PromptisePromptise
PlatformSoonEnterprise
DocsGitHub
Talk to usGet started
[framework]> agent · interface · harness
Live · open source

Everything you need to build agentic systems.

The agent, the MCP servers it works with and the runtime that runs it. One open-source framework, made to work together from the first line.

Get startedRead the docsGitHub
01 AgentSmart and reliable02 InterfaceAny system, agent-ready03 HarnessAutonomous, under control
  1. 01Why one
  2. 02Three parts
  3. 03Modules
  4. 04Capabilities
  5. 05Walkthrough
  6. 06Install
[n.01/07]> why one framework

Built together, not stitched together.

Most teams stitch an agent, its tools and a runtime together from separate libraries. Promptise ships all three in one install.

Separate libraries
modeltools · mcpmemoryguardrailsruntimetracingglue code at every joint

Glue code at every joint.

Each library has its own interfaces. Your team writes the code between them and keeps it working.

With Promptise
modeltools · mcpmemoryguardrailsruntimetracingone install · one set of interfaces

One install. One set of interfaces.

The agent, the interface and the harness are made to work together from the first line.

[n.02/07]> the three parts

Three parts, and what's inside each.

The agent does the work. The interface connects it to your systems. The harness runs it.

ThinkActOperateOne install
[01] The agent · It thinks
planthinkactreflectvalidatecritiqueanswerpath the agent choseallowed, not needed this time

Smart and reliable.

Our reasoning and execution engines turn any model into an agent that thinks before it acts. It works out the right approach for each task and checks its own result. You set the limits. It finds the way.

Inside
The Promptise AgentReasoning EngineExecution EnginePrompt & Context
Explore the agent
[02] The interface · It acts
openapi spec300 endpointsreviewtoolstested · deletes behind approval

Any system, agent-ready through MCP.

Build MCP servers for your own systems and connect to any that exist. Turn the API you already have into one an agent can use.

Inside
MCP Server SDKMCP ClientMCPcast
Explore the interface
[03] The harness · It operates
irreversible actions this runrefund 1refund 2refund 3refund 4limit 3 of 3pause + page on-callalso watched, without model callssame call repeatedno progresserror rate

Autonomous and under control.

Our agent runtime starts agents on a schedule or an event and keeps them working around the clock. They stay inside the limits you set, and you can see everything they did.

Inside
Agent RuntimeGovernanceAgent IdentityObservability
Explore the harness
ThinkActOperateOne install
[n.03/07]> the modules

Every module, and what it does.

Twelve modules in three parts. Start with the one you need and add the others later. Pick a part, then a module.

The agent page
The agent · It thinks

The Promptise Agent

One function returns a production agent. Any model, tools discovered from your MCP servers, memory searched before every turn, and guardrails, caching and tracing switched on by a flag.

3
memory providers
4
conversation stores
4
tool-selection levels
What you get
  • Any model: a provider string or any LangChain chat model
  • MCP tool discovery, with semantic tool selection
  • Memory in Chroma, Mem0 or in-memory
  • Conversations persisted to SQLite, Postgres or Redis
  • Per-request caller identity through cache, guardrails and tracing
agent.pypython
from promptise import build_agentfrom promptise.config import HTTPServerSpecfrom promptise.memory import ChromaProvider agent = await build_agent(    model="openai:gpt-5-mini",    servers={"crm": HTTPServerSpec(url="http://localhost:8000/mcp")},    memory=ChromaProvider(),    guardrails=True,    observe=True,)
Explore The Promptise Agent1 of 4 in the agent
[n.04/07]> production capabilities

Production-ready from the first line.

Eight capabilities come built in. You switch them on when you need them. Nothing has to be added later.

your agent
12345678

Governance & controls

Budgets · Approval gates · Health checks · Missions

Autonomy

Triggers · Journals · Crash recovery

Safety

Injection · PII · Credentials · Content safety

Identity & audit

Attribution · Verifiable credentials · Audit log

Tools & integration

MCP client · MCP servers · OpenAPI import

Observability

Tracing · Metrics · Eight destinations

Context

Memory · Conversation stores · Token budgets · Semantic cache

Reasoning

Reasoning graph · Strategies · Per-node models

  1. 1Governance & controlsBudgets · Approval gates · Health checks · Missions
  2. 2AutonomyTriggers · Journals · Crash recovery
  3. 3SafetyInjection · PII · Credentials · Content safety
  4. 4Identity & auditAttribution · Verifiable credentials · Audit log
  5. 5Tools & integrationMCP client · MCP servers · OpenAPI import
  6. 6ObservabilityTracing · Metrics · Eight destinations
  7. 7ContextMemory · Conversation stores · Token budgets · Semantic cache
  8. 8ReasoningReasoning graph · Strategies · Per-node models
What each capability does+
Context
Answers grounded in what the agent knows, without overflowing the context window or the budget.
Reasoning
Reasoning designed for the job, so results are predictable instead of left to one generic loop.
Tools & integration
Connect to any system through the open MCP standard, and publish your own APIs the same way.
Safety
Prompt injection, personal data and leaked credentials are caught before the model sees them, and again on the way out.
Governance & controls
Spending limits and approvals enforced in code, not in the prompt, with a person signing off where it counts.
Autonomy
Agents run on their own schedule and pick up where they left off when something breaks.
Identity & audit
Know which agent acted, and prove it to someone who was not there.
Observability
Every model call, tool call and retry traced, and sent to the tools your team already uses.
[n.05/07]> in action

Watch one request run through the system.

A customer writes in at three in the morning. Follow the ticket step by step: what wakes the agent, what it knows, how it reasons, what it calls, who signs off and what it records.

Open the full walkthrough
InterfaceIt actsAgentIt thinksHarnessIt operates01 · A ticket wakes the agent01Agent Runtime02 · It knows who it is0203 · The input is checked0304 · It gathers what it knows0405 · No shortcut this time0506 · It makes a plan0607 · It reaches for a tool0708 · The server checks the caller0809 · It double-checks the numbers0910 · A tool generated from a spec1011 · A person signs off1112 · It checks its own work1213 · The answer goes out1314 · Everything is on the record14

Step 01 / 14 · 03:02:11 · Agent Runtime

A ticket wakes the agent

A helpdesk webhook fires. The runtime wakes the support agent's process and hands it the ticket.

An illustrative run. Names and timings are examples; what each step describes is what the framework does. See every module in the full walkthrough →

[n.06/07]> install

Install it. Run your first agent.

Python 3.10 or newer. No scaffolding and no project generator: it works inside the code you already have.

Read the quickstart
01 · terminal
$ pip install promptise # or, with vector memory, ML guardrails and exporters$ pip install "promptise[all]"

promptise · verb

Let's promptise it. Whatever it is.

Like digitising something, promptising it changes how the work gets done. An agent thinks it through, works in your real systems, runs on its own and stays inside your rules, and you can see every step it took. Anything can be promptised.

What promptised means

Promptised means it

  • It thinksreasoning you design
  • It knowsmemory and your documents
  • It actstools, APIs and MCP
  • It works with othersagents that delegate
  • It runs on its owntriggers and recovery
  • It stays safeguardrails, approvals, budgets
  • It shows its worktraces and a journal
  • It shipsone command to production
[n.07/07]> beyond the framework

Built it? Two ways to go further.

The framework is yours to run. When you want more, there are two ways to get it.

[01] PlatformComing soon

Deploy with one push.

The platform will deploy, run and monitor what you build, in our cloud or on your own servers.

See the platformJoin early access
[02] EngineersAvailable now

Want it built with you? Hire our engineers.

The people who build Promptise work with your team, from the first prototype to production.

How we workBook a call

Build with the framework. Run it on the platform. Launch it with our engineers.

The framework is open source and free. The platform is coming, with early access now. Our engineers are ready when you are.

Get startedJoin early accessBook a call
Promptise - AI Framework LogoPromptise

The full-stack framework for agentic systems. Build with the framework. Run it on the platform. Launch it with our engineers.

pip install promptise

[01] Product

  • Framework
  • Platform (coming soon)
  • Enterprise
  • How it works
  • Contact

[02] Framework

  • The Agent
  • The Interface
  • The Harness

[03] Resources

  • Documentation
  • GitHub
  • Why Promptise
  • Use cases
  • Roadmap
  • Guides
  • Learning Paths
  • Questions

[04] Company

  • About
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
  • Subprocessors

© 2026 Promptise by Manser Ventures. All rights reserved.

hello@promptise.com