agent-cli 0.72.4__tar.gz → 0.72.6__tar.gz

{agent_cli-0.72.4 → agent_cli-0.72.6}/.claude-plugin/README.md

@@ -30,7 +30,7 @@ uvx --python 3.13 agent-cli dev new my-feature --agent --prompt "..."
 claude plugin marketplace add basnijholt/agent-cli
 
 # Then install
-claude plugin install agent-cli@agent-cli-dev
+claude plugin install agent-cli-dev@agent-cli
 ```
 
 ## Usage

{agent_cli-0.72.4 → agent_cli-0.72.6}/.github/workflows/docker.yml

@@ -104,6 +104,10 @@ jobs:
         include:
           - image: transcribe-proxy
             dockerfile: docker/transcribe-proxy.Dockerfile
+          - image: rag-proxy
+            dockerfile: docker/rag-proxy.Dockerfile
+          - image: memory-proxy
+            dockerfile: docker/memory-proxy.Dockerfile
 
     steps:
       - name: Checkout repository

{agent_cli-0.72.4 → agent_cli-0.72.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-cli
-Version: 0.72.4
+Version: 0.72.6
 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>
@@ -46,6 +46,8 @@ Requires-Dist: soundfile>=0.12.0; extra == 'kokoro'
 Requires-Dist: transformers>=4.40.0; extra == 'kokoro'
 Provides-Extra: llm
 Requires-Dist: pydantic-ai-slim[duckduckgo,google,openai,vertexai]>=0.1.1; extra == 'llm'
+Provides-Extra: llm-core
+Requires-Dist: pydantic-ai-slim[google,openai]>=0.1.1; extra == 'llm-core'
 Provides-Extra: memory
 Requires-Dist: chromadb>=0.4.22; extra == 'memory'
 Requires-Dist: fastapi[standard]; extra == 'memory'
@@ -88,7 +90,7 @@ Description-Content-Type: text/markdown
 
 # Agent CLI
 
-<img src="https://raw.githubusercontent.com/basnijholt/agent-cli/refs/heads/main/.github/logo.svg" alt="agent-cli logo" align="right" style="width: 250px;" />
+<img src="https://raw.githubusercontent.com/basnijholt/agent-cli/refs/heads/main/.github/logo.svg" alt="agent-cli logo" align="right" style="width: 200px;" />
 
 `agent-cli` is a collection of **_local-first_**, AI-powered command-line agents that run entirely on your machine.
 It provides a suite of powerful tools for voice and text interaction, designed for privacy, offline capability, and seamless integration with system-wide hotkeys and workflows.
@@ -391,7 +393,7 @@ agent-cli dev install-skill
 
 # Option 2: Install via Claude Code plugin marketplace
 claude plugin marketplace add basnijholt/agent-cli
-claude plugin install agent-cli@agent-cli-dev
+claude plugin install agent-cli-dev@agent-cli
 ```
 
 Once installed, Claude Code can automatically use this skill when you ask to:

{agent_cli-0.72.4 → agent_cli-0.72.6}/README.md

@@ -1,6 +1,6 @@
 # Agent CLI
 
-<img src="https://raw.githubusercontent.com/basnijholt/agent-cli/refs/heads/main/.github/logo.svg" alt="agent-cli logo" align="right" style="width: 250px;" />
+<img src="https://raw.githubusercontent.com/basnijholt/agent-cli/refs/heads/main/.github/logo.svg" alt="agent-cli logo" align="right" style="width: 200px;" />
 
 `agent-cli` is a collection of **_local-first_**, AI-powered command-line agents that run entirely on your machine.
 It provides a suite of powerful tools for voice and text interaction, designed for privacy, offline capability, and seamless integration with system-wide hotkeys and workflows.
@@ -303,7 +303,7 @@ agent-cli dev install-skill
 
 # Option 2: Install via Claude Code plugin marketplace
 claude plugin marketplace add basnijholt/agent-cli
-claude plugin install agent-cli@agent-cli-dev
+claude plugin install agent-cli-dev@agent-cli
 ```
 
 Once installed, Claude Code can automatically use this skill when you ask to:

agent_cli-0.72.6/agent_cli/_extras.json

@@ -0,0 +1,73 @@
+{
+  "audio": [
+    "Audio recording/playback",
+    [
+      "sounddevice"
+    ]
+  ],
+  "faster-whisper": [
+    "TODO: add description",
+    []
+  ],
+  "kokoro": [
+    "TODO: add description",
+    []
+  ],
+  "llm": [
+    "LLM framework (pydantic-ai)",
+    [
+      "pydantic_ai"
+    ]
+  ],
+  "llm-core": [
+    "Minimal LLM support for Docker images",
+    [
+      "pydantic_ai"
+    ]
+  ],
+  "memory": [
+    "Long-term memory proxy",
+    [
+      "chromadb",
+      "yaml"
+    ]
+  ],
+  "mlx-whisper": [
+    "TODO: add description",
+    []
+  ],
+  "piper": [
+    "TODO: add description",
+    []
+  ],
+  "rag": [
+    "RAG proxy (ChromaDB, embeddings)",
+    [
+      "chromadb"
+    ]
+  ],
+  "server": [
+    "FastAPI server components",
+    [
+      "fastapi"
+    ]
+  ],
+  "speed": [
+    "Audio speed adjustment (audiostretchy)",
+    [
+      "audiostretchy"
+    ]
+  ],
+  "vad": [
+    "Voice Activity Detection (silero-vad)",
+    [
+      "silero_vad"
+    ]
+  ],
+  "wyoming": [
+    "Wyoming protocol support",
+    [
+      "wyoming"
+    ]
+  ]
+}

{agent_cli-0.72.4 → agent_cli-0.72.6}/agent_cli/dev/cli.py

@@ -1779,7 +1779,9 @@ def install_skill(
     - Works when you ask to "work on multiple features" or "parallelize tasks"
 
     **Alternative:** Install globally via Claude Code plugin marketplace:
-    `claude plugin marketplace add basnijholt/agent-cli`
+
+    1. `claude plugin marketplace add basnijholt/agent-cli`
+    2. `claude plugin install agent-cli-dev@agent-cli`
     """
     # Use current repo root (works in worktrees too)
     repo_root = _get_current_repo_root()

{agent_cli-0.72.4 → agent_cli-0.72.6}/agent_cli/scripts/sync_extras.py

@@ -33,6 +33,7 @@ EXTRA_METADATA: dict[str, tuple[str, list[str]]] = {
     "openai": ("OpenAI API provider", ["openai"]),
     "gemini": ("Google Gemini provider", ["google.genai"]),
     "llm": ("LLM framework (pydantic-ai)", ["pydantic_ai"]),
+    "llm-core": ("Minimal LLM support for Docker images", ["pydantic_ai"]),
     # Feature extras
     "rag": ("RAG proxy (ChromaDB, embeddings)", ["chromadb"]),
     "memory": ("Long-term memory proxy", ["chromadb", "yaml"]),

{agent_cli-0.72.4 → agent_cli-0.72.6}/docker/docker-compose.yml

@@ -41,6 +41,17 @@
 #   LLM_OPENAI_MODEL   - Model name for OpenAI LLM provider
 #   OPENAI_BASE_URL    - OpenAI-compatible LLM endpoint
 #   OPENAI_API_KEY     - API key for OpenAI LLM
+#
+#   RAG_PORT           - RAG proxy port (default: 8000)
+#   RAG_LIMIT          - Number of document chunks per query (default: 3)
+#   RAG_ENABLE_TOOLS   - Enable read_full_document tool (default: true)
+#   EMBEDDING_MODEL    - Embedding model for RAG/memory (default: text-embedding-3-small)
+#
+#   MEMORY_PORT        - Memory proxy port (default: 8100)
+#   MEMORY_TOP_K       - Number of memories per query (default: 5)
+#   MEMORY_MAX_ENTRIES - Max entries per conversation (default: 500)
+#   MEMORY_SUMMARIZATION - Enable fact extraction (default: true)
+#   MEMORY_GIT_VERSIONING - Enable git versioning (default: true)
 
 services:
   # ===========================================================================
@@ -227,6 +238,69 @@ services:
       # - OPENAI_API_KEY=your-api-key
     restart: unless-stopped
 
+  # ===========================================================================
+  # RAG Proxy
+  # ===========================================================================
+
+  rag-proxy:
+    image: ghcr.io/basnijholt/agent-cli-rag-proxy:latest
+    build:
+      context: ..
+      dockerfile: docker/rag-proxy.Dockerfile
+    profiles: [cuda, cpu]
+    ports:
+      - "8000:8000"
+    volumes:
+      - rag-docs:/data/docs
+      - rag-db:/data/db
+      - rag-cache:/home/rag/.cache
+    environment:
+      - RAG_HOST=0.0.0.0
+      - RAG_PORT=${RAG_PORT:-8000}
+      - RAG_DOCS_FOLDER=/data/docs
+      - RAG_CHROMA_PATH=/data/db
+      - RAG_LIMIT=${RAG_LIMIT:-3}
+      - RAG_ENABLE_TOOLS=${RAG_ENABLE_TOOLS:-true}
+      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-text-embedding-3-small}
+      - LOG_LEVEL=${LOG_LEVEL:-info}
+      # OpenAI-compatible backend configuration
+      - OPENAI_BASE_URL=${OPENAI_BASE_URL:-http://ollama:11434/v1}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+    restart: unless-stopped
+
+  # ===========================================================================
+  # Memory Proxy
+  # ===========================================================================
+
+  memory-proxy:
+    image: ghcr.io/basnijholt/agent-cli-memory-proxy:latest
+    build:
+      context: ..
+      dockerfile: docker/memory-proxy.Dockerfile
+    profiles: [cuda, cpu]
+    ports:
+      - "8100:8100"
+    volumes:
+      - memory-data:/data/memory
+      - memory-cache:/home/memory/.cache
+    environment:
+      - MEMORY_HOST=0.0.0.0
+      - MEMORY_PORT=${MEMORY_PORT:-8100}
+      - MEMORY_PATH=/data/memory
+      - MEMORY_TOP_K=${MEMORY_TOP_K:-5}
+      - MEMORY_MAX_ENTRIES=${MEMORY_MAX_ENTRIES:-500}
+      - MEMORY_MMR_LAMBDA=${MEMORY_MMR_LAMBDA:-0.7}
+      - MEMORY_RECENCY_WEIGHT=${MEMORY_RECENCY_WEIGHT:-0.2}
+      - MEMORY_SCORE_THRESHOLD=${MEMORY_SCORE_THRESHOLD:-0.35}
+      - MEMORY_SUMMARIZATION=${MEMORY_SUMMARIZATION:-true}
+      - MEMORY_GIT_VERSIONING=${MEMORY_GIT_VERSIONING:-true}
+      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-text-embedding-3-small}
+      - LOG_LEVEL=${LOG_LEVEL:-info}
+      # OpenAI-compatible backend configuration
+      - OPENAI_BASE_URL=${OPENAI_BASE_URL:-http://ollama:11434/v1}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+    restart: unless-stopped
+
 volumes:
   ollama-data:
     name: agent-cli-ollama-data
@@ -236,3 +310,13 @@ volumes:
     name: agent-cli-whisper-cache
   tts-cache:
     name: agent-cli-tts-cache
+  rag-docs:
+    name: agent-cli-rag-docs
+  rag-db:
+    name: agent-cli-rag-db
+  rag-cache:
+    name: agent-cli-rag-cache
+  memory-data:
+    name: agent-cli-memory-data
+  memory-cache:
+    name: agent-cli-memory-cache

agent_cli-0.72.6/docker/memory-proxy.Dockerfile

@@ -0,0 +1,115 @@
+# Dockerfile for agent-cli Memory Proxy server
+# A long-term memory proxy that stores facts and injects relevant context into LLM requests
+#
+# Build example:
+#   docker build -f docker/memory-proxy.Dockerfile -t agent-cli-memory-proxy .
+#
+# Run examples:
+#   docker run -p 8100:8100 -v ./memory:/data/memory agent-cli-memory-proxy
+#
+#   # With custom OpenAI-compatible backend:
+#   docker run -p 8100:8100 \
+#     -v ./memory:/data/memory \
+#     -e OPENAI_BASE_URL=http://ollama:11434/v1 \
+#     agent-cli-memory-proxy
+#
+# Environment variables (priority: env var > config file > default):
+#   MEMORY_PATH          - Directory for memory storage (default: /data/memory)
+#   MEMORY_TOP_K         - Number of memories to retrieve per query (default: 5)
+#   MEMORY_MAX_ENTRIES   - Max entries per conversation before eviction (default: 500)
+#   MEMORY_MMR_LAMBDA    - MMR lambda 0-1, higher=relevance (default: 0.7)
+#   MEMORY_RECENCY_WEIGHT - Weight for recency vs semantic (default: 0.2)
+#   MEMORY_SCORE_THRESHOLD - Min relevance threshold (default: 0.35)
+#   MEMORY_SUMMARIZATION - Enable fact extraction: true/false (default: true)
+#   MEMORY_GIT_VERSIONING - Enable git versioning: true/false (default: true)
+#   EMBEDDING_MODEL      - Embedding model name (default: text-embedding-3-small)
+#   OPENAI_BASE_URL      - OpenAI-compatible API base URL
+#   OPENAI_API_KEY       - API key for embeddings and chat
+#   MEMORY_HOST          - Server bind address (default: 0.0.0.0)
+#   MEMORY_PORT          - Server port (default: 8100)
+#   LOG_LEVEL            - Logging level: debug, info, warning, error (default: info)
+
+# =============================================================================
+# Builder stage - install dependencies and project
+# =============================================================================
+FROM python:3.13-slim AS builder
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git build-essential && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
+WORKDIR /app
+
+COPY pyproject.toml uv.lock README.md ./
+COPY .git ./.git
+COPY agent_cli ./agent_cli
+COPY scripts ./scripts
+RUN uv sync --frozen --no-dev --no-editable --extra memory
+
+# =============================================================================
+# Runtime stage - minimal image using Python slim directly
+# =============================================================================
+FROM python:3.13-slim
+
+# Install runtime dependencies:
+# - libgomp1: Required by onnxruntime for parallel processing
+# - git: Required for memory git versioning feature
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends libgomp1 git && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+RUN groupadd -g 1000 memory && useradd -m -u 1000 -g memory memory
+
+WORKDIR /app
+
+COPY --from=builder /app/.venv /app/.venv
+
+RUN ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli
+
+# Create data directory
+RUN mkdir -p /data/memory && chown -R memory:memory /data
+
+USER memory
+
+# Configure git for memory versioning (required for commits)
+RUN git config --global user.email "memory-proxy@agent-cli.local" && \
+    git config --global user.name "Memory Proxy"
+
+# Cache directory for models (embeddings)
+ENV HF_HOME=/home/memory/.cache/huggingface
+RUN mkdir -p /home/memory/.cache/huggingface
+
+EXPOSE 8100
+
+ENV MEMORY_HOST=0.0.0.0 \
+    MEMORY_PORT=8100 \
+    MEMORY_PATH=/data/memory \
+    MEMORY_TOP_K=5 \
+    MEMORY_MAX_ENTRIES=500 \
+    MEMORY_MMR_LAMBDA=0.7 \
+    MEMORY_RECENCY_WEIGHT=0.2 \
+    MEMORY_SCORE_THRESHOLD=0.35 \
+    MEMORY_SUMMARIZATION=true \
+    MEMORY_GIT_VERSIONING=true \
+    EMBEDDING_MODEL=text-embedding-3-small \
+    LOG_LEVEL=info
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:${MEMORY_PORT}/health')" || exit 1
+
+ENTRYPOINT ["sh", "-c", "agent-cli memory proxy \
+    --host ${MEMORY_HOST} \
+    --port ${MEMORY_PORT} \
+    --memory-path ${MEMORY_PATH} \
+    --default-top-k ${MEMORY_TOP_K} \
+    --max-entries ${MEMORY_MAX_ENTRIES} \
+    --mmr-lambda ${MEMORY_MMR_LAMBDA} \
+    --recency-weight ${MEMORY_RECENCY_WEIGHT} \
+    --score-threshold ${MEMORY_SCORE_THRESHOLD} \
+    --embedding-model ${EMBEDDING_MODEL} \
+    --log-level ${LOG_LEVEL} \
+    $([ \"${MEMORY_SUMMARIZATION}\" = \"false\" ] && echo '--no-summarization' || echo '--summarization') \
+    $([ \"${MEMORY_GIT_VERSIONING}\" = \"false\" ] && echo '--no-git-versioning' || echo '--git-versioning') \
+    ${MEMORY_EXTRA_ARGS:-}"]

agent_cli-0.72.6/docker/rag-proxy.Dockerfile

@@ -0,0 +1,100 @@
+# Dockerfile for agent-cli RAG Proxy server
+# A document-aware proxy that indexes files and injects relevant context into LLM requests
+#
+# Build example:
+#   docker build -f docker/rag-proxy.Dockerfile -t agent-cli-rag-proxy .
+#
+# Run examples:
+#   docker run -p 8000:8000 -v ./docs:/data/docs agent-cli-rag-proxy
+#
+#   # With custom OpenAI-compatible backend:
+#   docker run -p 8000:8000 \
+#     -v ./docs:/data/docs \
+#     -v ./rag_db:/data/db \
+#     -e OPENAI_BASE_URL=http://ollama:11434/v1 \
+#     agent-cli-rag-proxy
+#
+# Environment variables (priority: env var > config file > default):
+#   RAG_DOCS_FOLDER      - Folder to watch for documents (default: /data/docs)
+#   RAG_CHROMA_PATH      - ChromaDB storage directory (default: /data/db)
+#   RAG_LIMIT            - Number of chunks to retrieve per query (default: 3)
+#   RAG_ENABLE_TOOLS     - Enable read_full_document tool: true/false (default: true)
+#   EMBEDDING_MODEL      - Embedding model name (default: text-embedding-3-small)
+#   OPENAI_BASE_URL      - OpenAI-compatible API base URL
+#   OPENAI_API_KEY       - API key for embeddings and chat
+#   RAG_HOST             - Server bind address (default: 0.0.0.0)
+#   RAG_PORT             - Server port (default: 8000)
+#   LOG_LEVEL            - Logging level: debug, info, warning, error (default: info)
+
+# =============================================================================
+# Builder stage - install dependencies and project
+# =============================================================================
+FROM python:3.13-slim AS builder
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git build-essential && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
+WORKDIR /app
+
+COPY pyproject.toml uv.lock README.md ./
+COPY .git ./.git
+COPY agent_cli ./agent_cli
+COPY scripts ./scripts
+RUN uv sync --frozen --no-dev --no-editable --extra rag
+
+# =============================================================================
+# Runtime stage - minimal image using Python slim directly
+# =============================================================================
+FROM python:3.13-slim
+
+# Install runtime dependencies:
+# - libgomp1: Required by onnxruntime for parallel processing
+# - git: Required for .git detection in some document types
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends libgomp1 git && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+RUN groupadd -g 1000 rag && useradd -m -u 1000 -g rag rag
+
+WORKDIR /app
+
+COPY --from=builder /app/.venv /app/.venv
+
+RUN ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli
+
+# Create data directories
+RUN mkdir -p /data/docs /data/db && chown -R rag:rag /data
+
+USER rag
+
+# Cache directory for models (embeddings, reranker)
+ENV HF_HOME=/home/rag/.cache/huggingface
+RUN mkdir -p /home/rag/.cache/huggingface
+
+EXPOSE 8000
+
+ENV RAG_HOST=0.0.0.0 \
+    RAG_PORT=8000 \
+    RAG_DOCS_FOLDER=/data/docs \
+    RAG_CHROMA_PATH=/data/db \
+    RAG_LIMIT=3 \
+    RAG_ENABLE_TOOLS=true \
+    EMBEDDING_MODEL=text-embedding-3-small \
+    LOG_LEVEL=info
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:${RAG_PORT}/health')" || exit 1
+
+ENTRYPOINT ["sh", "-c", "agent-cli rag-proxy \
+    --host ${RAG_HOST} \
+    --port ${RAG_PORT} \
+    --docs-folder ${RAG_DOCS_FOLDER} \
+    --chroma-path ${RAG_CHROMA_PATH} \
+    --limit ${RAG_LIMIT} \
+    --embedding-model ${EMBEDDING_MODEL} \
+    --log-level ${LOG_LEVEL} \
+    $([ \"${RAG_ENABLE_TOOLS}\" = \"false\" ] && echo '--no-rag-tools' || echo '--rag-tools') \
+    ${RAG_EXTRA_ARGS:-}"]

{agent_cli-0.72.4 → agent_cli-0.72.6}/docker/transcribe-proxy.Dockerfile

@@ -24,11 +24,9 @@
 # =============================================================================
 # Builder stage - install dependencies and project
 # =============================================================================
-FROM python:3.13-slim AS builder
+FROM python:3.13-alpine AS builder
 
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends git && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
+RUN apk add --no-cache git
 
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
@@ -38,30 +36,24 @@ COPY pyproject.toml uv.lock README.md ./
 COPY .git ./.git
 COPY agent_cli ./agent_cli
 COPY scripts ./scripts
-RUN uv sync --frozen --no-dev --no-editable --extra server --extra wyoming --extra llm
+RUN uv sync --frozen --no-dev --no-editable --extra server --extra wyoming --extra llm-core
 
 # =============================================================================
-# Runtime stage - minimal image
+# Runtime stage - minimal Alpine image
 # =============================================================================
-FROM debian:bookworm-slim
+FROM python:3.13-alpine
 
-COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
-
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends ffmpeg && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
+RUN apk add --no-cache ffmpeg
 
-ENV UV_PYTHON_INSTALL_DIR=/opt/python
-RUN uv python install 3.13
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
-RUN groupadd -g 1000 transcribe && useradd -m -u 1000 -g transcribe transcribe
+RUN addgroup -g 1000 transcribe && adduser -u 1000 -G transcribe -D transcribe
 
 WORKDIR /app
 
 COPY --from=builder /app/.venv /app/.venv
 
-RUN ln -sf $(uv python find 3.13) /app/.venv/bin/python && \
-    ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli
+RUN ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli
 
 USER transcribe
 
@@ -71,7 +63,7 @@ ENV PROXY_HOST=0.0.0.0 \
     PROXY_PORT=61337
 
 HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
-    CMD /app/.venv/bin/python -c "import urllib.request; urllib.request.urlopen('http://localhost:${PROXY_PORT}/health')" || exit 1
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:${PROXY_PORT}/health')" || exit 1
 
 ENTRYPOINT ["sh", "-c", "agent-cli server transcribe-proxy \
     --host ${PROXY_HOST} \

{agent_cli-0.72.4 → agent_cli-0.72.6}/docker/tts.Dockerfile

@@ -108,25 +108,19 @@ ENTRYPOINT ["sh", "-c", "agent-cli server tts \
 # =============================================================================
 # CPU target: CPU-only with Piper TTS
 # =============================================================================
-FROM debian:bookworm-slim AS cpu
+FROM python:3.13-slim AS cpu
 
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends ffmpeg && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-
-ENV UV_PYTHON_INSTALL_DIR=/opt/python
-RUN uv python install 3.13
-
-RUN getent group 1000 || groupadd -g 1000 tts; \
-    id -u 1000 >/dev/null 2>&1 || useradd -m -u 1000 -g 1000 tts
+RUN groupadd -g 1000 tts && useradd -m -u 1000 -g 1000 tts
 
 WORKDIR /app
 
 COPY --from=builder-cpu /app/.venv /app/.venv
 
-RUN ln -sf $(uv python find 3.13) /app/.venv/bin/python && \
+# Install imageio-ffmpeg for bundled static ffmpeg binary (77MB vs 420MB for Debian package)
+RUN uv pip install --python /app/.venv/bin/python imageio-ffmpeg && \
+    ln -s $(/app/.venv/bin/python -c "import imageio_ffmpeg; print(imageio_ffmpeg.get_ffmpeg_exe())") /usr/local/bin/ffmpeg && \
     ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli && \
     mkdir -p /home/tts/.cache && chown -R tts:tts /home/tts
 
@@ -144,7 +138,7 @@ ENV TTS_HOST=0.0.0.0 \
     TTS_DEVICE=cpu
 
 HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
-    CMD /app/.venv/bin/python -c "import urllib.request; urllib.request.urlopen('http://localhost:${TTS_PORT}/health')" || exit 1
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:${TTS_PORT}/health')" || exit 1
 
 ENTRYPOINT ["sh", "-c", "agent-cli server tts \
     --host ${TTS_HOST} \

{agent_cli-0.72.4 → agent_cli-0.72.6}/docker/whisper.Dockerfile

@@ -83,25 +83,19 @@ ENTRYPOINT ["sh", "-c", "agent-cli server whisper \
 # =============================================================================
 # CPU target: CPU-only with faster-whisper
 # =============================================================================
-FROM debian:bookworm-slim AS cpu
+FROM python:3.13-slim AS cpu
 
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends ffmpeg && \
-    apt-get clean && rm -rf /var/lib/apt/lists/*
-
-ENV UV_PYTHON_INSTALL_DIR=/opt/python
-RUN uv python install 3.13
-
-RUN getent group 1000 || groupadd -g 1000 whisper; \
-    id -u 1000 >/dev/null 2>&1 || useradd -m -u 1000 -g 1000 whisper
+RUN groupadd -g 1000 whisper && useradd -m -u 1000 -g 1000 whisper
 
 WORKDIR /app
 
 COPY --from=builder /app/.venv /app/.venv
 
-RUN ln -sf $(uv python find 3.13) /app/.venv/bin/python && \
+# Install imageio-ffmpeg for bundled static ffmpeg binary (77MB vs 420MB for Debian package)
+RUN uv pip install --python /app/.venv/bin/python imageio-ffmpeg && \
+    ln -s $(/app/.venv/bin/python -c "import imageio_ffmpeg; print(imageio_ffmpeg.get_ffmpeg_exe())") /usr/local/bin/ffmpeg && \
     ln -s /app/.venv/bin/agent-cli /usr/local/bin/agent-cli && \
     mkdir -p /home/whisper/.cache && chown -R whisper:whisper /home/whisper
 
@@ -118,7 +112,7 @@ ENV WHISPER_HOST=0.0.0.0 \
     WHISPER_DEVICE=cpu
 
 HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
-    CMD /app/.venv/bin/python -c "import urllib.request; urllib.request.urlopen('http://localhost:${WHISPER_PORT}/health')" || exit 1
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:${WHISPER_PORT}/health')" || exit 1
 
 ENTRYPOINT ["sh", "-c", "agent-cli server whisper \
     --host ${WHISPER_HOST} \

{agent_cli-0.72.4 → agent_cli-0.72.6}/docs/architecture/memory.md

@@ -46,7 +46,17 @@ A local-first system that gives LLMs persistent memory across conversations, wit
 
 ### Try It Now
 
-Get an LLM that remembers you using [Ollama](https://ollama.com). Two options:
+Get an LLM that remembers you using [Ollama](https://ollama.com). Three options:
+
+**Option 0: With Docker Compose (easiest)**
+
+```bash
+# Start Memory proxy with Ollama backend
+docker compose -f docker/docker-compose.yml --profile cpu up memory-proxy ollama
+
+# Point your chat client at http://localhost:8100/v1
+# The LLM will now remember facts across conversations
+```
 
 **Option A: With [Open WebUI](https://github.com/open-webui/open-webui) (web interface)**
 

{agent_cli-0.72.4 → agent_cli-0.72.6}/docs/architecture/rag.md

@@ -40,7 +40,19 @@ A local proxy that gives LLMs access to your documents using smarter multi-stage
 
 ### Try It Now
 
-Chat with your documents using [Ollama](https://ollama.com). Two options:
+Chat with your documents using [Ollama](https://ollama.com). Three options:
+
+**Option 0: With Docker Compose (easiest)**
+
+```bash
+# Start RAG proxy with Ollama backend
+docker compose -f docker/docker-compose.yml --profile cpu up rag-proxy ollama
+
+# Copy your documents into the volume
+docker cp ./my-docs/. $(docker volume inspect agent-cli-rag-docs --format '{{ .Mountpoint }}')/
+
+# Point your chat client at http://localhost:8000/v1
+```
 
 **Option A: With [Open WebUI](https://github.com/open-webui/open-webui) (web interface)**