npm

Search results

391 packages found

Guidance Control Plane - Compiles, retrieves, enforces, and evolves guidance rules for Claude Code sessions

published version 3.0.0-alpha.3, a month ago4 dependents licensed under $MIT
102,014

Enterprise governance framework for AI-assisted software delivery with Git hooks, SDD/OpenSpec, AST intelligence, evidence, MCP and multi-platform rule enforcement.

published version 6.3.379, 18 days ago0 dependents licensed under $MIT
29,659

Independent deterministic verification infrastructure for replay-safe governance execution, runtime provenance continuity, cryptographic attestations, release lineage validation, and portable trust reconstruction.

published version 1.98.56, 14 days ago3 dependents licensed under $Apache-2.0
11,137

Agentic governance layer for Claude Code — policy enforcement, hook-based safety gates, audit logging, and Codex-integrated adversarial review for AI-assisted projects

published version 0.49.1, a month ago0 dependents licensed under $MIT
8,846

TypeScript client for the Vaara HTTP API: EU AI Act runtime evidence for MCP tool calls. Conformal risk scoring, policy gating, hash-chained tamper-evident audit, named detectors.

published version 0.70.0, 3 days ago0 dependents licensed under $Apache-2.0
8,906

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

published version 0.17.0, a month ago0 dependents licensed under $MIT
7,606

AI Engineering Governance MCP Server - Session memory, knowledge system, feature registry, code intelligence, rule enforcement, tiered tooling (12 free / 73 total), 56 workflow commands, 11 agents, 20+ patterns

published version 1.15.0, 12 days ago0 dependents licensed under $BSL-1.1
6,838

Minimal governance runtime for AI agents. Intercept, govern, and verify agent actions.

published version 4.21.0, 2 days ago2 dependents licensed under $MIT
4,543

Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate.

published version 4.8.0, 4 days ago0 dependents licensed under $MIT
3,507

NeuroShield Sentry — host-level agent protection daemon. Detects and blocks malicious AI agent actions at the OS level.

published version 1.1.2, 13 days ago0 dependents licensed under $MIT
3,056

FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.

published version 1.4.23, 11 hours ago0 dependents licensed under $MIT
3,325

AGLedger™ SDK — Accountability and audit infrastructure for agentic systems.

published version 1.0.1, 5 days ago1 dependents licensed under $SEE LICENSE IN LICENSE
2,389

Occasio — cryptographically verifiable behavioral attestation for AI coding agents. Tool-call interception + policy enforcement + tamper-evident audit chain + Sigstore-signed in-toto attestations + windowed EDR detection. Same engine for Claude Code and M

published version 0.12.0, 9 days ago0 dependents licensed under $Apache-2.0
1,919

AI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag.

published version 0.4.1, 11 hours ago0 dependents licensed under $MIT
1,361

Enterprise AI agent governance framework. Hook-based enforcement, compliance packs (SOC 2, HIPAA, GDPR, PCI DSS, DORA, EU AI Act, ISO 27001), audit trails, multi-LLM adapter architecture (Claude production today; additional providers on roadmap).

published version 1.0.0-beta.30, 2 days ago0 dependents licensed under $SEE LICENSE IN LICENSE.md
1,528

A PM for your AI coding agents. Delegate, orchestrate, and audit Claude Code, Codex, Aider, OpenCode, Gemini, and any user-configured CLI agent from one local web UI — every AI action traced, every file scored, every spawn warmed with project memory.

published version 0.8.0, 8 days ago0 dependents licensed under $MIT
987

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

published version 0.3.0, 4 months ago0 dependents licensed under $MIT
980

AI Output Verification Toolkit — Local-first LLM safety, hallucination detection, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.

published version 1.5.2, 4 months ago0 dependents licensed under $MIT
1,101

Event bus contracts for loop execution signals.

published version 1.0.0-rc.0, 2 months ago6 dependents licensed under $Apache-2.0
846

Runtime governance layer for generative AI agents. Works with any MCP-compatible client — Claude, GPT, Gemini, Cursor, or custom frameworks. MAI classification, forensic audit trails, human-in-the-loop gates, EU AI Act compliance, NIST/SOC 2/CMMC mapping.

published version 0.4.0, 16 days ago0 dependents licensed under $SEE LICENSE IN LICENSE
876