/MCP/MAVLink bridges, OWASP ASI coverage
Hermes-native lifecycle and evidence ledger for AI-assisted software work.
Governed cognition substrate for AI engineering agents: mission envelopes, evidence-bound belief/plan graphs, quarantined memory, model-role review, sentinel checks, and BlackFox handoffs under human authority.
SZL Holdings monorepo — Ouroboros runtime, Lutar formulas, dual-witness adapters, agent-tooling, and CI substrate
Local Codex control plane for unattended repo upkeep, bug repair, self-auditing, and evidence-backed automation.
Skyflow vault bridge for Klaviyo profile exports. Reads an AI Procurement Decision Card v0.2 and tokenizes authorized PII before it leaves the operator's machine; reveal gated by caller role.
Operator surface for Camunda process governance, approval evidence, timer drift, and review-safe execution routing.
UKG workforce disclosure surface for employee notice coverage, acknowledgment evidence, provisioning attestations, and review-safe policy posture.
Evidence-bound workflow diagnostics and certified lower-bound reporting for long-running AI agent pipelines. Improve agent workflow throughput without changing the model.
Finite Python reference checker for Ledgered Scientific Availability and selected-terminal run-to-status transport.
Vendor-risk operator surface for third-party evidence, review gaps, renewal blockers, and approval-safe sequencing.
TypeScript control plane for integration governance, missing contract packets, replay evidence, and handoff-safe review routing.
Insurance claims operator surface for missing evidence packets, denial pressure, and appeal-safe routing.
Local academic writing helper that turns draft claims and evidence notes into a reviewable ledger
Check whether AI-assisted R&D work is truly verified progress. Local-first LOSCR implementation with JSONL evidence ledgers, deterministic replay, service control, and claim checking.
Employee communications control plane for audience evidence, approval posture, localization readiness, and send-safe delivery sequencing.
Reference Python kernel for CIMT: no-meta, observable-only certification machinery for affordance-compiled LLM-integrated systems.
Contribution tracking and reputation ledger for The Agency - EVE Frontier mercenary tribe. Discord bot + operator controls.
Trust infrastructure for Git workflows with human and AI-generated code
Verification framework for AI agents: runtime checks, claim validation, hypothesis tracking.
Add a description, image, and links to the evidence-ledger topic page so that developers can more easily learn about it.
To associate your repository with the evidence-ledger topic, visit your repo's landing page and select "manage topics."