Do a thing
Guides
Guides are for concrete tasks: use a feature, wire up an integration, or operate a workflow without turning the page into a theory seminar.
Core flow
Usage
Core command usage for `exec`, `ask`, `chat`, flags, examples, and agent selection.
Troubleshooting
Debugging
Use provider debug output and debug logs to figure out what the runtime is actually doing.
Media
Image generation
Generate and edit images with Gemini, OpenAI, xAI, Venice, or Flux.
Embeddings
Text embeddings
Generate vector embeddings for search, RAG, clustering, and similarity workflows.
Editing
File editing
Edit files with natural-language instructions, targeted ranges, and multiple diff formats.
Automation
Autonomous loops
Run an agent in a loop until a done condition is met.
Operations
Job runner
Run the jobs server, define scheduled work, and manage job definitions and runs from the CLI or API.
Integrations
MCP servers
Add external tools via Model Context Protocol and use them from term-llm commands.
Workflow bundles
Agents
Create and manage named workflow bundles with their own provider, model, tools, and instructions.
Long-term memory
Memory
Mine durable facts from completed sessions, search fragments, manage insights, and understand how memory differs from sessions.
Portable expertise
Skills
Use and manage portable instruction bundles that add task-specific context.
Ergonomics
Shell integration
Alias and shell-completion setup for using term-llm comfortably from the command line.