Security & privacy
Secrets live in your vault. Conversations and memories are encrypted, by default or, optionally, end to end. Data privacy lists how each kind of data is handled.
Developers build, validate and publish AI agents in the built‑in development environment. They also describe when to use each agent in plain English.
Users just chat with the platform. Semantic search routes each request to the agent whose description fits. The agent runs in a controlled runtime. Multiple agents build on each other in a conversation.
The platform handles all the plumbing and records every agent run for observability.
pip install tactetAn agent is written in JSON with Python expressions. Systems and prompts are defined outside the agent’s code: APIs, databases, MCP servers and LLMs in platform-wide profiles, and prompts in each agent’s meta.
The UI includes a complete development environment for agents. Tell Draft with AI what the agent should do, refine the generated agent in the schema‑aware code editor, then trace and validate it before publishing.
{
"functions": {
"main": {
"commands": {
"api": { … },
"var": { … },
"llm": { … }
}
},
"order_status": {
"commands": {
"db": { … },
"return": { … }
}
}
}
}
Agent: a set of functions
Function. Every run starts in main
Commands, run in this order
Another function
Its commands, in order
Users hold conversations from the UI, or from Slack and Teams with a bot. The LLM message thread is stored in a model-neutral format, so the next agent can continue the same thread with a different model. Conversation variables give agents short-term memory, and the memory command gives them long-term memory.
Conversations are one way to use Tactet agents. An agent harness, such as Claude Code, is another. Tactet‑skill connects the harness to every published agent. The harness splits a request into parts, runs Tactet agents alongside its local skills, and combines the results. Each agent runs on the agent server, inside your organization.
The platform has three parts: a stateless agent server and a UI that run in your organization, and a cloud service that provides state, search and reporting. pip installs the agent server and the UI together. Each can also be installed separately from the source. The agent server can run standalone or in a cluster. The cloud service can be shared or dedicated.
Secrets live in your vault. Conversations and memories are encrypted, by default or, optionally, end to end. Data privacy lists how each kind of data is handled.
Four roles: users, developers, administrators and owners. Service accounts for bots and scripts. Built-in authentication as well as single sign‑on.
Everything that runs in your organization can be built from the source: the agent server and the UI. Set the logging configuration to see every call to the cloud service.
An agent refers to enterprise systems by profile name. Dev and prod profiles point at their own systems, so the same agent runs unchanged.
Agent servers are stateless and can be run in a cluster. Configuration and profile changes are live on the next agent run on every server, without a restart.
Integrate at three levels: from Python expressions inside an agent, through the REST API, and with hooks that run your code at the platform’s decision points.