Metadata-Version: 2.4
Name: micro-cc
Version: 0.2.34
Summary: Harness that gives frontier models full system access — shell, filesystem, browser, MCP — running directly on the metal.
Author: George Salapa
License-Expression: MIT
Requires-Python: >=3.12
Description-Content-Type: text/markdown
Requires-Dist: anthropic>=0.76.0
Requires-Dist: anyio>=4.0
Requires-Dist: beautifulsoup4>=4.14
Requires-Dist: fastapi>=0.135
Requires-Dist: google-search-results>=2.4
Requires-Dist: httpx>=0.28
Requires-Dist: httpx-sse>=0.4
Requires-Dist: lxml>=6.0
Requires-Dist: mammoth>=1.11
Requires-Dist: markdown-it-py>=4.0
Requires-Dist: markdownify>=1.2
Requires-Dist: mcp>=1.26
Requires-Dist: numpy>=2.4
Requires-Dist: openai>=2.16
Requires-Dist: openpyxl>=3.1
Requires-Dist: pathvalidate>=3.3
Requires-Dist: pdfminer.six>=20260107
Requires-Dist: pillow>=12.0
Requires-Dist: playwright>=1.58
Requires-Dist: prompt_toolkit>=3.0
Requires-Dist: puremagic>=1.30
Requires-Dist: PyAutoGUI>=0.9
Requires-Dist: pydantic>=2.12
Requires-Dist: pydantic-settings>=2.13
Requires-Dist: python-dotenv>=1.2
Requires-Dist: python-pptx>=1.0
Requires-Dist: requests>=2.32
Requires-Dist: rich>=14.0
Requires-Dist: textual>=8.0
Requires-Dist: tiktoken>=0.12
Requires-Dist: uvicorn>=0.42
Requires-Dist: watchdog>=6.0
Requires-Dist: xlsxwriter>=3.2
Requires-Dist: youtube-transcript-api>=1.2

# micro · cc — cognitive compute

```
                   88
                   ""

88,dPYba,,adPYba,  88  ,adPPYba, 8b,dPPYba,  ,adPPYba,     ,adPPYba,  ,adPPYba,
88P'   "88"    "8a 88 a8"     "" 88P'   "Y8 a8"     "8a   a8"     "" a8"     ""
88      88      88 88 8b         88         8b       d8 · 8b         8b
88      88      88 88 "8a,   ,aa 88         "8a,   ,a8"   "8a,   ,aa "8a,   ,aa
88      88      88 88  `"Ybbd8"' 88          `"YbbdP"'     `"Ybbd8"'  `"Ybbd8"'
```

> Knowledge work is, by extension, a coding problem.

Frontier models with full system access — shell, filesystem, browser, MCP. Verbose, thorough planning paired with unrestricted file operations lets micro·cc take on complex multi-step work autonomously. Point it at any project directory and go.

## Install

```bash
pip install micro-cc
```

On first launch, micro·cc creates `~/.micro-cc/` with an example `.env` — add your API keys there and restart. That directory is also where conversation history and project state live.

## Platform

Built and tested on macOS. Works on Linux. Windows should work via `pip install` + any modern terminal — iTerm2 is macOS-only but micro·cc doesn't depend on it, it just looks best there.

## Environment

Edit `~/.micro-cc/.env` — set **one** endpoint:

```
# Option 1: Anthropic direct + OpenAI for embeddings
ANTHROPIC_API_KEY=sk-ant-
OPENAI_API_KEY=sk-proj-

# Option 2: LiteLLM proxy (Bedrock, Azure, etc.)
# LITELLM_BASE_URL=https://your-proxy.com
# LITELLM_API_KEY=sk-...

# Web search (always needed for search tools)
SERPAPI_KEY=
```

## Usage

```bash
microcc /path/to/your/project
```

**Controls:**
- `Enter` — submit prompt
- `Shift+Enter` — newline
- `Escape` — interrupt
- `/clear` — reset conversation
- `/model` — switch model
- `/exit` — quit

## Data

```
~/.micro-cc/
  .env                              API keys
  projects/
    {project}_{hash}/
      messages.jsonl                conversation history
      summary.json                  sliding-window summary
      project_path.txt              maps hash back to directory
```

## Tools

| Tool | Description |
|------|-------------|
| `bash_` | Shell execution in project_dir |
| `read_` | Read files with line numbers, offset/limit |
| `write_` | Create/overwrite files, auto-creates dirs |
| `edit_` | Surgical string replacement (fails if ambiguous) |
| `glob_` | Find files by pattern, sorted by mtime |
| `grep_` | Regex search with context lines |
| `browser_` | Web browsing and page extraction (beta) |
| `computer_use_` | Screen interaction and GUI automation (beta) |

All tools are discoverable — use `search_tools` to find more at runtime.

Relative paths resolve to `project_dir`. Absolute paths work anywhere.

## Architecture

```
start_live_.py (CLI)                textual TUI
       │
       │ async for event in claude_loop()
       ▼
claude_loop_.py (Core)              API calls, tool execution, JSONL storage
       │
       │ execute_tool_call()
       ▼
tools/                              bash_, file ops, browser, computer_use
       │
       ▼
~/.micro-cc/projects/{hash}/        conversation persistence
```

Full system access plus verbose planning. The model reads your codebase, writes plans, executes tools, observes results, iterates — until the work is done.
