26,830 packages matching “adversarial-verification”
@metaharness/harness
v0.2.0 · 1 month ago
Algorithmic Agent Harness (ADR-047) — a deterministic control plane that wraps any model/tool/skill as a replaceable worker: utility-scored decisions, four-gate safety, hash-chained receipts, circuit-breaker recovery, adversarial verification, and a bandi
No known vulnerabilities
polydeukes
v0.10.0 · 1 hour ago
A development discipline framework for building alongside an AI coding partner — deterministic covenants, a verifiable work ledger, local memory, and adversarial verification. Beta.
No known vulnerabilities
@ccx-agent/opencode-ccx
v0.8.0 · 4 months ago
Production-grade prompt engineering for OpenCode — disciplined coding, risk-aware actions, adversarial verification
No known vulnerabilities
pi-continuous-orchestration
v0.1.1 · 1 month ago
Pi extension that keeps a main agent working toward a high-level goal with durable Markdown memory and independent adversarial verification
No known vulnerabilities
@jhlee0409/elenchus-mcp
v1.3.0 · 7 months ago
MCP server for Elenchus adversarial verification system - state management, context sharing, and orchestration for code verification loops
No known vulnerabilities
crispy-code
v0.3.4 · 4 months ago
A GUI for Claude Code and Codex, built for multi-agent orchestration — with 'superthink' adversarial verification, agent memory, and Discord remote access.
No known vulnerabilities
secondopinion-x402
v0.4.1 · 1 month ago
Adversarial verification for AI agents: pay an independent skeptic per verdict in USDC via x402 (Base, Algorand, Solana). Structured verdicts with signed, offline-verifiable receipts. Vercel AI SDK + LangChain adapters, npx MCP server, free trial — no wal
No known vulnerabilities
@meir-labs/skill-security-audit
v0.1.8 · 2 months ago
The meirlabs security-audit skill — find real, exploitable issues and turn each into a ranked finding with an implementation plan: a threat model, a multi-lens static sweep, live-config checks, then a 3-skeptic adversarial verification pass so the report
No known vulnerabilities
pi-ultraplan
v0.1.0 · 3 months ago
Provider-agnostic ultraplan engine for Pi — fan-out planning, adversarial verification, structured plans, worktree-isolated execution. Reference adapter: fairy-tales-deepseek-openai / deepseek-v4-pro.
No known vulnerabilities
deepthink-js
v2.1.0 · 25 days ago
SOTA NPM module for agentic processes using local or cloud LLMs.
No known vulnerabilities
@zagents/gemini
v0.1.1 · 3 months ago
Algorithmic Agent Gemini (ADR-047) — a deterministic control plane that wraps any model/tool/skill as a replaceable worker: utility-scored decisions, four-gate safety, hash-chained receipts, circuit-breaker recovery, adversarial verification, and a bandit
No known vulnerabilities
mailauth
v5.0.3 · 20 days ago
Email authentication library for Node.js
No known vulnerabilities
@dr_inker/refute
v0.2.0 · 2 months ago
An adversarial verification panel: spawn independent skeptic agents that try to REFUTE a claim, a PR diff, or a finding — and only let it through if the panel can't.
No known vulnerabilities
@kontourai/survey
v3.0.0 · 1 month ago
Producer-side source, extraction, candidate, and review contracts for projecting verified claims into Surface.
No known vulnerabilities
pi-loom
v0.0.1 · 3 months ago
Dynamic multi-agent workflow orchestration for the pi agent harness — a faithful clone of Claude Code's workflow primitives (agent/parallel/pipeline/phase/log/budget) with structured output, adversarial verification, resumable journaling, and a live progr
No known vulnerabilities
verification-layer
v0.28.0 · 16 days ago
Open-source HIPAA compliance scanner and compliance delivery gate for healthcare code. 143 rules, evidence packages, policy gates, CLI + CI/CD.
No known vulnerabilities
pot-cli
v0.8.9 · 1 month ago
Multi-model AI verification with adversarial critique. No AI can verify itself — so they verify each other.
No known vulnerabilities
@upscalerjs/default-model
v1.0.0 · 5 months ago
ESRGAN Default Model for UpscalerJS. Upscale images and increase image resolution with AI using Javascript
No known vulnerabilities
react-verification-input
v4.2.2 · 1 year ago
Customizable, masked input, which can be used for all sorts of codes.
No known vulnerabilities
llm-trust-guard
v4.32.7 · 2 months ago
Comprehensive security guards for LLM-powered and agentic AI applications - 35 guards covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards accessible via unified TrustGuard facade. Features prompt injection (PAP/per
No known vulnerabilities