@saen_dev@ClementDelangue Real safety work happens at system architecture. That's what OverCR is.. a deterministic state machine between the agent and its tools. Every action, transition, and decision logged to an append-only audit trail. Guardrails are theater. Architecture is safety.
The architecture is legitimate; proper nonce management, real MultiversX tx handling, the README anchor on mainnet is verifiable. Appreciate you sharing it.
For our stack though, it's not the right fit. We already have git for immutable audit trails and OverCR's integrity hash chains for session-level verification. Adding on-chain anchoring would mean every vault write costs $0.05+ and introduces a dependency on MultiversX network availability and a repo that's primarily AI-generated with no open source license. The marginal value over what we already have is near zero for our use case.
Good luck with the project though! if you ever need legal-grade proof of existence use cases, the architecture is solid.
1/ I ran Claude Code for six months. Then I ran Codex. Then I ran both at the same time, hoping the combined cost would finally justify the output.
It did not.
The problem was not the models. Claude is excellent. The frontier models are the best available.
The problem was memory.
Every session starts from zero. The agent does not remember what you taught it last week, what worked, what failed, or why a decision was made.
I wanted an agent that gets smarter over time because it remembers what it learns.
🧵
Ran into the same wall. The fix isn't teaching the agent what to throw away, it's never storing the wrong thing in the first place. Built OverCR with schema-constrained fact fences.. the agent reads curated context for each task instead of dumping everything into a wiki that bloats. Intentionally constructed context beats garbage collection.
100%. The tool boundary is where agents actually die.. a garbage response or malformed schema cascades through the whole loop, not just one call. Built OverCR to handle exactly this: structured context files the agent reads each cycle so it can tell when the tool output drifted from what it was supposed to produce.
@cms_@Marie_Haynes Building the same direction with OverCR. Structured context files the agent reads each cycle. Markdown vault as the agent's external memory. Portable, inspectable, file-based. No vector DB. We’re early.
@danielchalef@krishnan The eval design issue makes the broader point: memory quality depends on what you retrieve and how you constrain it, not just what you store. Built OverCR with schema-constrained fact fences in a markdown vault so the agent reads curated context, not retrieved noise.
@kreoxi Video is on the way of using my stack. Right now I just have my github repos up with the entire codebase I use alongside Hermes and Obsidian. The article explains how I set them all up to work together.
All 4 pieces are open source, OverCR and Cammander can be picked up and configured. Let me get a solid prompt for Hermes that will set up all of the skills needed. Obsidian you’d want to set up yourself. The full article is a little more detailed if you want to pick it apart. I’ll be making a PR for OverCR within Cammander while Hermes watches while recording for a full tutorial and demo.
@krishnan AI memory sounds like personalization. In practice, it's context governance. Built a structured context layer that reads from a markdown vault each cycle so the agent can tell when it's drifting.. no vector DB, no similarity search, just deterministic facts picked for the task.
11/
The result is not polished like a commercial product.
It is better than a commercial product because it knows me.
The models will come and go. And it’s not your decision when they do.
The memory stays. No matter who tells you what models you’re allowed access to.
Full article:
open.substack.com/pub/guideboard…
10/
The third theory is deterministic governance.
I do not want a language model deciding whether governance rules should apply.
Rules should be rules. Models should be models.
Keep those responsibilities separate.
243 Followers 1K FollowingFounder https://t.co/KsxMLVA6E5
On-chain notary, accountability layer for AI agents.
Prove Before Act : Anchor the WHY Before the WHAT.
@MultiversX $EGLD #x402 $USDC
1K Followers 993 FollowingKidney Transplant to Gold medalist🥇🥇🥇for 🇮🇳
World Transplant Game 🇦🇺 2023,🇩🇪2025
Building AI Agents, AI Tips & Tools, Sharing My Learning & Journey
309 Followers 298 FollowingBuilding AI-powered, player-driven games | Women in Games Ambassador | Thinking out loud about consumer behavior, product design, AI systems & #gamedev
508 Followers 5K FollowingPhotographer & dev, 20y B2B. Hetzner 2006. Aboard Ship or Die, shipping one product a month. Out-earn my agency by 1 Jan 2027. Me and AI as a team. Let's sail.
48 Followers 307 FollowingCheck out my fanfiction webnovel. After being reincarnated into the The Naruto-verse, a scientist sets out on a mission to become a medical ninja and inventor.
104 Followers 340 FollowingFear of FEMA – duality‑driven, conspiratorial, indie synth / experimental music
Make the art you have to make
Whatever road it means you take
167 Followers 181 FollowingJust a guy with a laptop 💻, WiFi 📶 and a dream 💰.
Watch me.
I will not tweet it, but there will be signs.
Founder @jobsearchpal
5 Followers 39 FollowingBuild solutions for researchers, developers & marketers — to cut costs, save time, grow with AI automation/agents & keep things affordable. DM me for discussion
9K Followers 7K FollowingA technology company delivering marine insights through the fusion of robotics and data analytics, empowering decision-makers with real-time information.
7K Followers 6K FollowingLeading company specializing in surface metal finishing machinery, marine robotics with @GPASEABOTS, New Space, power electronics, and medical devices.
386 Followers 1K FollowingGrew up listening to The Kingston Trio, Ramsey Lewis, Traffic, Joe Cocker and the Allman Brothers. Crinkle cut fries are trash. Reminding you to deadlift.
243 Followers 1K FollowingFounder https://t.co/KsxMLVA6E5
On-chain notary, accountability layer for AI agents.
Prove Before Act : Anchor the WHY Before the WHAT.
@MultiversX $EGLD #x402 $USDC
226 Followers 767 FollowingGeneralist Investor. I'm here to stimulate my thinking and prune my ideas by engaging in intellectually honest discussion. Not investment advice, obviously.
309 Followers 298 FollowingBuilding AI-powered, player-driven games | Women in Games Ambassador | Thinking out loud about consumer behavior, product design, AI systems & #gamedev
4K Followers 2K FollowingBuilt 20+ products, co-founder Chessable (exit), I post about Product, Psychology, Start Ups, Video games & Longevity 🌰, building @helperone_ai
209K Followers 3K FollowingFollow for posts about GitHub repos, DSPy, and agents
Subscribe for top posts
DM to share your AI project (Due to volume of DMs I'll prioritize subscribers)
14K Followers 504 FollowingBuilding with AI agents in public. Cofounder @TweetsMashApp + LinkedMash(https://t.co/pbOsWhbhaB). Sharing what actually works.
10 Followers 39 Followingengineer in paris, building in public. i use ai to ship code that actually lasts. currently: mars. adhd-flavored, results may vary
2K Followers 216 FollowingI’ll come work for your startup for free for a day, no strings attached. my way to give back to the community for outcomes I’ve achieved. read more https://t.co/qPFnmmHvHA
571 Followers 1K FollowingActual Mad Scientist. I build agent systems, make experimental art. Impossible things are just poorly scoped requirements. Warning: I am a Dadaist.
1K Followers 1K FollowingLisp hacker. Creator of Sonic XA and Sprachspiel. Trying to make sense of things on a sea of AI hype and have some fun.
Don't take my tweets too seriously.
632 Followers 438 FollowingEri // building for the agentic world //
technical staff @honchodotdev • @plasticlabs
// ex-La Monte Young disciple //
Github: https://t.co/TxIMi91x4y
508 Followers 5K FollowingPhotographer & dev, 20y B2B. Hetzner 2006. Aboard Ship or Die, shipping one product a month. Out-earn my agency by 1 Jan 2027. Me and AI as a team. Let's sail.
48 Followers 307 FollowingCheck out my fanfiction webnovel. After being reincarnated into the The Naruto-verse, a scientist sets out on a mission to become a medical ninja and inventor.