Seven screens from what you know to what gets done.
No mock-ups. Every screen below is the product as it runs today, in a Praxis Agents OS workspace.
Public build, first tagged release pending. The platform runs end to end with the Docker quickstart. Public cloud deployment guides, self-service password reset, and user-developed applications are still to come.
- 01
Start with what you know.
Add documents, pages and files to a knowledge base that agents search and cite. Write down how your team does a job as a skill, with its reference documents. As agents work they keep memories, each with a record of where it came from, and you can review, correct, archive or purge them.
All of it lives in your database, not a vendor's. Retrieval combines keyword and semantic search, and agents cannot write to the knowledge base themselves.
- 02
Make an agent that works the way you do.
An agent is a name, a purpose, written instructions, a model and a set of tools. Pick OpenAI, Anthropic, Google, Azure OpenAI or an open-source model, and a tier from light to max. The exact model sits under Advanced, so most people never need to think about it.
Give it the skills it should follow and the other agents it may hand work to. Swap the model later and the instructions, skills and knowledge stay put.
- 03
Connect your accounts. Choose what each run can see.
Connect Gmail, Outlook Mail, SharePoint, Google Ads, Meta Ads, Google Analytics, Search Console, BigQuery, Airtable and Notion. Praxis discovers the accounts, properties, sites, drives, bases and datasets inside each connection. For every conversation or schedule, you pick which of those the agent works with.
Group resources into named context groups, such as all of one client's ad accounts, and reuse them.
- 04
Put it on a timetable.
Recurring, interval or one-off, in the timezone you choose. Pick a cadence in plain language, preview the next five runs, and attach a prompt and the context the run should use.
Scheduled runs pause for approval on external writes by default. Nothing goes out unattended unless the schedule is explicitly allowed to.
- 05
Decide what it does alone, and what needs you.
Every tool the agent can use has a switch: Off, Approval, or Auto. Reads such as running a report default to Auto. Writes default to Approval. Some writes, such as any change to a Google Ads account, cannot be set to Auto by anyone.
The policy lives with the tool definition in code, so an agent cannot talk its way past it.
- 06
Approve the email, not a blob of JSON.
When a run reaches a tool that needs approval, it stops and shows you the real thing: the email with its recipients and body, the record about to change, the campaign about to be paused. Edit it if you want. Then approve or decline.
The run resumes where it left off, even after a restart.
- 07
Keep the result. It adds to what you know.
Charts, reports and documents come back as artifacts with numbered versions. Every tool call is written to an append-only audit log with the actor, the person who asked, the tool, the provider, the request and the outcome.
Results, memories and audit rows stay in your workspace, so the next run starts from more. Audit rows survive the deletion of the agent, the user or the workspace they describe.
Not a model. Not a framework. The place agents live.
Praxis does not compete with model providers or agent frameworks. It holds what your organisation knows, and gives the agents that use it an identity, permissions, connections, a timetable and a record.
- Model providersOpenAI, Anthropic, Google or open-source models supply the reasoning. Swap them per agent.
- Agent runtimePydantic AI runs the model loop: instructions, history, tool calls, streaming.
- Praxis Agents OSKnowledge, skills, memory, workspaces, roles, tools and their policies, approvals, schedules, files, artifacts, audit.
- Your implementationThe agents, instructions, connections, rules and workflows specific to your organisation.
You run it. You own it. Including the pager.
The Docker quickstart gets a workspace running in minutes. Production on your cloud needs object storage, a secret manager, and someone whose job it is to keep it healthy.
Read the setup guide- 01Infrastructure: Postgres, object storage, a secret manager, and the API, worker and web containers
- 02Provider accounts and API keys for the models and integrations you enable
- 03Updates, backups, monitoring and incident response
- 04Roles, tool policies and approval rules for your workspaces
The architecture notes explain the why.
Nine documents: the runtime, streaming and durability, governance, context, Code Mode, integrations and the threat model. They describe what is built, not what is planned.