Promptise Foundry¶
The production framework for agentic AI systems. Build agents that discover tools, reason with custom patterns, remember context, enforce security, and run autonomously.
Quick Start¶
import asyncio
from promptise import build_agent
async def main():
agent = await build_agent(
model="openai:gpt-4o-mini",
instructions="You are a helpful assistant.",
)
result = await agent.ainvoke(
{"messages": [{"role": "user", "content": "Hello!"}]}
)
print(result["messages"][-1].content)
await agent.shutdown()
asyncio.run(main())
See the full Quick Start for tools, reasoning patterns, and production features.
Five Subsystems¶
| Subsystem | What it does | Start here |
|---|---|---|
| Agent | Turn any LLM into a production agent. MCP tool discovery, memory, guardrails, semantic cache, streaming, approval workflows. | Building Agents |
| Reasoning Engine | Design how your agent thinks. 20 composable nodes, 7 prebuilt patterns, 16 typed flags, 0.02ms overhead. Custom reasoning patterns for any task. | Custom Reasoning |
| MCP Server | Build tool APIs that agents call. JWT auth, guards, middleware, rate limiting, audit logs, TestClient. The FastAPI of MCP. | Building Servers |
| Agent Runtime | Run agents autonomously. Cron triggers, crash recovery, budget enforcement, health monitoring, mission tracking, distributed coordination. | Runtime Systems |
| Prompting | Prompts as software. Typed blocks with token budgeting, conversation flows, composable strategies, guards, version control, testing. | Prompt Engineering |
Hands-On Labs¶
Complete, runnable tutorials for real-world use cases:
- Lab: Customer Support Agent — KB search, conversation phases, escalation, guardrails
- Lab: Data Analysis Agent — SQL queries, cross-table analysis, specialized reasoning pattern
- Lab: Code Review Agent — Adversarial critique, per-node models, security scanning
Install¶
Python 3.10+ required.
Set your LLM provider key:
Verify:
Next Steps¶
- Quick Start — Build your first agent in 5 minutes
- Model Setup — Configure OpenAI, Anthropic, Ollama, or any provider
- Key Concepts — Architecture and design principles
- Reasoning Engine — The custom execution runtime that powers every agent