Aident Loadout logo
NofollowScheduled

Aident Loadout

Give your AI agents real capabilities: 1,000+ apps through one reusable setup.

ABuilt by Aident AI
Scheduled projects can’t be voted on until the launch week is live
aident.ai

AI-friendly Markdown · structured for AI citations

Visit website

Open Aident Loadout on the web — aident.ai

Aident Loadout preview

aident.ai

Visit website

About Aident Loadout

Aident Loadout is a capability layer for AI agents. You connect your apps once, and any supported agent can use them: Codex, Claude Code, Cursor, ChatGPT, Claude Desktop, OpenCode, OpenClaw, Hermes Agent, Antigravity, VS Code-style clients, or any MCP-compatible client.

Agents search 1,000+ apps and their actions by intent, read the live schema, and run the action. They can also start from 400+ expert-built Skills for research, outreach, content and operations. OAuth connections are authorized in the browser. API keys live in Aident Vault, so agents receive results, not raw credentials. Before an action runs, Loadout shows what it will cost. Afterwards, Audit records what ran, where it came from, whether it succeeded and what it cost.

More than 50 built-in services (for example search, scraping and media generation) run on one Aident balance instead of separate subscriptions. Missing app? Request it or connect its API as a custom app. Start free on pay-as-you-go.

Key features:

- 1,000+ apps across development, research, sales, content and operations, including Gmail, Slack, GitHub, Linear, Notion, Google Sheets, HubSpot, Firecrawl, Exa and fal.

400+ expert-built Skills: ready-made workflows agents can use from day one.

Set up once, use in every agent: the same connected apps and Skills work across Codex, Claude Code, Cursor, ChatGPT, Claude Desktop and other MCP clients.

One balance, not fifty subscriptions: 50+ built-in services billed from one Aident balance, with no separate provider accounts or API keys.

Aident Vault: OAuth in the browser; API keys and delegated credentials stay hidden from the model.

Cost preflight and approvals: check an action's cost and risk before it runs.

Audit: see what ran, from which agent, whether it worked, and what it cost.

Custom apps: connect any API that isn't in the catalog yet.

Remote MCP server, CLI and Skill: use whichever surface your agent supports.

How to set it up:

Loadout runs as a hosted remote MCP server at https://loadout.aident.ai/mcp, using streamable HTTP with OAuth sign-in on first use, so there is nothing to install locally. In Claude Code you add it with a single command, in Cursor you add the URL to your MCP configuration, and in Codex you register it with codex mcp add. Any other MCP-compatible client can connect with the same URL. Teams that prefer a terminal can use the Aident CLI, published on npm as @aident-ai/cli, and agents that read skills can install the open-source aident-skill from GitHub (MIT license), which teaches them when and how to use Loadout.

Who it is for:

Developers and teams who want their coding agents and chat assistants to do real work across the tools they already use, without wiring up a separate integration for every app or handing raw credentials to a model. Because every action is recorded in Audit with its source, status and cost, it is easy to see what your agents did and keep spending under control.

Pricing:

Pay-as-you-go is $0 per month, and you pay only for usage from your balance. Pro is $9.90 per month and includes a $5 monthly usage allowance and higher limits. Team is $59 per month and includes a $30 monthly usage allowance and a shared team balance. Actions that use your own OAuth account or API key can cost nothing on Aident's side.

Learn more at https://aident.ai and in the docs at https://docs.aident.ai/loadout/overview.

Ask AI about this project

Get a quick summary or comparison from ChatGPT, Claude, Gemini, Perplexity, or Mistral using this project's public listing.

Comments

Sign in to post a comment

No comments yet

Be the first to comment!