Chat

Interactive chat mode with AI agents

The chat command starts an interactive chat session with an AI agent.

Usage

praisonai chat [OPTIONS] [PROMPT]

Arguments

Argument	Description
PROMPT	Initial prompt for the chat session

Options

Option	Short	Description	Default
--model	-m	LLM model to use	provider-aware default
--verbose	-v	Verbose output	false
--memory		Enable memory persistence	false
--tools	-t	Comma-separated tool names (e.g. web_search,github) or a tools.py file path
--user-id		User ID for memory isolation
--session	-s	Session ID to resume
--workspace	-w	Workspace directory	current dir
--debug		Enable debug logging to ~/.praisonai/async_tui_debug.log	false
--safe / --no-safe		Safe mode: require approval for file writes and commands (default: on). Use --no-safe to disable.	true
--autonomy/--no-autonomy		Enable agent autonomy for complex tasks	true
--ui-backend		UI backend: auto, plain, rich, mg	auto
--json		Output JSON (forces plain backend)	false
--no-color		Disable colors	false
--theme		UI theme: default, dark, light, minimal	default
--compact		Compact output mode	false
--no-rules		Disable auto-injection of project instruction files	false
--no-context		Disable AGENTS.md/CLAUDE.md auto-loading into system prompt	false

praisonai chat with no --model picks a default that matches your active provider credential — it no longer always falls back to gpt-4o-mini. See Setup → What happens if you skip --model for the precedence ladder.

Piped Input

praisonai chat accepts piped stdin as an initial prompt seed.

echo "$STACKTRACE" | praisonai chat "Explain this"

Prompt argument is merged first, piped body second. The interactive REPL still opens for follow-up turns. See Piped Input.

Examples

Start a chat session

praisonai chat

Chat with initial prompt

praisonai chat "Hello, how can you help me today?"

Chat with specific model

praisonai chat --model gpt-4o "Explain machine learning"

Chat with memory enabled

praisonai chat --memory "Remember my name is Alice"

Resume a previous session

praisonai chat --session abc123

Use plain text output (no colors)

praisonai chat --ui-backend plain "What is 2+2?"

Output as JSON

praisonai chat --json "Summarize this text"

Use middle-ground UI (enhanced streaming)

praisonai chat --ui-backend mg

Chat without auto-loaded instructions

praisonai chat --no-rules "Hello, ignore project rules"

The chat session normally inherits AGENTS.md/CLAUDE.md/PRAISON.md from the working directory. --no-rules runs the assistant with only its built-in instructions.

Exit codes

praisonai chat returns a non-zero exit code on failure so shell scripts and CI can detect problems without parsing stderr.

Exit code	Meaning
0	Prompt executed successfully.
1	Authentication failed (invalid or missing API key), the agent raised an exception, or a profiled run finished with no response and a logged auth error.

Exit-code semantics apply to single-prompt / non-interactive invocations (praisonai chat "..." and praisonai chat --profile ...). The interactive TUI (praisonai chat with no prompt) always exits 0 when you leave the session.

Detect failures in a script

if ! praisonai chat "Summarize the changelog" >/dev/null; then
  echo "chat failed — check credentials or provider status" >&2
  exit 1
fi

CI example (GitHub Actions)

- name: Smoke-test chat
  run: praisonai chat "Say hello" > /tmp/chat.out
  env:
    OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

The step fails automatically if the key is invalid — no extra parsing needed.

Project context

By default, praisonai chat walks up from the current directory to your git root and prepends any AGENTS.md / CLAUDE.md / agents.md / .agents/AGENTS.md it finds to the agent’s system prompt, layered on top of ~/.praisonai/AGENTS.md. Pass --no-context (or set PRAISON_NO_CONTEXT=true) to disable. See Context Files for details.

UI Backends

The --ui-backend flag controls how output is rendered:

Backend	Description
auto	Auto-select best available (default)
plain	Plain text, no colors, works everywhere
rich	Rich formatting with colors and panels
mg	Middle-ground: enhanced streaming with no flicker

Environment variable: Set PRAISONAI_UI_SAFE=1 to force plain backend.

Interactive Commands

During a chat session, you can use these commands:

Command	Description
/help	Show available commands
/exit, /quit	Exit the chat session
/clear	Clear conversation history
/new	Start new conversation
/session	Show current session info
/sessions	List all saved sessions
/continue	Continue most recent session
/model [name]	Show or change model
/cost	Show token usage and cost
/history	Show conversation history
/export [file]	Export conversation to file
/import <file>	Import conversation from file
/status	Show ACP/LSP runtime status
/auto	Toggle autonomy mode (auto-delegate complex tasks)
/debug	Toggle debug logging to ~/.praisonai/async_tui_debug.log
/plan <task>	Create a step-by-step plan for a task
/handoff <type> <task>	Delegate to specialized agent (code/research/review/docs)
/compact	Toggle compact output mode
/multiline	Toggle multiline input mode
/files	List workspace files for @ mentions
/queue	Show pending prompts in queue

Quick Start

Running praisonai with no arguments starts interactive mode:

praisonai

This is equivalent to praisonai chat.

Features

The interactive chat mode includes:

• ASCII Art Logo - Beautiful PraisonAI branding on startup
• Status Bar - Shows model, session info, and keyboard shortcuts
• Auto-completion - Tab completion for commands and file paths
• Command History - Navigate previous commands with arrow keys
• Markdown Rendering - Rich formatted responses with syntax highlighting
• Streaming Output - Real-time response streaming

See Also

• Interactive TUI - Full TUI interface
• Session - Session management
• Memory - Memory management