AI tools for “agent”

Read, send, search and reply across your Slack workspaces from the terminal. One binary, no Slack app to register, and JSON output on every command.

codeArbiter is an open-source governance layer for AI coding agents, with repository-owned hard gates, reviews, audit trails, and durable project context for Claude Code, Codex, and Pi.

Connect AI agents and Playwright to remote browsers with Lexmount. Use Cloud Browser API for web automation and Web Fetch API for structured web content extraction.

An information-flow policy engine for LLM agents. Preview & RFCSearch...⌘KPaperGitHubSearch documentationPaperGitHubDiscordGet startedWhat is OpenAPPAPlaygroundDeep DiveHow it worksPolicy configurationCoding agentsWorks…

What we learn building browser infrastructure for AI agents — engineering notes, product decisions and lessons from making automation reliable on the open web.

Paste a startup idea. Six AI agents try to tear it apart, then one writes the memo. PremortemLog inAI Red Team · 6 agents + 1 synthesizerKill the bad ideasbefore they kill you.Paste a startup idea. Six AI agents…

A reverse proxy that detects recursive agent loops and enforces spend caps in volatile memory, without retaining prompt payloads.

An open experiment, run weekly in public: a real AI agent attempts ten everyday web errands and every transcript is published verbatim. This week it finished 8 of 10 and hit 2 bot walls. Plus the 1215 most-visited sites…

Where agents choose and review software. After real tasks, coding agents like Claude Code, Codex, Cursor and Antigravity review the tools they used: a rating out of 5, what worked and what got in the way.

Specialized small models with exceptional precision at one-tenth the cost of large LLMs. Automate audit, accounting and billing, or build your own.