Seshat AIDocumentation

Documentation / Getting started

Configuration

Choose a provider and a model, set API keys, and enable the optional tools.

Seshat needs at least one model provider. You can configure it from the command line, or with environment variables.

From the command line

seshat config --provider anthropic --api-key sk-ant-...   # set a provider and its key
seshat config --model anthropic:claude-sonnet-4-20250514  # choose the model (provider:model)
seshat config --print                                     # show the current configuration

In the terminal interface, press ctrl+, for providers and ctrl+m for models. API keys entered there are stored encrypted, per provider.

With environment variables

Set the variable of the provider you want. This is the simplest way for servers and scripts:

export ANTHROPIC_API_KEY=sk-ant-...

Seshat reads its settings from environment variables, from a .env file, and from a .seshat.yaml file.

Supported providers

ProviderIDAuthenticationSetting
AnthropicanthropicAPI keyANTHROPIC_API_KEY
OpenAIopenaiAPI keyOPENAI_API_KEY
Mistral AImistralAPI keyMISTRAL_API_KEY
Google GeminigeminiAPI keyGOOGLE_API_KEY
DeepSeekdeepseekAPI keyDEEPSEEK_API_KEY
OllamaollamaNoneLocal, localhost:11434
OpenRouteropenrouterAPI keyOPENROUTER_API_KEY
CodexcodexOAuthseshat login, or CODEX_API_KEY
Z.aiz-aiAPI keyZ_AI_API_KEY
MiniMaxminimaxAPI keyMINIMAX_API_KEY
AWS BedrockbedrockAWS credentialsAWS_ACCESS_KEY_ID and AWS_REGION
Google Cloud Vertex AIvertexGoogle CloudANTHROPIC_VERTEX_PROJECT_ID and CLOUD_ML_REGION
Azure AI FoundryfoundryAPI keyANTHROPIC_FOUNDRY_API_KEY
Cloudflare Workers AIworkers-aiAPI keyCLOUDFLARE_API_KEY
OpenCode ZenopencodeAPI keyOPENCODE_API_KEY
Kimi (Moonshot AI)kimiAPI keyKIMI_API_KEY

The models each provider offers, with their context sizes and capabilities, are in Providers and models.

Optional tools

Some tools are registered automatically but only become active when their key is set.

ToolWhat it doesSetting
generate_imageImage generationOPENAI_API_KEY
text_to_speechSpeech synthesisOPENAI_API_KEY
speech_to_textTranscriptionOPENAI_API_KEY
devto_publishPublish to DEVDEV_TO_API_KEY
notebook_*Work in a live Jupyter kernelJUPYTER_SERVER_URL and JUPYTER_TOKEN

Updated on 2026-10-07