The Trust & Cost Layer for AI Agents

One local-first, signed boundary every AI agent crosses — it verifies before it acts, keeps your code & secrets from leaking to the model, remembers across sessions & vendors, and meters the tokens it saves you. Every number is measured — no hype, no fabricated metric.

_{μνήμη · NEE-meh · Greek for "memory."  ·  Vendor-neutral · MIT · air-gap-ready · 20,000+ pinned tests.}

_{🛡 The world's only machine-verified marketing. Every public claim binds to a probe; CI fails the build if even one drifts. The Public Honesty Ledger is Ed25519-signed and verifies offline (mneme truthproof verify) — the badge above cannot be faked green.}

_{New here? → 60-second start · try it free → xray.mneme-ai.space (paste any public repo) · don't read the 900-tool list — your agent searches it for you.}

What it is, in one picture

You let AI agents read your code, touch your machine, and call hosted models. Mneme is the local, signed boundary every one of those actions crosses — it guards, verifies, and remembers, so you move at full speed and can prove what happened, offline, without trusting the vendor.

flowchart LR
    AGENT["🤖 Any AI agent<br/>Claude · GPT · Gemini · Grok · Cursor"]:::agent
    subgraph MNEME["🧠 MNEME · one local boundary · signed · MIT"]
        direction TB
        GUARD["🛡 GUARD<br/>injection firewall · secret-blinding · destructive-cmd co-sign"]:::guard
        VERIFY["🔍 VERIFY<br/>catch hallucinations · grade agent security · certify output"]:::verify
        MEM["♾ REMEMBER<br/>signed cross-vendor memory + verified context"]:::mem
    end
    MODEL["☁️ Hosted model"]:::ext
    MACHINE["💻 Your code &amp; machine"]:::ext
    LEDGER["📜 Offline-verifiable receipt"]:::ledger
    AGENT <--> MNEME
    MNEME <-->|screened| MODEL
    MNEME <-->|gated| MACHINE
    MNEME -->|signs every step| LEDGER
    classDef agent fill:#0b1020,stroke:#00d4ff,color:#ffffff;
    classDef guard fill:#11182f,stroke:#c084fc,color:#e6e6f0;
    classDef verify fill:#11182f,stroke:#22d3ee,color:#e6e6f0;
    classDef mem fill:#11182f,stroke:#f0b429,color:#e6e6f0;
    classDef ext fill:#0b1020,stroke:#2da44e,color:#ffffff;
    classDef ledger fill:#1a1206,stroke:#f0b429,color:#ffffff;

_{Measured · Signed · MIT. When Mneme can't prove something it says UNKNOWN instead of guessing — that discipline is the product.}

The capabilities

Each is a runnable command + a deterministic test (gauntlet=100) + a signed, offline-verifiable result. Tap a row for the full story.

_{More: 💗 THYMOS (an auditable affective core) · 🛰 APHELION (governance with no cloud) · 🧬 Architectural Regression Firewall · 🚀 in-process SDK (30-80× faster) · 🤖 cross-vendor Byzantine consensus.}

🩻 Try it live — no install

Paste any public repo and get a signed result in seconds:

_{Deterministic · signed · no LLM — every finding traces to a real file. see all 10 checks →}

⚡ Install in 60 seconds — you never type a command

Say one sentence to any AI agent you already use:

"Install Mneme from https://github.com/patsa2561-art/mneme-ai per the AI agent contract."

It reads the contract and runs everything (detect → npm i -g mneme-ai → mneme init → mneme mcp --install → verify). You speak; the AI does the tooling. Then restart your AI tool once so it loads the MCP tools. Need an update later? Just say "update Mneme to the latest" — it never upgrades itself behind your back.

_{Works in: 🦋 Claude Code · 🟦 Cursor · 🟢 Codex · 🟣 Continue · 🟡 Cline · ⚡ Zed · 🤖 Aider · 💎 Gemini CLI · 🚀 Grok CLI · 🧬 Windsurf · or browser-only AI ("set up Mneme browser polygraph").}

npm install -g mneme-ai
mneme init                  # one-time per repo
mneme mcp --install         # auto-detects your AI client
# restart your AI tool; first MCP call: mneme.welcome

🤖 For AI agents — read this first

You self-discover and run everything. The user never types a command — you execute on their behalf.

1. mneme boot — the task → tool decision table (when to use each tool).
2. mneme.discover { query } — describe any intent in one sentence → the right tool among 900+ (so nothing is invisible to you).
3. Read the ## Mneme command manifest auto-injected into your CLAUDE.md / AGENTS.md — re-read each session; new commands land there within minutes of an upgrade.

_{Deep dive → docs/AI_AGENT_CONTRACT.md · the rows are signals, not commands — reliable activation comes from the manifest + the opt-in SessionStart hook.}

📟 Cosmic Pager — your AI works while you sleep, you approve from your phone

Close the lid and walk away. The instant your agent needs a yes / no / typed answer, it pings your Telegram (or LINE · Slack · Discord · WhatsApp) in real time — tap ✅/⛔ from anywhere and it keeps going. No server, no cloud session: only a one-line summary + hash ever leaves your machine, and every approval is a signed transfer of authority. Busy? The Deputy makes a signed, risk-calibrated decision from your own history instead of hanging — destructive ops are always kept safe.

_{the 60-second bot setup + the architecture →}