sudo founder @ https://xitter.cf/t.co/G9G53oNzf6 // digital sovereignty infrastructure Esver OS (core) Mr Haven (web3 non-custodial) | Visage (Face Auth for Linux)

EST
Joined June 2016
Mr Haven’s smart contracts are now public. The code securing live and programmable time vaults on @base is open: verifiable, auditable, and inspectable by anyone. github.com/sovren-software/m… 🧵
5
1
2
8
4,738
Trillions of dollars are moving onchain. But the systems used for long-term wealth coordination — estate planning, inheritance distribution, beneficiary management, insurance coverage — were designed for traditional financial rails. They do not map cleanly to digital-native assets, global families, or self-custody. At the same time, self-custody without recovery introduces its own failure mode. Onchain infrastructure can solve both problems. But only if the underlying primitives are open. T4 Mr Haven V1 has been live on Base since December 2025: mrhaven.io Core contracts: VaultRouter 0x8C09a5f79e62D29BeB9d2FA710Ecc4cC17cdE842 PlanExecutor 0x244eA67F2FcaEBeEBeCdFF1cE45a9abB4918E02D EmailEscrowManager 0x2E3E2aC4F32A0eEe3b811D302fBB897f1E027b25 Verify the deployments on Basescan. Recompile from the v1.0.2 release tag. Bytecode is the proof. T5 Each user receives a dedicated personal vault. While assets remain time-locked, capital can earn yield through Aave V3. Distribution logic is governed by user-defined plans: • scheduled execution • inactivity-triggered execution • beneficiary-directed distribution Beneficiaries can be specified either by wallet address or by email using hash-locked escrow flows.
3
1
2
1,701
The protocol is dual-licensed: • AGPL-3.0 for the core protocol implementation • MIT for interfaces, libraries, and integration tooling Inspect it. Audit it. Fork it. Build on top of it. The next generation of digital-asset protection infrastructure will be open-source by default. @BaseHubHB @baselatam @EFetheverywhere @CoinbaseDev @ethereum
1
1
1,053
For the past five months, I’ve worked 70+ hour weeks to bring this idea to life. The thesis is simple: if AI is going to excel at computer use, it should be the computer itself. Today a milestone. Still early, much more ahead. 👇
1
5
997
This isn’t “small model beats GPT-5.5.” It’s “encode the workflow, and dispatch becomes the bottleneck.” What’s still hard: anti-bot reputation, cross-site transfer, and durability over days.
1
3
546
If you have a recurring workflow you wouldn't trust to a normal cloud agent, healthcare, admin, legal, compliance, back-office, let's talk. ▎xitter.cf/TheCesarCross/status/2…
1
4
522
Running a hard live-web workflow on our substrate, a cold prompted browser agent succeeded 8 out of 10 times at a median ~390s. After we compiled it into an executable skill, the same task hit 28/30 on a fresh local iGPU at ~58s median. The bottleneck wasn't the model. 🧵
3
2
3
690
This isn't "small local model beats GPT-5.5." It's "once the workflow is encoded, the dispatch path becomes the bottleneck." Hard problems remain, anti-bot reputation, cross-site transfer, production durability across days. The article names them.
1
2
237
If you have a recurring workflow you wouldn't trust to a normal cloud agent, healthcare admin, legal, compliance, back-office, let's talk. Full writeup: xitter.cf/TheCesarCross/status/2… Private AI that actually does the work.
2
341
1,800+ benchmark runs we ran internally at Sovren: - Optimized prompting alone: ~0pp uplift on knowledge retrieval - Engram + Dendrite harness on a local 27B Qwen: +34.2pp success rate, tighter variance, 40pp higher failure floor For project-specific context and coding agents, retrieval infrastructure is delivering more than model scale or extra reasoning. Posted the full results on @sovren_software. Curious how this lines up with what others are seeing in production.
2
1
8
431