SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

3,047 results · Page 76 of 85

Runable

AI agents

Runable is an AI general agent that can think, plan, and execute on a single platform. It can turn ideas into a business, automatically handle daily tasks, and support growth. Its main capabilities include: generating multi-page polished presentations in minutes; creating a working application from a single instruction without code; publishing a formal business website; handling file consultation, research with sources, and content creation within a conversation; producing marketing videos ready to publish directly to multiple platforms; generating and editing images and videos on an infinite canvas; teaching the agent custom skills to fit the way you work; integrating with more than 3,000 commonly used apps and tools; and designing engaging social media carousel posts. It can also read websites, products, past marketing data, and performance metrics, autonomously plan and execute marketing campaigns, generate pages, ads, and emails, and allocate budget based on performance.

Read more

sabot

AI agents

Sabot is an open-source benchmark project for evaluating the effectiveness of self-check mechanisms in multi-agent pipelines. It injects controlled faults into reference pipelines built with frameworks such as LangGraph, CrewAI, and AutoGen/Magentic-One, measuring whether the pipelines' own reviewer and guardrail stages can detect, respond to, or miss these faults. Test results show a median detection rate of 16.7%, and by modifying the reviewer prompt to require it to report all inconsistencies, the detection rate can be increased to 55.0%. The project provides frozen measurement specifications, runnable test frameworks, and public raw run traces, and is licensed under Apache-2.0.

Read more