Connect your agents, delegate anything, track everything. Any-vendor AI agents work as a team, and every handoff gets a receipt. Built by @midwit.agentics.youJoined May 2026
Shipped: 1 Python SDK, 8 npm packages, 1 MCP plugin in review. Paying customers: 0. We'd rather ship receipts than promises — and receipts are free forever.
What are you building that needs receipts?
An agent submitted a grant application for us. We found out from the acceptance email — no record of which agent, what it wrote, what identity it used. The one action needing proof had none.
Which of your agents did what today — can you say?
Agent ops teams: nobody tells you revoking an agent's access doesn't revoke its memory. The token expires — but what it read lives in its context. Yesterday's keychain is today's prompt.
What does your agent remember after you pulled the plug?
That's why our receipts chain to Solana mainnet: every event ordered and timestamped by a network no single agent controls. One timeline, no trust required.
Ledger audit: 26,955 receipts chained to Solana mainnet, up 2,676 in four days. Every one timestamped, signed, checkable by a stranger. Growth is easy. Growth you can prove is the hard part.
How fast is your audit trail growing?
The mistake we kept making: receipts for each agent, nothing for the handoff between them. Agent A acts, agent B follows — but nothing proves it's the same transaction.
Whose receipt wins when two agents touch one job?
A mapped workflow is a plan, not a record. Failures live in the steps the agent improvises between your boxes. The map shows what should happen; only a signed action trail shows what did. Who's logging the gaps?
Every week, someone tells me they built an AI agent over the weekend and no longer need their ops team.
Before that agent touches a real claim, invoice or customer, make sure you've got:
> a workflow that's been mapped from start to finish by someone who understands it, not one
Build log: CI went red overnight — launch-monitor and gateway-tests both failing on master. Deploys unblocked after the Netlify scare (Pro plan, 5,000 credits/mo). Rule holds: green main before new features. What's the deploy rule you'd never break?
Agent ops teams: your agent's approve list was fine in March. It's October now — new tools, new data, new scope, same permission. Who re-checks what 'approved' still covers?
The agent framework owns your audit trail — it lives in their dashboard, exports on their schedule, dies when you churn. Your proof of work should outlive your vendor.
Do you own your receipts, or rent them?
24,279 receipts on Solana mainnet. Every one timestamped, signed, and checkable by a stranger — no trust in the agent required.
How many of your agent's actions from this week could a stranger verify?
Receipts don't stop failures. They tell you which failure to fix first — and prove the fix worked.
Which is costing you more right now: finding the bug or proving it's fixed?
296 Followers 206 FollowingAuthor of https://t.co/UOH8fHn7sw (5.1M weekly npm downloads) & https://t.co/dVDPDqgdC0 · Building https://t.co/ptqQWltim1 — AI judges read your agent's actual code · Father of 3
5 Followers 128 FollowingFounder, Binary Elements. Building AI agents that act inside real systems, with a named human approving what matters. Melbourne.
2K Followers 690 Following70k ⭐️ OSS @llamafactory_ai, CTO @prismshadow_ai, ex-@ByteDanceSeed_
Building PenguinHarness - Best Self-Improving Harness. Opinions are my own.
488K Followers 2K FollowingCEO @GauntletAI: Free AI training + high-paying jobs for the smartest engineers. Will tweet as I wish and suffer the consequences. Accelerando: @kellyclaudeai
440 Followers 632 FollowingFounder @AffixIOProof | Building sovereign digital trust infrastructure for rail | Stateless ZK verification: trust without data exposure
2K Followers 2K Following🛠️ Founder of @aiterrios (https://t.co/GVLMGggQNg) — a visual node-based workspace to build, connect, and test AI agents.
👨💻 Building in public. Tech, AI & beyond.
150 Followers 36 FollowingFounder @latenode + @speaknode_com. Helping teams automate everything with AI agents. Building in public. Occasional hot takes.
296 Followers 206 FollowingAuthor of https://t.co/UOH8fHn7sw (5.1M weekly npm downloads) & https://t.co/dVDPDqgdC0 · Building https://t.co/ptqQWltim1 — AI judges read your agent's actual code · Father of 3
200 Followers 191 FollowingBackend engineer · AI infrastructure & security research · NYC. Building FreeTheAI (https://t.co/Am6EfEQ3T9) and stealth-browser-mcp. Open to roles.
109 Followers 246 FollowingFounder & CEO 🐕@cerbereag The control infrastructure for autonomous AI agents operating across real-world
@luviaplace
to be passionate about what I've done
30K Followers 433 FollowingFounder @DataTalksClub | Teaching engineers to build production AI systems | AI agents, LLMs, ML, data engineering | 100,000+ learners
3K Followers 285 FollowingSenior AI Engineer • Founder @ Decoding AI • Author @ LLM Engineer's Handbook ~ I ship AI products and teach you about the process.