Agent Vault
Hacker ApprovedShares rank 4 of 20 secrets managers by recommenders
Keeps credentials out of AI agents' context via an egress proxy, so agents never handle raw keys. Critics note it has no security audit and doesn't stop all exfiltration.
Keeps credentials out of AI agents' context via an egress proxy, so agents never handle raw keys. Critics note it has no security audit and doesn't stop all exfiltration.
23 people gave an opinion
- recommend it
- 20
- criticize it
- 3
- approval share
- 87%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 20 people recommend itNeeds 10 or more, met.
- 6.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Keeps credentials out of agent context
“there was no solution that kept credentials out of an agent’s context, preventing theft and unauthorized actions”
Comment from 15 Oct 2026 in “Agent Vault” “The credentials-out-of-context design is what stood out to me.”
Comment from 15 Oct 2026 in “Agent Vault” Interface-agnostic, works without modifying agents
“Where Agent Vault shines is that it fits right into the tools and workflows that your agents are already using”
Comment from 24 Apr 2026 in “Show HN: Agent Vault – A HTTP credential proxy and vault for AI agents” “we feel like this is the right approach in terms of interface-agnostic ergonomics”
Comment from 24 Apr 2026 in “Show HN: Agent Vault – A HTTP credential proxy and vault for AI agents” “interface-agnostic credential brokering without modifying the agent itself”
Comment from 25 Apr 2026 in “Show HN: Agent Vault – A HTTP credential proxy and vault for AI agents” Encrypted credentials, none stored in plaintext
“There's not really any reason to be storing sensitive keys in plaintext on your local disk that the agent can access.”
Comment from 29 Jun 2026 in “A way to exclude sensitive files issue still open for OpenAI Codex” “The nice thing about Agent Vault is the encryption of credentials”
Comment from 11 Jun 2026 in “Show HN: Claw Patrol, a security firewall for agents” Simple, auditable design
“Simpler, auditable, handles multi-recipient natively, no web of trust complexity.”
Comment from 1 Mar 2026 in “How HN: Agent-Vault – A Zero-trust credential manager for AI agents” “This feels cleaner to me.”
Comment from 25 Apr 2026 in “Show HN: Agent Vault – A HTTP credential proxy and vault for AI agents”
Other secrets managers people recommend
The four most recommended other secrets managers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| OneCLI | 39 | 8 | 83% | 6 | — | Approved |
| SOPS | 28 | 5 | 85% | 10 | — | Approved |
| HashiCorp Vault | 26 | 10 | 72% | 10 | — | Approved |
| Agent VaultThis page | 20 | 3 | 87% | 5 | — | Approved |
| fnox | 20 | 4 | 83% | 9 | — | Approved |
What people said
All 28 comments that mention it, newest first. Each links to the original comment.
“The credentials-out-of-context design is what stood out to me.”
“awesome - check out docs.agentvault.io for more info on the technical specs”
“Super excited to finally trust my CC data and passwords with agents with Agent Vault”
“there was no solution that kept credentials out of an agent’s context, preventing theft and unauthorized actions”
“There's not really any reason to be storing sensitive keys in plaintext on your local disk that the agent can access.”
“The nice thing about Agent Vault is the encryption of credentials”
“Infiscals agent vault might be the best middle ground for this kind of setups”
“interface-agnostic credential brokering without modifying the agent itself”
“This feels cleaner to me.”
“we think this first implementation makes a move in the right direction”
“This solves hostile or compromised inference providers.”
“The thing I like about this (Agent Vault) approach is that it's more extensible than what we're offering”
“lots of thoughtful choices we hadn't gotten to yet”
“how are you going to prevent the agent from gaining access to the vault and keys itself?”
“This is a good start, it does covers gaps in certain areas.”
“I really like the approach you've taken of providing an egress proxy.”
“Where Agent Vault shines is that it fits right into the tools and workflows that your agents are already using”
“we feel like this is the right approach in terms of interface-agnostic ergonomics”
“was missing exactly this Vault. I'm relieved not to need to invent (vibe code) it.”
“I think this is generally on the right track with how the industry is thinking about solving credential exfiltration”
“at least AV prevents them from gaining direct access to begin with”
“you'd still be able to exfiltrate data”
“this feels to me like widening the attack surface rather than tightening security”
“These tools are useful, but I can't help to feel like they're solving the wrong part of the problem.”
“OneCLI does not even have a security audit”
“Simpler, auditable, handles multi-recipient natively, no web of trust complexity.”
“gate access to secrets via external service that replaces placeholder values with actual secrets”
“the subsequent malicious actions could be stopped by you”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.