Skip to main content
Glama
README.md
# AgentDevX SDK

**Give your AI hands.**

The identity and security infrastructure every AI agent needs. Not a tool collection — a gateway. Register any API via OpenAPI spec, and every agent gets cryptographic identity, encrypted credential storage, automatic credential injection, and a full audit trail.

[![npm](https://img.shields.io/npm/v/@agentdevx/install)](https://www.npmjs.com/package/@agentdevx/install)
[![License: MIT](https://img.shields.io/badge/License-MIT-purple.svg)](LICENSE)
[![Smithery](https://img.shields.io/badge/Smithery-99%2F100-purple)](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx)

## What AgentDevX Is

Every developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.

| Problem | AgentDevX Solution |
|---------|-------------------|
| Auth spaghetti | One Ed25519 cryptographic identity per agent |
| Credential sprawl | AES-256-GCM encrypted vault, scoped per agent |
| Integration hell | Register any API via OpenAPI spec, call via proxy |
| No agent identity | Stable cryptographic identity across all tools |
| No memory | Encrypted per-agent memory, persists across sessions |

## Why It's Different

The only gateway an AI agent can discover, install, and use **entirely on its own** — no human OAuth, no manual key exchange, no dashboard.

| Feature | AgentDevX | Composio/Nango | Auth0 |
|---------|-----------|----------------|-------|
| AI self-bootstrap | ✅ | ❌ | ❌ |
| Ed25519 identity | ✅ | ❌ | ❌ |
| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |
| Per-agent memory | ✅ | ❌ | ❌ |
| MCP native | ✅ | ❌ | ❌ |
| Indie pricing | ✅ Free tier | ❌ | ❌ |

## Quick Start

```bash
npx @agentdevx/install
```

## Bootstrap Your Agent

One call. No human needed.

```bash
PUBLIC_KEY=$(openssl rand -hex 32)

curl -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \
  -H "Content-Type: application/json" \
  -d "{\"name\":\"my-agent\",\"email\":\"you@example.com\",\"public_key\":\"$PUBLIC_KEY\"}"
```

Returns: JWT + 75,000 free credits + instant access to all registered tools.

## Connect via MCP

```json
{
  "mcpServers": {
    "agentdevx": {
      "url": "https://agentdevx.onrender.com/mcp"
    }
  }
}
```

Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.

## What Your Agent Gets

- 🔐 **Ed25519 identity** — cryptographic, not OAuth tokens
- 🔒 **AES-256-GCM vault** — store any API key, auto-injected on every call
- 🛡️ **OPA policy engine** — access control, dry-run mode, capability tags
- 📋 **Immutable audit log** — every tool call recorded
- 🧠 **Persistent memory** — encrypted per-agent state across sessions
- ⚡ **42+ pre-registered tools** — plus register your own via OpenAPI spec
- 🌐 **MCP-native** — auto-discovery, protocol 2025-03-26

## API Reference

| Endpoint | Method | Description |
|----------|--------|-------------|
| `/agents/v1/bootstrap` | POST | Create agent + get JWT + 75k credits |
| `/agents/me` | GET | Agent profile + credit balance |
| `/agents/me/memory` | POST/GET | Read/write encrypted memory |
| `/proxy/call` | POST | Execute any registered tool |
| `/credentials` | POST | Store encrypted API key |
| `/billing/checkout` | POST | Create payment checkout |
| `/mcp` | POST | MCP JSON-RPC endpoint |

## Pricing

| Plan | Price | Calls/day |
|------|-------|-----------|
| Free | $0 | 100/day + 75k credits |
| Starter | $8/mo | 500/day |
| Pro | $12/mo | 5,000/day |
| Scale | $29/mo | Unlimited |

## Links

- 🌐 Gateway: https://agentdevx.onrender.com
- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx
- 🦞 ClawHub: https://clawhub.ai/mirajmahmudul/agentdevx-skill
- 📦 npm: https://www.npmjs.com/package/@agentdevx/install

## License

MIT © mirajmahmudul

TDQS

C2.9/5.0

Scored across 38 tools

Disambiguation4/5

The namespace prefixes and resource-specific names make most tools easy to distinguish, and different API namespaces are separated. A couple of tools could still be confused, notably petstore-api.getInventory vs petstore-api.findPetsByStatus and webscrape.scrape vs webscrape.extractDesign.

Naming Consistency3/5

Most tools follow a namespace.verbResource camelCase pattern, but there are notable deviations such as acme-mailer.send_email, memory.stre, and echo-server.add. The overall style remains readable, but the mixing of snake_case, camelCase, and verb-only names prevents a strong consistency score.

Tool Count2/5

With 38 tools across ten unrelated API namespaces, the server is oversized and unfocused. The PetStore block alone carries 19 tools, and many of these clusters would be better split into separate purpose-specific servers.

Completeness2/5

Several included API surfaces are only partially covered: JSONPlaceholder has create/get but no update/delete, GitHub is read-only, exchange-rate only exposes latest rates, and memory has store/recall but no delete or list. These gaps make the set feel incomplete for an agent relying on those services.

Maintenance

ActivityMaintained
ResponsivenessNo issues