Trust infrastructure for AI agents. Receipts, not vibes.

I build the full stack that answers one question: should this agent be allowed to do that? Identity, translation, audit, enforcement — every claim on this page links to a repo, a live receipt or a spec. Nothing here is a vibe.

Live: marketnow.site — the registry · utalabs.tech — the stack · alicelabs.site — the company

• 74 PRs merged — 30 into 20 external repositories, 44 into AliceLabs repos. Selected: punkpeye/awesome-mcp-servers #16284 (97k+ star repo), useagenthq/useagent ×5, cognicore-dev/cognicore-env ×7, flisk-sh/flisk #951 (Hall of Fame), floatpane/matcha #1733 (completed the Spanish translation), meetdino/dino #124.
• 57 issues filed — headlined by a fail-closed spend-authority proposal series to agent-wallet teams: microsoft/autogen #8377, crewAIInc/crewAI #8381, safe-global/safe-core-sdk #1453, tkhq/sdk (Turnkey) #1622, privy-io/aws-agentcore-sdk #10, akash-network/console #4549, glama-ai/lightport #15 — plus x402-foundation/x402 #3803 on the PAYMENT-REQUIRED schema.
• 47 PRs open — distribution in flight: MarketNow into docker/mcp-registry #5263 (local + remote), xai-org/plugin-marketplace #1012, solana-foundation/pay #525, browser-use #6226, run-llama/llama_index #23758, plus 15+ curated lists.
• 2 packages on npm: marketnow-mcp — free trust layer for MCP agents (1.1k downloads last month) · @marketnow/uta-conformance — signed ATC/1.0 conformance vectors.
• Registry & audit numbers: 71,198+ MCP servers indexed on marketnow.site · Sentinel: 1,211,488 checks, 1,030 threats caught · mcptry 96/100, #454 of 4,704 in AI & Agents.

Four files, one question. Each product answers it at a different layer.

Fail-closed is the house rule: unreachable revocation check → DENY. Downtime degrades to "no", never to "probably fine".

sloth.utalabs.tech · repo

Sleepy Lazy Overnight Task Handler. A 1B open-weight brain (Gemma 3 + llama.cpp) that runs on your CPU and does the boring stuff while you sleep. Every action lands on a SHA-256 hash chain, signed with Ed25519 — offline-verifiable by anyone in ~30 seconds, no account. Irreversible clicks stay human.

• Read tonight's receipt: receipt/latest.json
• Verify the chain yourself: sloth.utalabs.tech/verify

marketnow.site · status · repo

Where the stack meets the world: security infrastructure for AI agents — skills, credentials and domains verified across 71,198 MCP servers indexed (135,547 tracked), with a free MCP API — 10 tools, no keys, no signup — plus signed submissions, revocation checks and a Sentinel score on every entry.

• Free API: marketnow.site/api/mcp
• Live status: status.marketnow.site
• Agent surface: uta-ai — installable skills, subagents, MCP servers, Claude Code plugin

• alethech — verifiable agent continuity: Ed25519-signed memory, hash-linked DAG, key rotation with reachability guarantee. Local-first, zero-LLM, zero-blockchain. Docs: alethech.alicelabs.site. Listed in Awesome-Agent-Memory after a maintainer audit of the claims against the code.
• universal-trust-adapter — ATC/1.0 protocol spec + reference impl (Ed25519, RFC 8785 JCS, 10 verification controls). One-command conformance: npx @marketnow/uta-conformance (36 published vectors). Listed in awesome-agent-native-services after review (PR #229 merged).
• marketnow-mcp — free trust layer for AI agents over MCP: verify credentials (8 formats), scam-check domains, fingerprint tools. Live: marketnow.site/api/mcp. Listed on mcp.so.
• sloptotal — open-source AI text detector: 23 engines, one calibrated score, every number measured on a public benchmark. Self-hosted, CPU-only. Live: sloptotal.com.
• mcp-suite — 229 MCP servers mapped to real agent pains: 1,035 tools, 349 functional tests.
• BernAudio Model 80 — real-time professional audio measurement in the browser: RTA, spectrogram, transfer function, impulse response, SPL. Free alternative to Smaart. repo

• alethech-agent-vault — Vultr Agent Rush (Nov 3–8, 2026): verifiable agent execution on Vultr; every agent action signed via alethech.
• mailhand-aws-cds — AWS CDS Agentic AI Partner Hackathon (Oct 28, 2026): agentic email code review via AWS SES + Bedrock AgentCore.
• mermail-escrow-agent — Mermail Build & Demo bounty: peer-to-peer escrow over a Mermail email thread — buyer funds held in Agent Wallet, released to the seller only after buyer email confirmation (USDC).
• zolo-qloo-agent — Qloo hackathon submission: conversational cultural-discovery agent on Cloudflare Workers AI.

• useagenthq/useagent — 5 merged PRs: axe accessibility sweep across the five main pages with fixes, desktop smoke test on the packaged app, collapse-all and jump-to-error controls in the trace view, content-aware waits, package README.
• cognicore-dev/cognicore-env — 7 merged PRs: quarantine-backend flush at end of import_bundle, lexical-search score bounds in the SQLite backend, verifier-defeat chain topology tests, CI dependency and mock fixes.
• punkpeye/awesome-mcp-servers #16284 — alethech listed under Knowledge & Memory after maintainer review.
• profullstack/x402-gateway #23 — x402 verification badge endpoint for external indexers.
• Podiom/Podiom #380 — MCP pin dedupe merge semantics with focused tests.
• aniruddhaadak80/skills #471 — Ed25519 skill verification badges (sign + verify).
• taikotalent-phishing-iocs — published IoCs and attack-chain writeup for a live fake-recruiter campaign (dev.to writeup).

• run-llama/llama_index #23758 — optional trust-verification middleware for MCP servers; companion fix #23352 (simple fusion builds fresh wrappers instead of mutating retriever-owned ones).
• browser-use/browser-use #6226 — trust verification before browser tool execution.
• docker/mcp-registry #5263 · #5175 — MarketNow local and remote MCP servers.
• xai-org/plugin-marketplace #1012 — marketnow as a remote source with pinned sha.
• solana-foundation/pay #525 — reference remote spending authority over HTTP.
• Curated lists with open submissions: punkpeye/awesome-mcp-servers #13933 (MarketNow) and #17326 (uta-shield), punkpeye/awesome-remote-mcp-servers #1928, x402-foundation/x402 #3815, and 10+ more.

• Hacktoberfest 2026 Completionist badge — awarded by DEV Community (Nov 2026), "one of Hacktoberfest 2026's top participants". Profile: dev.to/edison_flores_6d2cd381b13.
• XERJ Corpus Hub contributor — universal-trust-adapter selected and indexed by the XERJ Corpus Hub (Oct 2026).
• MarketNow on mcptry — #454 of 4,704 in AI & Agents, score 96/100 (Nov 2026). Also listed on mcp.so and mcpservers.org.
• Flisk Hall of Fame — first merged contribution (PR #951, closes #905): refactored the project.json file name into a PROJECT_JSON constant; 7 kyu rank in Flisk CLI Cove (Oct 2026).
• Flisk Founding Contributor #8 of 100 — numbered badge reserved for the first 100 code contributors to flisk-sh/flisk; unlocked via the Flisk Discord (@arxh80), Nov 2026.

Long-form series on building agent trust infrastructure — what a maintainer audit actually checks, and the honest accounting of what listings pay: dev.to/edison_flores_6d2cd381b13

utalabs.tech · alicelabs.site · AliceLabs LLC — Wyoming, USA · Quito, Ecuador