Foundry AI Agent by promptise-com

<div align="center"> <a href="https://www.promptise.com"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/hero-dark.svg"> <img alt="Promptise Foundry: the foundation layer for agentic intelligence" src="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/hero-light.svg" width="100%"> </picture> </a> <br/>

<a href="https://pypi.org/project/promptise/"><img alt="PyPI" src="https://img.shields.io/pypi/v/promptise?style=flat-square&color=1a1a1a&label=pypi"></a> <a href="https://pypi.org/project/promptise/"><img alt="Python 3.10 to 3.13" src="https://img.shields.io/badge/python-3.10%20%E2%80%93%203.13-1a1a1a?style=flat-square"></a> <a href="https://github.com/promptise-com/foundry/actions/workflows/test.yml"><img alt="Tests" src="https://github.com/promptise-com/foundry/actions/workflows/test.yml/badge.svg"></a> <a href="https://github.com/promptise-com/foundry/blob/main/LICENSE"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/license-Apache%202.0-1a1a1a?style=flat-square"></a> <a href="https://docs.promptise.com"><img alt="Docs" src="https://img.shields.io/badge/docs-docs.promptise.com-1a1a1a?style=flat-square"></a> <a href="https://github.com/promptise-com/foundry/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/promptise-com/foundry?style=flat-square&color=1a1a1a&label=stars"></a>

Website  ·  Docs  ·  Quick start  ·  How it works  ·  Examples  ·  Discussions

</div> <br/>

What Promptise is

The framework for agentic intelligence.

Promptise gives you everything an agentic system needs, in one place and working together from the first line: agents that think, safe ways for them to act in your systems, and a harness that keeps them running and accountable. You decide what your agent should do; Promptise takes care of everything around it.

Start with one agent on your laptop and grow it into a fleet running real work, with the same framework and the same way of building all the way through. No rewrite in between, and nothing to stitch together yourself.

<br/> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/stack-dark.svg"> <img alt="The three parts of every agentic system: Agent, Interface and Harness" src="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/stack-light.svg" width="100%"> </picture> <br/>

Layer	What it does for you
Agent · it thinks	Agents that work through a task step by step, check their own work and get it right.
Interface · it acts	Safe access to your tools, your data and the systems you already run.
Harness · it operates	Keeps your agents running around the clock, within budget, and accountable for everything they do.

<br/>

Get started in 30 seconds

pip install promptise
export OPENAI_API_KEY=sk-...

import asyncio
from promptise import build_agent, tool


@tool
def order_status(order_id: str) -> dict:
    """Look up the status of an order."""
    return {"order_id": order_id, "status": "shipped", "eta": "Friday"}


async def main():
    agent = await build_agent(
        model="openai:gpt-5-mini",
        instructions="You are a helpful support assistant.",
        extra_tools=[order_status],
        observe=True,  # traces every step, token and cost
    )
    result = await agent.ainvoke(
        {"messages": [{"role": "user", "content": "Where is order A-1001?"}]}
    )
    print(result["messages"][-1].content)
    await agent.shutdown()


asyncio.run(main())

Any Python function with @tool becomes a tool; its type hints are the schema. To give the agent the tools of an MCP server, add it to servers; the agent discovers its tools by itself:

from promptise.config import HTTPServerSpec

agent = await build_agent(
    model="openai:gpt-5-mini",
    servers={"tools": HTTPServerSpec(url="http://localhost:8000/mcp")},
)

To start a full project instead, run promptise init --project my-bot.

Any model, one string. openai:gpt-5-mini · anthropic:claude-sonnet-5-5 · azure:chat-prod · gemini:gemini-3.8-flash · bedrock:… · ollama:llama3.1. The same string works in build_agent(), .superagent files and every CLI command, and promptise models check <string> tells you exactly what a provider still needs. → Model setup

<br/>

Run your project

promptise.toml is to an agent project what package.json is to a Node project: it names the main file, the scripts and the environment the project needs. promptise run runs your program like python main.py; with dev tools, the terminal UI or the HTTP API it also instruments every agent the program builds, with no code changes.

promptise init --project my-bot   # promptise.toml, agent.py, main.py, .env.example
promptise run                     # run main.py with the project's environment
promptise run --devtools          # live traces, tool calls, tokens and cost
promptise run --tui               # the full terminal UI
promptise run --serve             # an HTTP API for your agent
promptise run --prod              # JSON logs, preflight checks, graceful SIGTERM

[scripts] work like npm scripts (promptise run dev), and --watch restarts on every save. → Projects & promptise run

<img alt="promptise run --tui: the chat with an agent, its tool calls inline, and live tokens and cost in the header" src="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/run/tui-chat-approved.svg" width="100%"> <br/>

One request, through the whole system

A customer writes in at three in the morning. The runtime wakes the agent, its identity is established, the input is checked, it gathers context, plans, calls a tool through MCP, a person approves the refund, it checks its own work, answers, and every step lands in the audit trail.

<br/> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/flow-dark.svg"> <img alt="One customer request handled across the Interface, Agent and Harness layers" src="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/flow-light.svg" width="100%"> </picture> <br/> <p align="center"><a href="https://www.promptise.com/how-it-works"><b>Walk through all fourteen steps, with every module linked →</b></a></p> <br/>

Already have an API? MCPcast it.

promptise mcpcast openapi.yaml --profile standard --auth env-token

MCPcast reads an OpenAPI or Swagger document and writes a real, reviewed MCP server: a small set of tools an agent can actually use, chosen and described for agents. Reads by default; writes only when you ask, and every one of them approval-gated on the server, so a person signs off before anything changes, whichever MCP client calls it.

<br/> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/mcpcast-dark.svg"> <img alt="MCPcast turns an OpenAPI spec into a reviewed MCP server" src="https://raw.githubusercontent.com/promptise-com/foundry/main/docs/assets/readme/mcpcast-light.svg" width="100%"> </picture> <br/>

What comes out is a project, not a script: an installable package, a launcher, a generated test suite, pyproject.toml, a Dockerfile and a README, all regenerated from mcpcast.plan.yaml, the one file you edit. --eval grades the result A to F with a real agent before you ship, and plain promptise mcpcast opens a guided setup in the terminal. Above: the real output for the Swagger Petstore spec. → MCPcast, end to end

<br/>

Built for governance and structure

For people and teams who need their agentic systems to be accountable: who did what, on whose behalf, within which limits. These are part of the framework, not something you add later.

• Multi-tenant, by construction. Tag a request with a tenant, and every place data lives — memory, cache, conversations, rate limits, audit — stays separated per tenant. Two tenants who both have a user named alice can never see each other's data. It's a structural rule, not a filter you have to remember on every query. → Multi-Tenant Platform guide

• Human approval, enforced on the server. Mark a tool as needing sign-off and the approval is required no matter which app calls it — including one you didn't write. Denies on timeout, rejects self-approval, records who approved what. → Approval Gates

• A real identity for each agent. Agents authenticate as themselves to the APIs they call, backed by Microsoft Entra ID, AWS, Google Cloud, SPIFFE, or plain OIDC — so you can retire the shared API key, and every action traces to the person it acted for, even across agents calling agents. → Agent Identity

• Audit you can hand to a reviewer. Every action is written to a tamper-evident chain, tied to the tenant and the user. Delete one user's cached answers, memories and recorded events with purge_user() when they ask. → Auth & Security

• Runs offline. The security models, embeddings, and vector store can all run locally — so the whole stack works air-gapped, for on-premises and regulated environments where data can't leave. → Guardrails · Model Setup

<br/>

Everything Promptise ships

<table> <tr><td colspan="2">_{<b>AGENT</b> &nbsp;·&nbsp; it thinks}</td></tr> <tr> <td valign="top" width="24%">

The Promptise Agent

One function turns any model into a production agent.

Explore →

</td> <td valign="top">

Setup   Build · Server config · Network server · SuperAgent files · Custom patterns · Cross-agent

Memory & state   Memory · RAG · Conversations · Semantic cache · Context engine

Security   Guardrails · Approval · Auto-approval · Sandbox

Performance   Tool optimization · Fallback · Adaptive strategy

Execution   Streaming · Events · Observability

Reference   Config · Types · Default prompt · Callbacks · Tools · Env resolver · Exceptions · CLI

</td> </tr> <tr> <td valign="top">

Reasoning Engine

Reasoning as a graph you can read and change.

Explore →

</td> <td valign="top">

Graph   Overview · Nodes · Edges · Flags · Internals

Patterns & skills   Prebuilt patterns · Skills · Skill registry · Custom reasoning

Runtime   Tool injection · Processors · Hooks · Serialization

</td> </tr> <tr> <td valign="top">

Prompt Engineering

Prompts built like software, versioned and tested.

Explore →

</td> <td valign="top">

Build   PromptBlocks · ConversationFlow · Builder · Loader & templates · Shell injection

Strategies   Strategies · Chaining · Context & variables

Quality   Guards · Inspector · Testing · Suite & registry

</td> </tr> <tr><td colspan="2">_{<b>INTERFACE</b> &nbsp;·&nbsp; it acts}</td></tr> <tr> <td valign="top">

MCP Server, Client & MCPcast

Build a tool once; every agent can use it.

Explore →

</td> <td valign="top">

Server   Guide · MCPcast an existing API · Fundamentals · Routers & middleware · Auth & security · Multi-tenancy · Approval gates · Production · Caching · Observability · Resilience · Queue · Advanced · Deployment · Testing

Client   Guide · Tool adapter

</td> </tr> <tr><td colspan="2">_{<b>HARNESS</b> &nbsp;·&nbsp; it operates}</td></tr> <tr> <td valign="top">

Agent Runtime

Run agents unattended, on budget, recoverable.

Explore →

</td> <td valign="top">

Core   Processes · Orchestration API · Manager · Context & state · Lifecycle · Hooks · Conversation

Governance   Mission · Budget · Health · Secrets

Triggers   Overview · Cron · Event & webhook · File watch

Journal & recovery   Overview · Backends · Replay · Rewind

Config & scale   Options · Manifests · Meta-tools · Coordinator · Discovery · Dashboard · CLI

</td> </tr> <tr> <td valign="top">

Agent Identity

An authenticated identity for every agent.

Explore →

</td> <td valign="top">

Core   Overview · Quickstart · Guide · Architecture · Security · Migration

Providers   Microsoft Entra ID · AWS IAM · Google Cloud · SPIFFE / SPIRE · Generic OIDC

</td> </tr> <tr><td colspan="2">_{<b>ALSO IN THE DOCS</b>}</td></tr> <tr> <td valign="top"><b>Guides &amp; labs</b></td> <td valign="top">

Building agents · Context lifecycle · Code-action · Production MCP servers · Agentic runtime · Prompt engineering · Multi-user systems · Agent-to-MCP identity · Secure multi-tenant platform · Multi-agent coordination  •  Labs: Customer support · Data analysis · Code review · Pipeline observer

</td> </tr> <tr> <td valign="top"><b>API reference</b></td> <td valign="top">

Agent · Config · Memory · RAG · Sandbox · Observability · Identity · MCP server · MCP client · Prompts · Runtime · Cross-agent · SuperAgent · Utilities

</td> </tr> <tr> <td valign="top"><b>Start here</b></td> <td valign="top">

Installation · Extras · Quick start · Cookbook · Why Promptise · What is MCP? · Model setup · Best LLMs · Key concepts · Glossary  •  More: Blog · Showcase · Examples · Migration · Changelog · FAQ · Contributing

</td> </tr> </table> <br/>

Works with what you already run

Area	Works with
Models	OpenAI · Anthropic · Azure OpenAI & AI Foundry · Gemini & Vertex AI · Bedrock · Mistral · Groq · Ollama · Hugging Face · any LangChain chat model · FallbackChain for failover → Model setup
Memory & vectors	ChromaDB · Mem0 · Sentence Transformers · local embeddings for air-gapped installs → Memory
Conversations	PostgreSQL · Redis · SQLite · in-memory, with session ownership enforced → Conversations
Identity & auth	Microsoft Entra ID · AWS IAM · Google Cloud · SPIFFE / SPIRE · OIDC · JWT · OAuth 2.0 → Agent Identity
Observability	OpenTelemetry · Prometheus · Slack · PagerDuty · webhook · HTML · JSON · console → Observability
Sandbox & deploy	Docker · gVisor · seccomp · capability dropping · Kubernetes health probes → Sandbox
Protocols	Model Context Protocol over stdio, streamable HTTP and SSE · OpenAPI · HMAC-chained audit logs

<br/>

---

<div align="center">

Contributing  ·  Security  ·  Changelog  ·  License: Apache 2.0

_{Built by <a href="https://www.promptise.com"><b>Promptise</b></a> · questions and ideas in <a href="https://github.com/promptise-com/foundry/discussions">Discussions</a> · bugs in <a href="https://github.com/promptise-com/foundry/issues/new/choose">Issues</a>}

_{^{Formerly <a href="https://github.com/cryxnet/DeepMCPAgent">DeepMCPAgent</a>, a public preview of one part of this framework (MCP-native agent tooling).}}

</div>