|
Cipherlatch — Agentic Access Management
Cipherlatch gives every AI agent scoped, revocable, short-lived access — the latch opens only for a verified request, and the keys stay in your custody.
|
85 % |
|
Vera: The Agent Authorization Rail
Vera is a neutral trust layer for the agent economy. One API call verifies that an AI agent is authorized to take a specific action on behalf of a specific p...
|
85 % |
|
Agent Trust — Know every agent. Control every capability. Verify every action.
Know every AI agent in your environment, control every capability it may use, and verify every important action. Build agents inside Agent Trust on your own...
|
84 % |
|
PastKeys · Zero-Access Credential Broker for AI Agents
PastKeys is a zero-access credential broker for AI agents. Agents request an authorized operation, never a secret. Short-lived, scoped credentials with a def...
|
84 % |
|
Agent Identity Kit — identity, delegation, and receipts for AI agents
Open-source identity layer for AI agents: sponsored registration, provable delegation chains, just-in-time credentials, a drop-in MCP gateway, signed receipt...
|
84 % |
|
Grantor — give agents permission, not credentials
Agent authority infrastructure: give AI agents bounded, revocable permission instead of raw credentials. Your app verifies a self-certifying deed against a p...
|
84 % |
|
AgentBox — Identity and access for AI agents
AgentBox gives every AI agent runtime a signed, revocable identity delegated from a developer, and governs it with the enterprise's own directory groups, tea...
|
83 % |
|
Agentdriven — Build governed AI agents
Build and operate governed AI agents with isolated runtimes, scoped tools, policy controls, brokered secrets, human approvals, observability and audit trails.
|
83 % |
|
Usery — Authority for your AI agents
Usery gives your AI agents narrow, expiring, revocable authority without sharing your reusable credentials.
|
83 % |
|
kvsecure - Local vault for AI agent credentials
kv stores secrets in a local encrypted vault and gives AI agents brokered ways to use credentials without receiving the raw values by default.
|
82 % |
|
Shrike | Action Governance for AI Agents
Ship AI agents that act — safely. Your policy enforced on every tool call, command, SQL query, and A2A message before it runs. 9-layer engine. Free tier.
|
82 % |
|
Descles — Give your agents what your company knows
Descles gathers your company's systems into one layer every agent can use, in your network and within its permissions, and learns from runs: 76% fewer tokens.
|
82 % |
|
SecretProxy — Egress for AI agents
An egress proxy for AI agents, built on target-scoped credential injection. Keep service credentials outside agent runtimes. Agent-specific controls are in d...
|
82 % |
|
AgentAuth — Delegation tokens for AI agents
AgentAuth lets one AI agent authorize another to act on its behalf — with a spend cap and a short expiry. Signed Ed25519 delegation tokens, server-enforced c...
|
82 % |
|
Metamynd | Runtime Authorization & Governance for AI Agents
Runtime authorization for AI agents: verifiable agent identity, delegated authority, policy enforcement at the moment of action, and tamper-evident evidence...
|
82 % |
|
VIVARY - Coordinate AI agents in ways you can actually explain.
|
82 % |
|
Bouncer — Agents need a network of their own
A federated network for AI agents: identity, bounded authority, secure messaging, and payment — where every action is a message someone authorized.
|
82 % |
|
Caracal
The identity and authorization layer for AI agents. Agents never hold credentials: every action is policy-approved before it runs, delegation can only narrow...
|
82 % |
|
Pryme Intelligence — the governed agentic operating system for business
A governed agentic operating system for business. Build, train, certify and deploy agents that can act — and can prove how far they were allowed to.
|
82 % |
|
OAuth2 delegation and consent for AI agents | Agentic Identity Broker
Agentic Identity Broker — an open-source OAuth2 delegation and consent broker that lets users grant AI agents scoped, revocable access to third-party services.
|
82 % |
Detected social media networks