Metadata-Version: 2.4
Name: canai-tools
Version: 0.2.1
Summary: WORK WITH AI STRONGER — 21 Python CLI tools for AI-assisted development. Zero mandatory dependencies.
Author: CanTech Team
License: MIT
Project-URL: Homepage, https://smartinnventory.com/canai-nuxt
Project-URL: Documentation, https://smartinnventory.com/canai-nuxt/docs
Project-URL: Repository, https://github.com/can-tech/canai
Project-URL: Issue Tracker, https://github.com/can-tech/canai/issues
Keywords: ai,llm,claude,openai,gemini,deepseek,cli,developer-tools,context,prompt-engineering
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# WORK WITH AI STRONGER

**AI-Tools v0.2.0** — 15 production-grade Python tools engineered for AI-assisted development.

## The Stack

```
                         ┌──────────────┐
                         │   ai-tools   │  Master CLI
                         └──────┬───────┘
         ┌──────────────────────┼──────────────────────┐
         │                      │                      │
    ┌────┴────┐           ┌────┴────┐           ┌────┴────┐
    │ CONTEXT │           │  AGENT  │           │ QUALITY │
    └────┬────┘           └────┬────┘           └────┬────┘
         │                      │                      │
┌────────┼────────┐    ┌───────┼────────┐   ┌────────┼────────┐
│ctxbuilder       │    │apibridge        │   │qualgate         │
│ctxmerge         │    │smartroute       │   │perfscope        │
│repomap          │    │tokencost        │   │logparser        │
│smartpack        │    │memkeeper        │   │diffdigest       │
│scaffoldai       │    │                 │   │                 │
│specforge        │    │                 │   │                 │
│promptforge      │    │                 │   │                 │
└─────────────────┘    └─────────────────┘   └─────────────────┘
```

## Modules

| # | Module | Category | One-Liner |
|---|--------|----------|-----------|
| 1 | **ctxbuilder** | Context | Codebase → CLAUDE.md / llms.txt |
| 2 | **promptforge** | Context | Prompt templates + token count + cache |
| 3 | **diffdigest** | Quality | Git diff → AI-friendly summary |
| 4 | **scaffoldai** | Context | Bootstrap .ai/ + CLAUDE.md + AGENTS.md |
| 5 | **apibridge** | Agent | Claude + OpenAI + Gemini, one API |
| 6 | **perfscope** | Quality | Profiler output → bottleneck report |
| 7 | **ctxmerge** | Context | Merge monotrepo contexts |
| 8 | **specforge** | Context | Spec/PRD → structured task list |
| 9 | **logparser** | Quality | Raw logs → AI-optimized analysis |
| 10 | **tokencost** | Agent | Token usage + cost tracking |
| 11 | **repomap** | Context | Semantic repo map (hub detection) |
| 12 | **smartpack** | Context | Intelligent context packing |
| 13 | **memkeeper** | Agent | Cross-session persistent memory |
| 14 | **smartroute** | Agent | Task → cheapest adequate model |
| 15 | **qualgate** | Quality | Security + quality gate checker |

## Quick Start

```bash
pip install -e .

# Master CLI
ai-tools --version

# Understand any codebase
ctxbuilder /path/to/project

# Pack optimal context for a task
smartpack "fix the login bug" -p /path/to/project

# Chat with any LLM
apibridge "Explain this code" --provider claude

# Route task to cheapest adequate model
smartroute "Fix a typo in README"

# Save a development memory
memkeeper save "Auth pattern" "We use JWT with refresh tokens" -c pattern -t auth,jwt

# Run quality gate before merge
qualgate --base main -f compact

# Track AI costs
tokencost summary

# Find your biggest performance bottleneck
perfscope analyze profile.pstats

# Generate GitHub issues from a spec
specforge parse spec.md --format github
```

## Stats

- **69 Python files** — ~9,300 lines
- **1 core library** (ai_tools) + **15 tool modules**
- **16 CLI commands** — one master + 15 individual
- **4 LLM providers** — Claude, OpenAI, Gemini + extensible
- **Zero mandatory dependencies** — Python 3.10+ stdlib only
- **All outputs AI-optimized** — markdown, JSON, mermaid diagrams
