|
EverHarden — Know what your support agent can approve
Review the rules around your support agent's refunds and account changes. Find gaps, understand what needs approval, and plan the next fix.
|
88 % |
|
ROJO · Behavioral security for AI agents
Rojo is behavioral security for AI agents. We drive your running agent with adversarial inputs, record every tool call it actually makes, and hand you the ex...
|
85 % |
|
ActionSure | Contact-center workflow assurance for AI customer-service agents
ActionSure is contact-center workflow assurance for AI customer-service agents. Test whether agents safely complete refund, billing, escalation, and case-clo...
|
85 % |
|
Assevra — Find agent failures before your users do
Open-source agent evaluation with actionable findings, explicit release gates, and portable evidence. Connect captured runs, fix failing cases, and verify th...
|
85 % |
|
Rete.si: Your agents should learn from each other
Rete.si turns AI support agents’ best conversations into human-approved playbooks that spread across the team—and retires the ones that stop helping.
|
85 % |
|
Gradia | Enterprise AI evaluation and workflow intelligence
Test AI agents on your business tasks. See what succeeds, what fails and whether a change helps. Capture workflows and connect the results to reviewable evid...
|
84 % |
|
Roleplay | Social-engineering tests for AI agents
Find AI agent social-engineering exploits locally, fix them as a team, and prevent regressions in CI.
|
84 % |
|
AI Agent Guardrails & Approval Workflows | Gatewise
Control AI agent actions before execution. Gatewise applies deterministic guardrails, business policies and human approval workflows to your agent tools.
|
84 % |
|
TraceDojo — Agent testing
Run controlled failures against your agents. Inspect every action and compare the fix.
|
84 % |
|
Runweft — Turn agent failures into tests
Runweft is developing regression testing for AI-agent workflows. Turn failed runs into test fixtures, compare changes, and understand what broke before you s...
|
84 % |
|
AI Agent Regression Testing for Tool-Using Agents | Konsista
Catch AI agent regressions before release. Repeat mocked tool-use scenarios to expose skipped approvals, wrong targets, missing tools, and duplicate actions.
|
83 % |
|
GrubX | Runtime Action Firewall for AI Agents
GrubX checks every AI agent action, including MCP tool calls, API requests, and SaaS operations, against your policy before it executes. Allow, block, or req...
|
83 % |
|
Arklex.AI | Simulation-Based Agent Evaluation
Generate realistic multi-turn conversations with your AI agents. Evaluate every turn. Ship with evidence, not hope.
|
83 % |
|
Scale Factory | Done-for-you evals for production AI agents
We turn your SOPs, real cases, and production agent responses into tests your agent has to pass, then iterate until it does. When something breaks, you find...
|
83 % |
|
SafeAct — the safety checkpoint for AI actions
SafeAct — the safety checkpoint every AI action passes through before it happens. Checked, held when unsure, exactly-once, provable.
|
83 % |
|
looprun — generate agents proven to follow your rules
looprun turns your rules into guards — deterministic checks in code — and ships every agent measured, with the exam and the evidence that prove it.
|
83 % |
|
Struxum · AI Action Reliability
Struxum is the reliability layer between AI agents and the external systems they change, making consequential actions safe to execute, retry, verify and reco...
|
83 % |
|
Curber: guardrails for AI agents
Curber is a guardrail and approval layer between AI agents and their tools. Join the beta waitlist.
|
83 % |
|
Primary Path: approvals and a provable audit trail for AI agents
Self-hosted approval inbox and tamper-evident audit trail for AI agents that take real actions. Open source, Apache-2.0.
|
82 % |
|
Versalist - Know What Your Agent Does Before You Release It
Versalist helps developers test AI agents, inspect failures, and compare changes before release.
|
82 % |
Detected social media networks