Agent

Otōto is an MCP server for Claude Code and OpenCode: a small model on a server you choose explores the code and hands your agent short answers with...

AgentiLoop Agent! is a 100% native macOS agentic AI. One app, 23 LLM providers, total command over your Mac. Build apps, automate workflows, control...

Give your AI agent fleet a shared artifact storage. AgentDrive is a cloud filesystem where agents and people share files across work sessions. Create...

magpie

AI agent orchestration for Mac. Run Claude Code, Codex and Cursor on one canvas with shared context, focused handoffs and voice control. Try free for 3...

gawkbot puts every coding agent on your Mac, and the ones in the cloud, in the notch. Approve, answer and talk back with one key or your voice, or...

Provision VMs on any cloud or computer, load them with your favorite agent(s), and then remote control the agents from any chat surface, app, or API.

Give your coding agents names. Let Claude Code, Codex, Grok Build, OpenCode, and Pi talk to each other with Agent Exchange.

40 pre-built synthetic environments for Salesforce, Jira, Stripe, and more. We generate the dataset, 200 adversarial queries, and the correct answer...

Botscent tells your site if an AI agent, not a person, is browsing it, and which one. 5 KB, MIT, 0 deps.

Your agent broke Supabase. You probably didn't notice. Sodabase detects broken Supabase tables, finds the cause, and fixes the issue automatically.

A design system for AI coding agents. Square corners, 1px borders, a mostly gray palette, and a linter that fails the build when the agent breaks a rule.

A local AI agent test environment. Draft tests with AI, review the rules, run your agent in a world and inspect what changed. Stripe and Zendesk public...

Stop trusting your AI agent with your machine. Give it a sandbox it can

Ember is an AI sales agent for the relationships in your inbox and CRM. It drafts each follow-up in your voice and sends from your inbox when you approve.

Stop juggling coding-agent sessions. Delegate work to multiple agents, keep your focus, and review completed commits when it suits you.

Rhyven is a marketplace and runtime for headless, agent-first apps. Install apps, connect your agent through MCP or REST, and store app data in your...

Point at your UI. Tell your coding agent what to change. Click elements in Chrome, collect the edits, and copy one prompt for Claude Code, Cursor, or...

Connect your agent to web search, scraping, and enrichment APIs through one account. Use the unified API, MCP server, or CLI, and pay for the calls you...

Review AI-written code as fast as agents write it. Review Assist is a free, open-source MCP server that turns a coding agent

AI context engineering and agentic commerce for LLMs & AI applications — RAG Chunk Inspector, Memory Architecture Visualizer, Agent Trace Inspector,...

ZCode 将 GLM-5.3 与领先的 AI 编程 Agent 和你的现有工具链结合，帮助你顺畅完成规划、编码、评审与上线。

Tin is an open-source marketing system your coding agent can run: hundreds of workflow templates, schedules, evaluations and live data, Apache 2.0. Add...

An AI agent writes each strategy in a small typed language, a validator checks every draft, and the version that passes is compiled into a fixed...

Code review for your own machines and your own agents. GitWarren reads the worktree directly — staged, unstaged and untracked — so you read an agent

Put your agent to work on shared expenses. Install the BananaSplit CLI, connect your account, and track expenses, manage groups, and review balances...

The CAFE(S) framework judges agent context on clarity, actionability, fidelity, efficiency, and security, but its fixes all assume context lives in...

Where agents choose and review software. After real tasks, coding agents like Claude Code, Codex, Cursor and Antigravity review the tools they used: a...

We call your voice agent, you get a pass/fail in your pipeline. The testing infrastructure for AI voice agents.

BotGauge helps teams red-team, evaluate, monitor, and govern AI agents from development to production - with testing, guardrails, and continuous...

Bridle is an open protocol that connects your coding agent to your teammate's. Push context, hand off tasks, request runs — both ends opt in, every...

Let two AI agents talk directly. Make a link, give it to both, and they connect peer to peer.