#verification

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

Monorepo for the @orangecheck/* npm packages + the orangecheck Python SDK. SDK, gate middleware, React bindings, wallet adapter, CLI, Strfry relay filter, airdrop-gate.

ZKPassport Monorepo

Canonical node->browser content-addressing contract for the DIG Network — dig:// URN scheme + URN->retrieval-key derivation + resolution interface + browser content-verification (merkle proof + chain-anchored root, gate-then-decrypt, fail-closed). Pure leaf; behavior = dig-urn-resolver.

Agent Action Capsule — an open SCITT statement profile for recording and verifying what an AI agent did (draft-mih-scitt-agent-action-capsule)

Open-source, verification-only C2PA + CAWG SDK: Rust core with CLI, Python, C, WASM, and Go surfaces. No signing, no network at verify time.

A programming language where signatures declare types, effects, and machine-checked promises — proven with Z3, compiled with LLVM. Built for trusting AI-written code.

verification toolchain for TypeScript (Tech Preview)

Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.

Soma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.

Require fresh, file-bound verification evidence before coding agents declare completion.

Verifiable knowledge graph for scientific experiments

AI model health monitor for LLM apps – runtime checks for drift, hallucination risk, latency, and JSON/format quality on any OpenAI, Anthropic, or local client.

An async security library for the Sanic framework.

RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify the lineage independently.

Fresh-context iterative loop for Claude Code — Leader/Worker/Verifier protocol inspired by Ralph Loop and Codex design-desk

Provider‑first .NET testing framework for auto‑mocking, DI‑driven test creation, and optional Moq compatibility.

Trust what you ship: download and verify browser extension artifacts (zip structure, manifest, metadata) and emit a deterministic JSON report for CI release gates.

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

A drip-feed verification pipeline as an MCP server: phases, steps, and a cursor the agent cannot move.

A utility library for SHA-256 hashing and verification.

Majik Signature is a hybrid post-quantum content signing and verification library for the Majikah ecosystem. Built on top of Majik Key, it provides tamper-proof, forgery-resistant digital signatures for any content format — using a dual-algorithm architecture that combines classical Ed25519 with post-quantum ML-DSA-87 (FIPS-204).

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.

A pure Rust implementation of the Minisign signature tool.

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

PI Coding Dynamic Workflows

Verifiable proof layer for AI agent computations on Casper Network

Test object properties and value types.

A small Rust crate to verify Minisign signatures.

A TypeScript engine for verifying Ethiopian bank transfer receipts — supports CBE, Telebirr, Bank of Abyssinia, and E-Birr via receipt links, SMS, transaction references, and OCR screenshots. No framework dependencies