I've been writing about agent governance for months. This is the first time I've been able to show it instead of explain it.
45 seconds, and yes, there's a dragon guarding the keys.
https://t.co/WluwkhBk0q
API keys, passwords, wallet keys. One bad instruction and a key walks out the door.
Here's what Feir does about it: keys in a vault the agent can't open, one checkpoint that denies anything not allowed, and every action sealed into a log an auditor verifies on their own machine.
started dusting off an old project, https://t.co/TMeB6BVQH3, from scratch, would be great to see how Devin does on it! (it's essentially a network to rank up your profile as a code reviewer instead of leetcode, as that's a more important skill than writing the code nowadays, while helping vibecoders)
Averin v0.1.0-alpha is out: a tamper-evident flight recorder for AI-agent activity. Signed, hash-chained records, verifiable offline without trusting the machine that produced them. Source-only alpha. Apache-2.0. https://t.co/V00NiWr2gA
We are considering an early adopter stealth launch of our Beta….
- Limited Time
or
- Limited Seats
Which ever comes first!
Perks:
+ In platform “Airdrop”
+ [Redacted]
+ [Redacted]
+ [Redacted]
While at @draper_u@OrionFund accelerator program we have been prompted to get feedback, So what better feedback than from real users?
The EU AI Act changed in July.
High-risk deadlines moved, but Article 50 transparency rules are already in effect.
For AI agent teams, now is the time to build enforceable oversight, action-level controls, and verifiable records.
Our practical guide: https://t.co/2ffho4UXYB
4/ Written in Rust. Self-hosted. MIT.
Repo → https://t.co/IzWtxeGKwD
Site → https://t.co/sfFtGVjiWH
This is a relaunch of a much simpler earlier version I archived. The current one expanded significantly from that base. Would love eyes on the security model and the MCP surface especially.
(If you build agents or MCP servers, tell me what’s missing.)
1/ Agents + long-lived secrets is a mess.
I kept putting API keys (and PGP keys, SSH keys…) into agent environments and watching them leak into prompts, tool calls, and logs.
So I built Vultrino – a credential proxy for the AI era.
2/ Core idea is simple:
Agent only gets an alias + an action surface.
Vultrino holds the real secret and injects/authenticates/signs on the other side.
Never in the prompt. Never in the context window. Never in the agent’s memory.
Guardrails shape what a model says. Governance controls what an agent does.
We wrote a plain-language reference on what agent governance actually is, how it differs from guardrails, and the six properties a real governance layer needs.
First of five: https://t.co/HBRD09a2iO
if your agents can act, you need to know what they did and who said yes.
building exactly that. looking for design partners, free in alpha, I'll do the integration with you
https://t.co/g54kqEvZqI