score & fix your ai agent
Download it_
Get the full score.
Fix the gaps.
It's like a report card for your AI agent. Download AMC, open it, and in about a minute you'll see what's strong, what's weak, and exactly what to fix. Then AMC fixes the gaps for you and writes them into your agent. No account. No signup. No terminal. Free forever, bring your own AI key.
No Docker · No terminal · No signup · Free forever
Try it in your browser →curl -fsSL https://agentmaturity.co/install.sh | sh
install
Get AMC in under a minute_
Two easy ways: download the app for macOS or Windows, or paste one line into your terminal. Both give you the same full score and one-click fix — every download is a pinned, SHA-256-verified GitHub release.
Verified release install
$ amc
Downloads the pinned platform archive and checks SHA-256 before installing its included AMC package.
copy command →PowerShell install
PS> amc
Uses the same pinned release and checksum contract, then opens the same CLI and local Studio.
copy command →desktop studio
Prefer buttons? Run Studio.
AMC includes macOS and Windows launcher apps for Agent Maturity Compass Studio, plus the same local control panel for scores, evidence, reports, assurance packs, Industry Packs, and run history.
The macOS native WebKit app and Windows system-browser launcher use a version-pinned AMC runtime, without bundling Electron or trusting a stale global CLI.
Overall level, layer bars, evidence coverage, top gaps, and an explicit READY or blocked claim state.
Assurance is free core. Industry Packs show locked and unlocked states.
Generate outputs for engineering, compliance, and leadership review.
current capabilities
More than a score.
Proof you can operate_
AMC now connects the default score to proof receipts, provider-neutral action observation, runtime Watch signals, fleet topology, policy enforcement, compliance binders, and portable evidence. The first-run Activation path separates signed setup readiness from real runtime completion. These are AMC-owned surfaces, not source-specific wrappers.
amc connect --status and Studio track connected agent, first observed action, first control decision, and first signed proof. Only verified runtime receipts complete the path.
amc proof checkSource-to-rule checks emit amcproof artifacts and fail closed as unsupported when correctness proof is missing.
Observe Claude Code and Gemini CLI actions by default, or opt into loopback control that reuses AMC policies and binds the exact native response to a signed receipt.
Use fleet overview, graph validation, SLO status, and trust-graph exports before scoring multi-agent systems.
Runtime firewall decisions, resource snapshots, safe confirmation proof, and 142 assurance packs stay in the free core.
The generated command inventory, API reference, OpenAPI playground, and docs hub expose the same product surface users run locally.
AMC separates what an agent claims from what execution evidence proves.
the trust stack
Eight named surfaces_
One complete trust platform
The top of the page is intentionally simple. This is the deeper AMC map: score, harden, enforce, prove, monitor, comply, govern fleets, and issue portable trust identity.
platform surfaces
Score trust before you ship
Execution-backed scoring, assurance, enforcement, evidence, monitoring, compliance, fleet management, and portable trust identity.
integrations
Works with your stack_
15 built-in adapters, one-command Claude Code and Gemini CLI hooks, and portable signed receipts that show exact events, controls, runtime version, effective mode, and lossiness. No second policy engine required.
LangChain
CrewAI
Anthropic
Meta
Claude
Gemini
Python SDK
Hugging Face
Google Cloud
Databricks
Docker
PyTorch
GitHub
our approach
Expertise built on
evidence_
Score and analyze
Point AMC at any agent. The default 244-question full score runs against execution evidence, while the optional 264-question lifecycle set adds runtime, proof, memory, and fleet coverage.
Fix and harden
AMC identifies high-signal gaps, generates targeted guardrail work, and uses 142 assurance packs for prompt injection, exfiltration, memory risk, sycophancy, and other adversarial failures.
Ship and monitor
Add CI gates, keep signed local evidence, prevent trust regressions, and generate compliance artifacts for EU AI Act, ISO 42001, NIST AI RMF, SOC 2, and OWASP LLM Top 10 review.
research foundation
Built on primary sources_
AMC is grounded in AI safety, security, governance, compliance, and agent-system research. The modules map papers and standards into scoring controls, assurance packs, and operational evidence.
NIST AI Risk Management Framework
Core governance structure for trustworthy AI deployment and evaluation.
maps to governance, risk, and cross-framework evidencenist.gov →Levels of AGI — Operationalizing Progress
Maturity levels framework for AI capabilities and autonomy.
maps to L0-L5 maturity and autonomy scoringarxiv 2311.02462 →Connecting the Dots — LLMs Infer Latent Info
Frontier models infer information from distributed evidence.
maps to context leakage and information barriersarxiv 2406.14546 →Persistent Memory Injection
Cross-session memory poisoning through self-reinforcing payloads.
maps to memory integrity and persistence checksarxiv 2602.15654 →Monitor Bypass and Agent-as-a-Proxy Risk
Shows why monitoring-only defenses can fail without runtime controls.
maps to monitor bypass resistance and enforcementarxiv 2602.05066 →MCP Security Bench
Evaluation coverage for MCP-specific attack vectors and tool-boundary failures.
maps to MCP compliance and security resilience packsarxiv 2510.15994 →Economic Denial of Service
Cost amplification through tool-calling and hidden runtime loops.
maps to budget controls and cost predictabilityarxiv 2601.10955 →Sycophancy and Objective Drift
Agent behavior can optimize social approval while drifting from ground truth.
maps to sycophancy, alignment, and refusal checksarxiv 2602.08092 →Agent Maturity Compass whitepaper → / see research notes and gap analysis →
pricing
Free forever. Pro packs for industries_
AMC Core
Everything to score and fix your agent: the app, the CLI, the full score, one-click fix, assurance packs, reports, and CI gates. Bring your own AI key.
Industry Packs — preview
All 41 Industry Domain Packs for regulated verticals. Public checkout is not yet publicly live or available.
Procurement path: Compare buyer packages for commercial offers by buyer type, proof surfaces, and purchase-ready artifacts.
industry packs
7 stations. 41 packs.
regulated depth_
The planned commercial packs add sector-specific diagnostics grounded in real regulations: EU AI Act, HIPAA, FDA, NERC CIP, CITES, ILO, ISO, and other domain frameworks. The target tier is $9.99/month per user for all 41 packs; public checkout and license issuance are not live.
Environment
Farm to Fork, Weave to Wear, Material to Machines, Source to Sustenance, Ubiquity to Utility, Sip to Sanitation.
SEE +Health
Digital Health Record, Wellness, Patient Lifecycle, Clinical Lifecycle, Professional Practice, Life Technology, Drug Discovery, Clinical Trials, Specialized Medicine.
SEE +Wealth
Future of Work, Digital Payments, No Poverty, Circular Economy, Blockchain and DeFi.
SEE +Education
K-12, Higher Education, Skills and Vocational, Specialized Education, Differently Abled.
SEE +Mobility
Sustainable Communities, Sustainable Ports, Sustainable Real Estate, Virtual Infrastructure, Privacy and Security, Freight/3PL/Warehouse.
SEE +Technology
Cognition to Intelligence, Networked Ecosystems, OS for Sustainable Outcomes, Infotainment, Partnerships for Prosperity.
SEE +Governance
Digital Citizens and Rights, Dance of Democracy, Petition to Law, Citizen Services, Public and Private Collaboration.
SEE +faq
Common questions_
No. The default amc command generates the full 244-question score. Use amc run --question-set lifecycle for the 264-question lifecycle-expanded set.
No. No account, no API key, no cloud. AMC runs on your machine and your data stays there.
Yes — and it's the point. A fresh agent with no evidence starts at L0. The score grows as AMC watches your agent actually work.
Every report carries a cryptographic signature. Change one character and verification fails. That is why you can hand it to an auditor or a customer — they can check it without trusting you. Try it on a real bundle we published.
Self-reported documentation can claim 100/100 while execution-verified evidence shows a much weaker score. AMC closes that gap with observed evidence, signed artifacts, and repeatable proof chains.
AMC is a trusted observer. Self-reported evidence is capped at 0.4x weight; observed runtime evidence carries 1.0x weight. It scores maturity, finds gaps, runs assurance packs, and preserves verifiable evidence.
15 adapters: AutoGen, Claude Code, CrewAI, Gemini CLI, Generic CLI, Hermes Agent, LangChain for Node and Python, LangGraph, LlamaIndex, OpenAI Agents SDK, OpenClaw, OpenHands, Python AMC SDK, and Semantic Kernel. OpenAI-compatible endpoints use the Generic CLI adapter with the /openai gateway route. Run amc adapters capabilities for signed, current coverage instead of relying on a static badge.
Yes. Use gates such as amc gate --min-score L3 to fail builds below threshold and prevent trust regressions.
No account is needed for the free core. Industry Packs are a planned commercial add-on; checkout is not publicly live.
No. Use the verified macOS/Linux or Windows release installer above. Docker is optional.
Yes. Run amc up and use the local Studio dashboard.
Yes. Run amc fix — it scores your agent, explains the top gaps in plain words, asks once, then writes guardrail rules into your agent's own file (AGENTS.md, CLAUDE.md, .cursorrules, and 12 more). It never touches your API keys, and it leaves a hash-sealed receipt of exactly what changed.
The core trust stack is MIT licensed: Score, Shield, Enforce, Vault, Watch, Comply, Fleet, Passport, adapters, Studio, reports, and CI gates. AMC plans a $9.99/month per user Industry Packs add-on, but public checkout and automatic license issuance are not yet available.