evidence-ledger

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

Autonomous Infrastructure Runtime (AIR) & Trust Runtime gateway. Enforcing policy gates, CircuitBreaker controls, and evidence-driven cryptographic verification for Ubuntu Pools.

Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25519, ROS2/MCP/MAVLink bridges, OWASP ASI coverage

PolyForge: a Rust CLI toolkit that turns any GitHub repo into an agent-verifiable knowledge base via MCP with a Merkle hash evidence ledger.

Provenance•9 is an open-source, tamper-evident evidence ledger for AI and digital systems. It creates independently verifiable records of what happened, when it happened and whether the evidence has been altered.

Your coding agent says "done." Godmode checks. A local, tamper-evident record of what your agent ran, changed and proved: risky commands stopped before they run, claims downgraded until a real check backs them. Zero dependencies, nothing leaves your machine. Claude Code · Codex · Grok · OpenCode · Antigravity.

DeepSeek Harness 的 AdaptiveContextPlane (ACP) 插件——带治理的长期记忆系统

Verification framework for AI agents: runtime checks, claim validation, hypothesis tracking.

Hermes-native lifecycle and evidence ledger for AI-assisted software work.

Your agent history is scattered. MiseLedger makes it searchable evidence. Local SQLite FTS ledger for AI work history; Brigade-ready evidence bundles. No network.

NoeRelay by Axiovex Systems, LLC — local AI routing, agent execution, and managed coding clients.

Local Codex control plane for unattended repo upkeep, bug repair, self-auditing, and evidence-backed automation.

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.

Give AI agents hands without handing them the keys: exact one-use approvals and verifiable receipts for registered actions.

Veridict — the verdict that survived verification. An append-only, hash-chained audit standard for AI-generated work: signed evidence, blind juries, human risk ownership.

Evidence-first AI for civic & consumer problems: verified official routing, deterministic evidence checks, and human-confirmed action packets.

A tiny local-first raw evidence ledger for AI and human workflows.

Read-only financial event intelligence, evidence ledger, replay, and operations terminal

Contribution tracking and reputation ledger for The Agency - EVE Frontier mercenary tribe. Discord bot + operator controls.

Specs, sealed — an implement/review agent chain with hook enforcement, an evidence ledger with drift detection, and a tool-agnostic review handoff protocol.