This page now carries the broader runtime and product story. The homepage is focused on the business wedge. The docs are where the open-source runtime, architecture, workflow model, and long-term direction should live.
`seshat` is the public Go runtime: sessions, tools, permissions, MCP, memory, RAG, providers, CLI, gRPC, and SDK surfaces.
These docs also explain the broader thesis: organized agentic work, multi-agent teams, workflow composition, and the layers that can be built above the runtime.
curl -fsSL https://raw.githubusercontent.com/KPO-Tech/seshat/main/scripts/install.sh | bashPick the path that matches what you need right now: install, understand the runtime, build workflows, or contribute to the open-source layer.
Install the runtime locally, configure a provider, and run your first session.
Start with the quick start and first-agent flow before exploring deeper architecture.
Learn how sessions, tools, permissions, memory, MCP, and execution fit together.
Use the Go SDK to compose workflows, agent teams, and controlled runtime loops.
See the broad open-source thesis, the wedge, and where the public runtime is going.
Contribute to the runtime, documentation, skills, examples, and future SDK layers.
CLI, Go SDK, gRPC clients, and future SDKs consume the same runtime foundation.
`seshat` owns sessions, tools, permissions, memory, MCP, RAG, execution, and agent primitives.
Enterprise workflow products, private delivery layers, and higher-level team systems can sit above the runtime, but these docs stay focused on the public foundation.
The structure is broader than the currently published content. This page reflects the actual state instead of pretending every layer is already complete.
Install Seshat and run your first autonomous agent in minutes.
Understand the architecture and core ideas that make Seshat different.
Programmatic access to Seshat from any language or platform.
Step-by-step guides for end users and product surfaces.
Deep dives into agentic AI concepts, patterns and architecture decisions.
Honest side-by-side comparisons with popular agent frameworks.