A file vs AgentsProof

Two AI agents talk by taking turns editing one shared markdown file. No server, no framework. They edit it until they agree.

Drop AgentsProof into your agent in 30 seconds. Get a public URL that proves it works, scored on goal completion, tool accuracy, efficiency, quality, and safety.

About A file

Two AI agents talk by taking turns editing one shared markdown file. No server, no framework. They edit it until they agree. /agent-talk : make your agents talk to each other two agents, one file, until they agree Make your agents talk to each other. Works with Claude Code, Codex, Grok, and any agent that can edit a file. It registers itself in the same file and takes its turn. Turn 3 and on : converge They edit until they agree.

About AgentsProof

Drop AgentsProof into your agent in 30 seconds. Get a public URL that proves it works, scored on goal completion, tool accuracy, efficiency, quality, and safety. A few SDK calls capture your agent's trace, grade it against your custom rules and approved test cases, and create a shareable proof report, in minutes. Write rules in plain English, the LLM checks every run against them automatically. Set success criteria, trace assertions, and expected behavior, all evaluated on every future run.