{ "markdown": "
\n\n\"μνήμη\n\n# The Trust & Cost Layer for AI Agents\n\n

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.

\n\nμνήμη · NEE-meh · Greek for \"memory.\"  ·  Vendor-neutral · MIT · air-gap-ready · 20,000+ pinned tests.\n\n

\n\n\"npm\"\n\"GitHub\n\"MCP\n\"GAUNTLET\"\n\"TRUTH\n\"license\n\n
🛡 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.\n\n
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.\n\n
\n\n---\n\n## What it is, in one picture\n\nYou 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.\n\n```mermaid\nflowchart LR\n AGENT[\"🤖 Any AI agent
Claude · GPT · Gemini · Grok · Cursor\"]:::agent\n subgraph MNEME[\"🧠 MNEME · one local boundary · signed · MIT\"]\n direction TB\n GUARD[\"🛡 GUARD
injection firewall · secret-blinding · destructive-cmd co-sign\"]:::guard\n VERIFY[\"🔍 VERIFY
catch hallucinations · grade agent security · certify output\"]:::verify\n MEM[\"♾ REMEMBER
signed cross-vendor memory + verified context\"]:::mem\n end\n MODEL[\"☁️ Hosted model\"]:::ext\n MACHINE[\"💻 Your code & machine\"]:::ext\n LEDGER[\"📜 Offline-verifiable receipt\"]:::ledger\n AGENT <--> MNEME\n MNEME <-->|screened| MODEL\n MNEME <-->|gated| MACHINE\n MNEME -->|signs every step| LEDGER\n classDef agent fill:#0b1020,stroke:#00d4ff,color:#ffffff;\n classDef guard fill:#11182f,stroke:#c084fc,color:#e6e6f0;\n classDef verify fill:#11182f,stroke:#22d3ee,color:#e6e6f0;\n classDef mem fill:#11182f,stroke:#f0b429,color:#e6e6f0;\n classDef ext fill:#0b1020,stroke:#2da44e,color:#ffffff;\n classDef ledger fill:#1a1206,stroke:#f0b429,color:#ffffff;\n```\n\nMeasured · Signed · MIT. When Mneme can't prove something it says UNKNOWN instead of guessing — that discipline is the product.\n\n---\n\n## The capabilities\n\nEach is a runnable command + a deterministic test (`gauntlet=100`) + a signed, offline-verifiable result. Tap a row for the full story.\n\n| | Capability | What it does | Detail |\n|--|--|--|--|\n| 🌌 | **Singularity Search** | Find the right tool among **900+ from one sentence** (EN/Thai) — so no capability is ever invisible to an agent. *top-3 ≥98.5%* | → |\n| 🧠 | **Hallucination Protection** | The **last gate before an agent answers** — a mesh of nerves reflex-blocks any hard fault, abstains when unsure. *precision-when-TRUSTED = 1.0* | → |\n| 🛡 | **Agent Security Posture** | Grade an agent's whole safety surface in one **signed A–F report**: MUTAGEN derives novel attack variants vs its guardrail · ESCALON finds tool-chain **privilege-escalation** paths + poisoned tools. *postureGauntlet=100* | → |\n| 📜 | **Public Honesty Ledger** | Every public claim binds to a probe; **CI fails the build if one drifts**. A signed ledger anyone verifies offline — the badge **can't be faked green**. *zero-drift* | → |\n| 🎗️ | **Verified-by-Mneme** | A signed **trust certificate for AI-worker output** — never certifies a deliverable with a known fault. *CERTIFIED-precision 1.0* | → |\n| 🛂 | **The Context Passport** | **Cross-agent verified context** that lives in git — what one agent learns, the next inherits; poison is screened out. *TRUST-precision 1.0* | → |\n| 🚢 | **The Ark** | **Accountable AI reproduction** — a child agent inherits values + scars + verified context and can only NARROW authority. *a malicious birth is never approved* | → |\n| 🌌 | **Cosmos** | Compress memory into a seed, **inflate only the slice a problem needs**; entangled-gravity retrieval visits far fewer nodes than a scan. *≥98.5%* | → |\n| 🎖 | **Agent Run Certificate** | A portable **signed proof of an agent's whole run** that anyone verifies offline — and that can't lie about itself. | → |\n| 🛤 | **The Matrix Rail** | One signed, streaming pipe every agent crosses — reachable **three ways: MCP · gRPC · CLI** over a single core. | → |\n| 🏛 | **The Agent Governor** | Set a **Charter** once; your agents run inside it 24/7; you approve only the genuinely-irreversible escalations. | → |\n| 🔭 | **−95.9% tokens** | Orient on a file's full structure for a skeleton instead of a raw read — the saving metered into a signed ledger. | → |\n\nMore: 💗 THYMOS (an auditable affective core) · 🛰 APHELION (governance with no cloud) · 🧬 Architectural Regression Firewall · 🚀 in-process SDK (30-80× faster) · 🤖 cross-vendor Byzantine consensus.\n\n---\n\n## 🩻 Try it live — no install\n\nPaste any public repo and get a signed result in seconds:\n\n| | | |\n|--|--|--|\n| 🩻 **review** — graded Codebase Accountability Report | 🎗️ **certify** — trust certificate for AI output | 🎭 **persona** — each dev's commit style |\n| 🔮 **seance** — why a file is the way it is | 🧭 **brief** — git-native repo context | 🚢 **ark** — accountable agent reproduction |\n\nDeterministic · signed · no LLM — every finding traces to a real file. see all 10 checks →\n\n---\n\n## ⚡ Install in 60 seconds — you never type a command\n\n**Say one sentence to any AI agent you already use:**\n\n> *\"Install Mneme from https://github.com/patsa2561-art/mneme-ai per the AI agent contract.\"*\n\nIt 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.\n\nWorks in: 🦋 Claude Code · 🟦 Cursor · 🟢 Codex · 🟣 Continue · 🟡 Cline · ⚡ Zed · 🤖 Aider · 💎 Gemini CLI · 🚀 Grok CLI · 🧬 Windsurf · or browser-only AI (*\"set up Mneme browser polygraph\"*).\n\n
\nPrefer to type the commands yourself?\n\n```bash\nnpm install -g mneme-ai\nmneme init # one-time per repo\nmneme mcp --install # auto-detects your AI client\n# restart your AI tool; first MCP call: mneme.welcome\n```\n
\n\n---\n\n## 🤖 For AI agents — read this first\n\n**You self-discover and run everything. The user never types a command — you execute on their behalf.**\n\n1. **`mneme boot`** — the *task → tool* decision table (when to use each tool).\n2. **`mneme.discover { query }`** — describe any intent in one sentence → the right tool among 900+ (so nothing is invisible to you).\n3. **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.\n\nDeep dive → docs/AI_AGENT_CONTRACT.md · the rows are signals, not commands — reliable activation comes from the manifest + the opt-in SessionStart hook.\n\n---\n\n## 📟 Cosmic Pager — your AI works while you sleep, you approve from your phone\n\nClose 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.\n\n**the 60-second bot setup + the architecture →**\n\n---\n\n
\n\n## 👤 Author\n\n\"Shinnapat\n\n### Shinnapat Phunsriphatchalakul\n**AI Software Engineer · Truth-Infrastructure Architect**\n\nDesigner + sole maintainer of Mneme — built solo · MIT · 20,000+ pinned tests · dual-100 GAUNTLET + TRUTH GATE.\n\n| Email | GitHub | npm | Discord | WhatsApp | Telegram |\n|--|--|--|--|--|--|\n| patsa2561@gmail.com | @patsa2561-art | @mneme_npm | `pat195` | +66 93 945 5645 | @devson2561 |\n\nOpen to: truth-infrastructure / AI-safety collaboration · safety-critical AI consulting · vendor partnerships (embed Mneme inside Cursor / Cline / Claude Code / Grok CLI) · full-time where the bottleneck is trust, not capability.\n\n
\n\n---\n\n
\n\n📦 npm · 💻 GitHub · 📘 Functions (EN) · 📗 ฟังก์ชั่น (ไทย) · 🤖 AI Agent Contract · 🏛 Enterprise · 📜 CHANGELOG · 📃 MIT\n\n
Mneme is the diamond in the dirt nobody saw the value of — cut and polished, it becomes the most valuable diamond in the world.\n
Made with care for every AI agent that wants to remember + verify + reason together.\n\n
\n", "bytes": 12475, "sha": "49510b250e8eabc14b252d1a3a9968a49f4f5e1b063b130e9bc119a469b31493", "repo_slug": "patsa2561-art/mneme-ai", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_patsa2561_art_mneme_ai_2888c251/readme" }