agent-cli 0.76.4__tar.gz → 0.77.0__tar.gz

{agent_cli-0.76.4 → agent_cli-0.77.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-cli
-Version: 0.76.4
+Version: 0.77.0
 Summary: A suite of AI-powered command-line tools for text correction, audio transcription, and voice assistance.
 Project-URL: Homepage, https://github.com/basnijholt/agent-cli
 Author-email: Bas Nijholt <bas@nijho.lt>
@@ -143,7 +143,7 @@ Since then I have expanded the tool with many more features, all focused on loca
 - **[`rag-proxy`](docs/commands/rag-proxy.md)**: RAG proxy server for chatting with your documents.
 - **[`dev`](docs/commands/dev.md)**: Parallel development with git worktrees and AI coding agents.
 - **[`server`](docs/commands/server/index.md)**: Local ASR and TTS servers with dual-protocol (Wyoming & OpenAI-compatible APIs), TTL-based memory management, and multi-platform acceleration. Whisper uses MLX on Apple Silicon or Faster Whisper on Linux/CUDA. TTS supports Kokoro (GPU) or Piper (CPU).
-- **[`transcribe-daemon`](docs/commands/transcribe-daemon.md)**: Continuous background transcription with VAD. Install with `uv tool install "agent-cli[vad]" -p 3.13`.
+- **[`transcribe-live`](docs/commands/transcribe-live.md)**: Continuous background transcription with VAD. Install with `uv tool install "agent-cli[vad]" -p 3.13`.
 
 ## Quick Start
 
@@ -254,7 +254,7 @@ The setup scripts automatically install:
     - [Provider Defaults](#provider-defaults)
   - [`autocorrect`](#autocorrect)
   - [`transcribe`](#transcribe)
-  - [`transcribe-daemon`](#transcribe-daemon)
+  - [`transcribe-live`](#transcribe-live)
   - [`speak`](#speak)
   - [`voice-edit`](#voice-edit)
   - [`assistant`](#assistant)
@@ -514,19 +514,19 @@ agent-cli install-extras rag memory vad
 
  Available extras:
 
-  • rag - RAG proxy server (ChromaDB, embeddings)
-  • memory - Long-term memory proxy (ChromaDB)
-  • vad - Voice Activity Detection (Silero VAD via ONNX)
-  • audio - Local audio recording/playback
-  • piper - Local Piper TTS engine
-  • kokoro - Kokoro neural TTS engine
-  • faster-whisper - Whisper ASR for CUDA/CPU
+  • audio - Audio recording/playback
+  • faster-whisper - Whisper ASR via CTranslate2
+  • kokoro - Kokoro neural TTS (GPU)
+  • llm - LLM framework (pydantic-ai)
+  • memory - Long-term memory proxy
   • mlx-whisper - Whisper ASR for Apple Silicon
-  • whisper-transformers - Whisper ASR via HuggingFace transformers (safetensors)
-  • wyoming - Wyoming protocol for ASR/TTS servers
+  • piper - Piper TTS (CPU)
+  • rag - RAG proxy (ChromaDB, embeddings)
   • server - FastAPI server components
-  • speed - Audio speed adjustment
-  • llm - LLM framework (pydantic-ai)
+  • speed - Audio speed adjustment (audiostretchy)
+  • vad - Voice Activity Detection (Silero VAD via ONNX)
+  • whisper-transformers - Whisper ASR via HuggingFace transformers
+  • wyoming - Wyoming protocol support
 
  Examples:
 
@@ -538,9 +538,9 @@ agent-cli install-extras rag memory vad
 
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
-│   extras      [EXTRAS]...  Extras to install: rag, memory, vad, audio, piper, kokoro,  │
-│                            faster-whisper, mlx-whisper, whisper-transformers, wyoming, │
-│                            server, speed, llm                                          │
+│   extras      [EXTRAS]...  Extras to install: audio, faster-whisper, kokoro, llm,      │
+│                            memory, mlx-whisper, piper, rag, server, speed, vad,        │
+│                            whisper-transformers, wyoming                               │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --list  -l        Show available extras with descriptions (what each one enables)      │
@@ -953,7 +953,7 @@ the `[defaults]` section of your configuration file.
 
 </details>
 
-### `transcribe-daemon`
+### `transcribe-live`
 
 **Purpose:** A continuous background transcription service that automatically detects and transcribes speech.
 
@@ -972,10 +972,10 @@ uv tool install "agent-cli[vad]" -p 3.13
 
 **How to Use It:**
 
-- **Basic Daemon**: `agent-cli transcribe-daemon`
-- **With Custom Role**: `agent-cli transcribe-daemon --role meeting`
-- **With LLM Cleanup**: `agent-cli transcribe-daemon --llm`
-- **Custom Silence Threshold**: `agent-cli transcribe-daemon --silence-threshold 1.5`
+- **Basic Daemon**: `agent-cli transcribe-live`
+- **With Custom Role**: `agent-cli transcribe-live --role meeting`
+- **With LLM Cleanup**: `agent-cli transcribe-live --llm`
+- **Custom Silence Threshold**: `agent-cli transcribe-live --silence-threshold 1.5`
 
 **Output Files:**
 
@@ -983,7 +983,7 @@ uv tool install "agent-cli[vad]" -p 3.13
 - **Audio Files**: `~/.config/agent-cli/audio/YYYY/MM/DD/*.mp3`
 
 <details>
-<summary>See the output of <code>agent-cli transcribe-daemon --help</code></summary>
+<summary>See the output of <code>agent-cli transcribe-live --help</code></summary>
 
 <!-- CODE:BASH:START -->
 <!-- echo '```yaml' -->
@@ -991,20 +991,20 @@ uv tool install "agent-cli[vad]" -p 3.13
 <!-- export TERM=dumb -->
 <!-- export COLUMNS=90 -->
 <!-- export TERMINAL_WIDTH=90 -->
-<!-- agent-cli transcribe-daemon --help -->
+<!-- agent-cli transcribe-live --help -->
 <!-- echo '```' -->
 <!-- CODE:END -->
 <!-- OUTPUT:START -->
 <!-- ⚠️ This content is auto-generated by `markdown-code-runner`. -->
 ```yaml
 
- Usage: agent-cli transcribe-daemon [OPTIONS]
+ Usage: agent-cli transcribe-live [OPTIONS]
 
- Continuous transcription daemon using Silero VAD for speech detection.
+ Continuous live transcription using Silero VAD for speech detection.
 
- Unlike transcribe (single recording session), this daemon runs indefinitely and
- automatically detects speech segments using Voice Activity Detection (VAD). Each
- detected segment is transcribed and logged with timestamps.
+ Unlike transcribe (single recording session), this runs indefinitely and automatically
+ detects speech segments using Voice Activity Detection (VAD). Each detected segment is
+ transcribed and logged with timestamps.
 
  How it works:
 
@@ -1020,11 +1020,11 @@ uv tool install "agent-cli[vad]" -p 3.13
  Examples:
 
 
-  agent-cli transcribe-daemon
-  agent-cli transcribe-daemon --role meeting --silence-threshold 1.5
-  agent-cli transcribe-daemon --llm --clipboard --role notes
-  agent-cli transcribe-daemon --transcription-log ~/meeting.jsonl --no-save-audio
-  agent-cli transcribe-daemon --asr-provider openai --llm-provider gemini --llm
+  agent-cli transcribe-live
+  agent-cli transcribe-live --role meeting --silence-threshold 1.5
+  agent-cli transcribe-live --llm --clipboard --role notes
+  agent-cli transcribe-live --transcription-log ~/meeting.jsonl --no-save-audio
+  agent-cli transcribe-live --asr-provider openai --llm-provider gemini --llm
 
 
  Tips:
@@ -1032,7 +1032,7 @@ uv tool install "agent-cli[vad]" -p 3.13
   • Use --role to tag entries (e.g., speaker1, meeting, personal)
   • Adjust --vad-threshold if detection is too sensitive (increase) or missing speech
     (decrease)
-  • Use --stop to cleanly terminate a running daemon
+  • Use --stop to cleanly terminate a running process
   • With --llm, transcripts are cleaned up (punctuation, filler words removed)
 
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮

{agent_cli-0.76.4 → agent_cli-0.77.0}/README.md

@@ -49,7 +49,7 @@ Since then I have expanded the tool with many more features, all focused on loca
 - **[`rag-proxy`](docs/commands/rag-proxy.md)**: RAG proxy server for chatting with your documents.
 - **[`dev`](docs/commands/dev.md)**: Parallel development with git worktrees and AI coding agents.
 - **[`server`](docs/commands/server/index.md)**: Local ASR and TTS servers with dual-protocol (Wyoming & OpenAI-compatible APIs), TTL-based memory management, and multi-platform acceleration. Whisper uses MLX on Apple Silicon or Faster Whisper on Linux/CUDA. TTS supports Kokoro (GPU) or Piper (CPU).
-- **[`transcribe-daemon`](docs/commands/transcribe-daemon.md)**: Continuous background transcription with VAD. Install with `uv tool install "agent-cli[vad]" -p 3.13`.
+- **[`transcribe-live`](docs/commands/transcribe-live.md)**: Continuous background transcription with VAD. Install with `uv tool install "agent-cli[vad]" -p 3.13`.
 
 ## Quick Start
 
@@ -160,7 +160,7 @@ The setup scripts automatically install:
     - [Provider Defaults](#provider-defaults)
   - [`autocorrect`](#autocorrect)
   - [`transcribe`](#transcribe)
-  - [`transcribe-daemon`](#transcribe-daemon)
+  - [`transcribe-live`](#transcribe-live)
   - [`speak`](#speak)
   - [`voice-edit`](#voice-edit)
   - [`assistant`](#assistant)
@@ -420,19 +420,19 @@ agent-cli install-extras rag memory vad
 
  Available extras:
 
-  • rag - RAG proxy server (ChromaDB, embeddings)
-  • memory - Long-term memory proxy (ChromaDB)
-  • vad - Voice Activity Detection (Silero VAD via ONNX)
-  • audio - Local audio recording/playback
-  • piper - Local Piper TTS engine
-  • kokoro - Kokoro neural TTS engine
-  • faster-whisper - Whisper ASR for CUDA/CPU
+  • audio - Audio recording/playback
+  • faster-whisper - Whisper ASR via CTranslate2
+  • kokoro - Kokoro neural TTS (GPU)
+  • llm - LLM framework (pydantic-ai)
+  • memory - Long-term memory proxy
   • mlx-whisper - Whisper ASR for Apple Silicon
-  • whisper-transformers - Whisper ASR via HuggingFace transformers (safetensors)
-  • wyoming - Wyoming protocol for ASR/TTS servers
+  • piper - Piper TTS (CPU)
+  • rag - RAG proxy (ChromaDB, embeddings)
   • server - FastAPI server components
-  • speed - Audio speed adjustment
-  • llm - LLM framework (pydantic-ai)
+  • speed - Audio speed adjustment (audiostretchy)
+  • vad - Voice Activity Detection (Silero VAD via ONNX)
+  • whisper-transformers - Whisper ASR via HuggingFace transformers
+  • wyoming - Wyoming protocol support
 
  Examples:
 
@@ -444,9 +444,9 @@ agent-cli install-extras rag memory vad
 
 
 ╭─ Arguments ────────────────────────────────────────────────────────────────────────────╮
-│   extras      [EXTRAS]...  Extras to install: rag, memory, vad, audio, piper, kokoro,  │
-│                            faster-whisper, mlx-whisper, whisper-transformers, wyoming, │
-│                            server, speed, llm                                          │
+│   extras      [EXTRAS]...  Extras to install: audio, faster-whisper, kokoro, llm,      │
+│                            memory, mlx-whisper, piper, rag, server, speed, vad,        │
+│                            whisper-transformers, wyoming                               │
 ╰────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮
 │ --list  -l        Show available extras with descriptions (what each one enables)      │
@@ -859,7 +859,7 @@ the `[defaults]` section of your configuration file.
 
 </details>
 
-### `transcribe-daemon`
+### `transcribe-live`
 
 **Purpose:** A continuous background transcription service that automatically detects and transcribes speech.
 
@@ -878,10 +878,10 @@ uv tool install "agent-cli[vad]" -p 3.13
 
 **How to Use It:**
 
-- **Basic Daemon**: `agent-cli transcribe-daemon`
-- **With Custom Role**: `agent-cli transcribe-daemon --role meeting`
-- **With LLM Cleanup**: `agent-cli transcribe-daemon --llm`
-- **Custom Silence Threshold**: `agent-cli transcribe-daemon --silence-threshold 1.5`
+- **Basic Daemon**: `agent-cli transcribe-live`
+- **With Custom Role**: `agent-cli transcribe-live --role meeting`
+- **With LLM Cleanup**: `agent-cli transcribe-live --llm`
+- **Custom Silence Threshold**: `agent-cli transcribe-live --silence-threshold 1.5`
 
 **Output Files:**
 
@@ -889,7 +889,7 @@ uv tool install "agent-cli[vad]" -p 3.13
 - **Audio Files**: `~/.config/agent-cli/audio/YYYY/MM/DD/*.mp3`
 
 <details>
-<summary>See the output of <code>agent-cli transcribe-daemon --help</code></summary>
+<summary>See the output of <code>agent-cli transcribe-live --help</code></summary>
 
 <!-- CODE:BASH:START -->
 <!-- echo '```yaml' -->
@@ -897,20 +897,20 @@ uv tool install "agent-cli[vad]" -p 3.13
 <!-- export TERM=dumb -->
 <!-- export COLUMNS=90 -->
 <!-- export TERMINAL_WIDTH=90 -->
-<!-- agent-cli transcribe-daemon --help -->
+<!-- agent-cli transcribe-live --help -->
 <!-- echo '```' -->
 <!-- CODE:END -->
 <!-- OUTPUT:START -->
 <!-- ⚠️ This content is auto-generated by `markdown-code-runner`. -->
 ```yaml
 
- Usage: agent-cli transcribe-daemon [OPTIONS]
+ Usage: agent-cli transcribe-live [OPTIONS]
 
- Continuous transcription daemon using Silero VAD for speech detection.
+ Continuous live transcription using Silero VAD for speech detection.
 
- Unlike transcribe (single recording session), this daemon runs indefinitely and
- automatically detects speech segments using Voice Activity Detection (VAD). Each
- detected segment is transcribed and logged with timestamps.
+ Unlike transcribe (single recording session), this runs indefinitely and automatically
+ detects speech segments using Voice Activity Detection (VAD). Each detected segment is
+ transcribed and logged with timestamps.
 
  How it works:
 
@@ -926,11 +926,11 @@ uv tool install "agent-cli[vad]" -p 3.13
  Examples:
 
 
-  agent-cli transcribe-daemon
-  agent-cli transcribe-daemon --role meeting --silence-threshold 1.5
-  agent-cli transcribe-daemon --llm --clipboard --role notes
-  agent-cli transcribe-daemon --transcription-log ~/meeting.jsonl --no-save-audio
-  agent-cli transcribe-daemon --asr-provider openai --llm-provider gemini --llm
+  agent-cli transcribe-live
+  agent-cli transcribe-live --role meeting --silence-threshold 1.5
+  agent-cli transcribe-live --llm --clipboard --role notes
+  agent-cli transcribe-live --transcription-log ~/meeting.jsonl --no-save-audio
+  agent-cli transcribe-live --asr-provider openai --llm-provider gemini --llm
 
 
  Tips:
@@ -938,7 +938,7 @@ uv tool install "agent-cli[vad]" -p 3.13
   • Use --role to tag entries (e.g., speaker1, meeting, personal)
   • Adjust --vad-threshold if detection is too sensitive (increase) or missing speech
     (decrease)
-  • Use --stop to cleanly terminate a running daemon
+  • Use --stop to cleanly terminate a running process
   • With --llm, transcripts are cleaned up (punctuation, filler words removed)
 
 ╭─ Options ──────────────────────────────────────────────────────────────────────────────╮

agent_cli-0.76.4/agent_cli/agents/transcribe_daemon.py → agent_cli-0.77.0/agent_cli/agents/transcribe_live.py

@@ -1,4 +1,4 @@
-"""Continuous transcription daemon with voice activity detection."""
+"""Continuous live transcription with voice activity detection."""
 
 from __future__ import annotations
 
@@ -287,9 +287,9 @@ async def _daemon_loop(cfg: DaemonConfig) -> None:  # noqa: PLR0912, PLR0915
                     await asyncio.wait(background_tasks, timeout=2.0)
 
 
-@app.command("transcribe-daemon", rich_help_panel="Voice Commands")
+@app.command("transcribe-live", rich_help_panel="Voice Commands")
 @requires_extras("audio", "vad", "llm")
-def transcribe_daemon(  # noqa: PLR0912
+def transcribe_live(  # noqa: PLR0912
     *,
     # Daemon-specific options
     role: str = typer.Option(
@@ -368,9 +368,9 @@ def transcribe_daemon(  # noqa: PLR0912
     config_file: str | None = opts.CONFIG_FILE,
     print_args: bool = opts.PRINT_ARGS,
 ) -> None:
-    """Continuous transcription daemon using Silero VAD for speech detection.
+    """Continuous live transcription using Silero VAD for speech detection.
 
-    Unlike `transcribe` (single recording session), this daemon runs indefinitely
+    Unlike `transcribe` (single recording session), this runs indefinitely
     and automatically detects speech segments using Voice Activity Detection (VAD).
     Each detected segment is transcribed and logged with timestamps.
 
@@ -387,24 +387,24 @@ def transcribe_daemon(  # noqa: PLR0912
 
     **Examples:**
 
-        agent-cli transcribe-daemon
-        agent-cli transcribe-daemon --role meeting --silence-threshold 1.5
-        agent-cli transcribe-daemon --llm --clipboard --role notes
-        agent-cli transcribe-daemon --transcription-log ~/meeting.jsonl --no-save-audio
-        agent-cli transcribe-daemon --asr-provider openai --llm-provider gemini --llm
+        agent-cli transcribe-live
+        agent-cli transcribe-live --role meeting --silence-threshold 1.5
+        agent-cli transcribe-live --llm --clipboard --role notes
+        agent-cli transcribe-live --transcription-log ~/meeting.jsonl --no-save-audio
+        agent-cli transcribe-live --asr-provider openai --llm-provider gemini --llm
 
     **Tips:**
 
     - Use `--role` to tag entries (e.g., `speaker1`, `meeting`, `personal`)
     - Adjust `--vad-threshold` if detection is too sensitive (increase) or missing speech (decrease)
-    - Use `--stop` to cleanly terminate a running daemon
+    - Use `--stop` to cleanly terminate a running process
     - With `--llm`, transcripts are cleaned up (punctuation, filler words removed)
     """
     if print_args:
         print_command_line_args(locals())
     setup_logging(log_level, log_file_logging, quiet=quiet)
 
-    process_name = "transcribe-daemon"
+    process_name = "transcribe-live"
 
     # Handle stop/status commands
     if stop:

{agent_cli-0.76.4 → agent_cli-0.77.0}/agent_cli/cli.py

@@ -121,9 +121,10 @@ from .agents import (  # noqa: E402, F401
     rag_proxy,
     speak,
     transcribe,
-    transcribe_daemon,
+    transcribe_live,
     voice_edit,
 )
+from .daemon import cli as daemon_cli  # noqa: E402, F401
 from .dev import cli as dev_cli  # noqa: E402, F401
 from .install import extras, hotkeys, services  # noqa: E402, F401
 from .server import cli as server_cli  # noqa: E402, F401