🧠 TIAMAT API Documentation

Persistent Memory & Research APIs for Autonomous AI Agents

🚀 Quick Start (5 Minutes)

1. Store a Memory

curl -X POST https://memory.tiamat.live/api/memory/store \\
  -H "Content-Type: application/json" \\
  -d '{
    "key": "insight_001",
    "value": "Claude Sonnet is faster for reasoning",
    "type": "insight",
    "importance": "high"
  }'

2. Search Memories

curl -X POST https://memory.tiamat.live/api/memory/recall \\
  -H "Content-Type: application/json" \\
  -d '{
    "query": "inference speed comparison",
    "limit": 5
  }'

3. Check Usage

curl https://memory.tiamat.live/api/memory/stats

📖 API Reference

POST /api/memory/store

Store a memory with key, value, type, and importance. Free tier: 100 memories/month. Pro tier: 10,000/month.

POST /api/memory/recall

Full-text search across all memories. Returns relevance scores and metadata. Free tier: 500 searches/month.

GET /api/memory/stats

Check usage quotas and tier status. Returns stored memories count, searches remaining, upgrade options.

GET /health

Service health check. Returns API version, uptime, and database status.

💰 Pricing Tiers

Free

$0
  • 100 memories/month
  • 500 searches/month
  • <200ms response time
  • 90-day retention
  • Community support

⭐ Pro

$9.99

Most Popular

  • 10,000 memories/month
  • 50,000 searches/month
  • <100ms response time
  • Unlimited retention
  • Priority support
  • Batch operations
  • Custom metadata
  • Data export/backup
Upgrade to Pro

Enterprise

Custom
  • Unlimited everything
  • <50ms response time
  • 99.99% SLA
  • Dedicated support
  • Custom integration
  • On-premises option
Contact Sales

💡 Use Cases

Autonomous Agent Learning

Store insights from each cycle so your agent learns what works and doesn't.

{
  "key": "cycle_42_optimization",
  "value": "Switching to Groq reduces latency from 890ms to 500ms",
  "type": "insight",
  "importance": "high",
  "metadata": { "cycle": 42, "latency_improvement_pct": 43.8 }
}

Decision Tracking

Remember strategic decisions and why they were made.

{
  "key": "decision_pricing_strategy_2026",
  "value": "Chose $5/week to target AI developers. A/B test showed 40% conversion at this price point.",
  "type": "decision",
  "importance": "critical"
}

Failure Analysis

Capture failures and their resolutions so you don't repeat mistakes.

{
  "key": "failure_rate_limit_cascade",
  "value": "Anthropic rate limits caused failures. Root cause: no per-provider timeout. Fix: separate timeout + health filtering.",
  "type": "failure",
  "importance": "high"
}

🤝 Support & Community

Having issues or want to contribute?