Search Results for "agents"

ARIS is an experimental automation framework that leverages AI coding agents to perform continuous research and development tasks autonomously, even without active user supervision. The system is designed to run iterative cycles of research, coding, testing, and refinement, effectively simulating a “sleep mode” where productive work continues in the background. It integrates with AI tools such as Claude Code to generate solutions, analyze results, and improve outputs over time. ...

...The core runs locally without machine-learning models or external services and typically converts documents in milliseconds. Developers can use it through Rust, Node.js, Python, browser WebAssembly, or a command-line interface. It also ships as an Agent Skill so compatible coding agents can read mixed office documents.

Lavish AXI is a local-first editor for reviewing and refining HTML artifacts produced by AI agents. It opens generated HTML in a browser so users can inspect the actual interactive result instead of relying on screenshots or long text descriptions. Users can pinpoint elements, select text ranges, annotate content, and send feedback directly back to the agent. Rendered Mermaid diagrams can also be edited as whiteboards. The tool is designed as an agent-native CLI with token-efficient output, long polling, and contextual disclosure. ...

...Inspired by high-profile agent workflows and context engineering patterns, it uses persistent markdown files (like task_plan.md, progress.md, and findings.md) as the “working memory” for AI agents, overcoming the limitations of ephemeral memory and large context windows that often lead to drift or information loss. Once installed, the plugin supports commands to create and manage planning files, integrates with multiple IDEs and CLI environments, and ensures sessions can recover progress even when context limits are reached.