canai-tools 0.2.1

WORK WITH AI STRONGER — 21 Python CLI tools for AI-assisted development. Zero mandatory dependencies.

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

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