|
Tenuo | Task-scoped authorization for AI agents
Give AI agents task-scoped authority, check every action before it runs, and narrow permissions across delegation. Open source, Apache 2.0.
|
86 % |
|
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.
|
85 % |
|
Emberlink · agents need authority at runtime
Emberlink is the Grant Warden for AI agents. Scoped grants in, signed receipts out — the human's signature on machine action, verifiable offline.
|
85 % |
|
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...
|
84 % |
|
ArgSeal | Deterministic authority for AI tool calls
ArgSeal is a runtime authority layer for AI agents. It enforces host-issued, field-scoped authority before protected tool calls execute.
|
84 % |
|
Alvoki | Let agents act without broad credentials
Let agents use GitHub, MCP tools, API actions, and deployment targets through Alvoki without placing broad provider credentials in the agent environment.
|
84 % |
|
Crewhelm — Open-source control plane for AI Agents
The open-source personal control plane for owner-controlled Agents on Cloudflare.
|
84 % |
|
ActaMeshAI | Accountability for Enterprise Agents
Put policy, approvals, scoped credentials, and evidence between enterprise AI agents and the tools they use.
|
84 % |
|
GeraGuard is paused | GeraGuard
GeraGuard is paused. The service is not operating, no payments are being taken, and no new signups are accepted.
|
83 % |
|
Local access control for AI agents | Vardra
Vardra gives named AI agents scoped, time-boxed access to local secrets with Ask-first policy, audit, and next-use revocation on macOS.
|
83 % |
|
AiOverload, governed execution for AI agent fleets
Governed execution for AI agent fleets: an event-sourced audit log, default-deny on the declared tool plane, per-run credentials on gateway-backed runs, ever...
|
83 % |
|
AOSIQ — Agent operations runtime for regulated infrastructure
A capability-authorization runtime for AI agents and deterministic actors, with built-in human approval gates and tamper-evident audit. Same governance primi...
|
82 % |
|
MCP Gateway & AI Agent Authorization | Endram
Control AI agent and MCP tool calls with identity-aware policy, human approvals, one-use grants, and signed evidence.
|
82 % |
|
Approval Broker
Approval workflows pause high-risk agent actions until accountable review, delegated authority checks, and exception handling are complete.
|
82 % |
|
z-gateway | Runtime governance for AI agents
z-gateway helps teams govern MCP-connected AI agents with policy checks, approvals, quotas, and audit trails across GitHub and database workflows.
|
82 % |
|
Brain — AI agents that build software
Brain is an open-source desktop app where AI agents coordinate autonomously to build software. Add a project, set a goal, agents do the rest.
|
82 % |
|
Neurelay — AI Agent Governance
Policy-driven governance for AI agents. Control which tools your agents access, with what permissions, under whose authority. Every action auditable.
|
82 % |
|
node9 · Access control for AI agents
Access control for AI agents. You decide what your agents can do; node9 enforces it before they act: allow, review or block each tool call, with every decisi...
|
82 % |
|
DriftGuard — Runtime Governance for Autonomous AI Agents
An independent enforcement layer between AI agents and everything they touch. Every action checked against an approved plan at runtime. Every decision record...
|
82 % |
|
AgentCI Guard — Review the authority behind your agent
AgentCI Guard is an experimental static linter for risky AI-agent workflows in GitHub Actions. Review token permissions, event paths and analysis limits.
|
82 % |
Detected social media networks