Evalpilot Support
Evaluates after-sales support agents for teams comparing models and reviewing performance.
Listed automaticallyPrice not confirmedDeveloper
Testing agents
AI agents that handle testing work.
111 agents · 25ms
Trace2evolve Autoresearch
A developer tool that iteratively tests and improves customer-support agent behavior.
Listed automaticallyPrice not confirmedDeveloper
Databricks Agentic App Workshop
Hands-on workshop for developers building and evaluating a retail customer support agent on Databricks.
Listed automaticallyPrice not confirmedDeveloper
Prowler
Open-source cloud security and compliance platform for teams and AI agents.
Listed automaticallyOpen sourceDeveloper
Agent Lightning
An open-source framework for developers training and improving AI agents with reinforcement learning.
Listed automaticallyOpen sourceDeveloper
SkillSpector
Scans AI agent skills for security risks before developers install them.
Listed automaticallyPrice not confirmedDeveloper
Nx
A monorepo platform for developers and AI agents that speeds up builds and CI.
Listed automaticallyOpen sourceDeveloper
Signoz
An observability platform for engineering teams monitoring applications and AI agents.
Listed automaticallyOpen sourceDeveloper
Anthropic Cybersecurity Skills
A cybersecurity skills library for developers building AI agents and security workflows.
Listed automaticallyOpen sourceDeveloper
Pentagi
Autonomous penetration-testing agents for security professionals and teams.
Listed automaticallyOpen sourceDeveloper
IFixAi
Audits AI agents for reliability and alignment, for teams and agents seeking fast independent evaluations.
Listed automaticallyPrice not confirmedDeveloper
Goose
An extensible coding agent for developers to run, modify, and test code with their chosen LLM.
Listed automaticallyOpen sourceDeveloper
Autoresearch
Automates overnight LLM training experiments for AI researchers and developers.
Listed automaticallyPrice not confirmedDeveloper
Ponytail
A developer skill that helps AI coding agents produce simpler code and test risky logic.
Listed automaticallyOpen sourceDeveloper
seal
Provides signed, independently verifiable AI decision receipts for teams operating AI systems.
Listed automaticallyPrice not confirmedDeveloper
TapeAgents
A developer framework for building, debugging, serving, and optimizing LLM agents.
Listed automaticallyPrice not confirmedDeveloper
ARC (arcreport.ai): can an agent reach checkout?
Checks whether AI agents can reach checkout on a store without making a payment.
Listed automaticallyFreeDeveloper
Palico AI
A developer toolkit for building, evaluating, and deploying LLM applications.
Listed automaticallyPrice not confirmedDeveloper
Sotopia
A developer platform for evaluating social intelligence in language agents through interactive scenarios.
Listed automaticallyOpen sourceDeveloper
APIANT
Builds, tests, and monitors app integrations for businesses connecting their systems.
Listed automaticallyFreemiumDeveloper