kdeps agent

An autonomous LLM REPL you run on your machine. Tool use, persistent memory, multi-step reasoning, skills, and a judge panel (the eval, on unless you turn it off). The default model is local, with no API key, fully offline. Point llm.base_url at an LLM server you run and the same REPL sends prompts there. Whole workflows and components register as callable tools; the model decides what to invoke.

kdeps            # bare REPL - built-in tools only
kdeps ./my-agent # also load that agent's workflows/components as tools

# ~/.kdeps/config.yaml
llm:
  backend: openai
  base_url: http://192.168.1.50:8000/v1   # your LLM server, your network
  models:
    - llama3.2                            # one model, or several

The desktop app reads the same file. The boundary rules are on Data sovereignty. The server page has the client contract.

Not this? If you want a deterministic request→response pipeline (same input, same execution path, safe to run unattended), that is kdeps workflow. To orchestrate several agents as one system, kdeps agencies.

---

Single workflow vs folder

When you point at a folder, kdeps discovers every workflow and agency file inside it (recursively). Each becomes a separate tool. The tool name is metadata.name from the workflow's manifest - not the filename.

Target	Workflow/agency/component tools registered
No path	None (built-in tools only)
Single workflow file/dir	One tool (metadata.name) + one per component
Single agency file	One tool (agency metadata.name)
Folder	One tool per workflow/agency found recursively + component tools

How it works

Given a workflow whose metadata.name is my-agent, running kdeps ./my-agent/ gives the LLM one tool named my-agent. When it calls that tool, kdeps runs the full workflow DAG - every resource in dependency order - and returns apiResponse.response to the LLM. The LLM can then call more tools or produce a final answer.

Command and flags

kdeps [path] [flags]

[path] is optional. When provided it must be a workflow or agency file or directory.

Flag	Default	Description
--model	KDEPS_AGENT_MODEL or llama3.2:1b	LLM model name
--backend	KDEPS_AGENT_BACKEND or file	LLM backend (file, gguf, ollama, openai, ...)
--base-url	KDEPS_AGENT_BASE_URL	LLM API base URL
--system	(none)	System prompt injected at conversation start
--skill	(none)	Path to a skill file or directory (repeatable)
--prompt	(none)	Path to a prompt templates directory (repeatable)
--resume	(none)	Session ID to resume directly (skips the picker)
--new	false	Start clean, skipping this folder's resume picker
--index	(none)	Search a folder outside the project with it (repeatable): added to the card and indexed first. See search folders
--theme	normal	REPL theme: normal, black, linux, vim, emacs, or a custom name from ~/.kdeps/themes/
--debug	false	Enable debug logging

# Environment variables (flags override these)
KDEPS_AGENT_MODEL=llama3.2:1b
KDEPS_AGENT_BACKEND=file              # default: local llamafile
KDEPS_AGENT_BASE_URL=http://localhost:11434/v1
KDEPS_THEME=black                     # same as --theme

Examples

kdeps                                            # bare REPL, built-in tools only
kdeps ./my-agent/                                # register one workflow as a tool
kdeps ./agents/                                  # register every workflow in the folder
kdeps ./agents/ --model mistral --system "You are a data analyst."
kdeps --backend gguf --model qwen3.5-4b          # local GGUF model
KDEPS_AGENT_BACKEND=openai kdeps ./agents/ --model gpt-4o
kdeps --resume abc123def456                      # resume a session

More on the agent loop

Topic	Page
Slash commands and auto-detected shell/file mentions	REPL slash commands
Built-in tool catalog, permission modes, lean mode	Built-in tools
Shell execution (!cmd, Ctrl+C / Ctrl+Z, jobs)	Shell execution
Live status line and stall detection during a tool run	Tool execution monitoring
Rewriting each prompt for clarity before the turn	Prompt refinement
Independent review of the final answer	Judge panel
/model, /context, auto-routing, running local servers	Local model management
One-time permission exceptions for a denied tool call	Approval tokens
Optional turo token reducer	Prompt reduction (turo)
Skills, prompt templates, KDEPS.md instructions	Skills and prompt templates
Per-folder session history and the startup resume picker	Sessions
Pasting, rendering, themes, notifications, updates	Agent loop REPL features

Differences from workflow mode

	Workflow mode (kdeps run)	Agent mode (kdeps [path])
Execution	DAG, deterministic	LLM loop, tool-driven
Entry point	metadata.targetActionId	User prompt
Unit of work	Individual resources	Whole workflows
Tools	Functions in chat.tools	One per workflow + one per component + built-ins
Input	One workflow path	Optional file or folder
Conversation	Single run	Multi-turn, persistent JSONL

See also

• Agent loop REPL features - pasting, rendering, sessions, updates
• Skills and prompt templates - context files that teach the agent
• REPL slash commands - full command reference
• Workflow mode - deterministic DAG pipelines
• LLM provider reference - backend config and model names
• Agencies - multi-agent orchestration