AI Workflows for Claude Code
17 workflows, 17 auto-triggering skills, MCP server with 41 tools. Plus the documentation toolchain we built along the way — now four standalone packages.
What is it?
How to do it?
Full API detail
Workflows That Remember
What makes it an OS, not a toolbox: orchestrated workflows on top, persistent memory underneath. Your AI collaborator stops starting from zero.
Orchestrated Workflows
17 multi-stage workflows — security audit, code review, bug prediction, release prep — with cost-tiered model routing and structured, readable reports. Works on a Claude subscription or an API key.
Cross-Session Memory
Findings from each session are stashed and recalled in the next. A retrievable lessons corpus surfaces the right engineering lesson at the moment a prompt needs it — automatically, or on demand with /recall.
Redis Semantic Tier
Local-first by default; plug in Redis Agent Memory Server for semantic search over your memory — local Ollama embeddings, no cloud required. Enable it with pip install 'attune-ai[redis]' plus a local AMS service. Our int8 vector quantization work is an open upstream PR to Redis.
The Documentation Toolchain
attune-ai began as a tool to help people work with AI, then grew into an engineering toolkit focused on Claude — and later Redis. The documentation toolchain came after, built with the same development discipline, and split off as four standalone packages forming an end-to-end author → reader loop. Use the full stack, or drop in just the piece you need.
- 1
attune-authorGenerates 15 kinds of source-grounded templates with per-type LLM polish. Runs at dev time or in CI.
- 2
attune-ragKeyword + semantic retrieval, mean faithfulness ≥ 0.97 (CI-gated) — answers stay grounded in your code.
- 3
attune-helpReads the templates at runtime. 1 dependency, no API key required. Embed in any Python tool.
- 4
attune-guiLocal dashboard. Browse templates, edit specs, run commands — one pane for the whole stack.
All four are open source — Apache 2.0.
# 1. attune-author — generate polished, source-grounded
# templates from your codebase (CI or dev time)
from attune_author.generator import generate_feature_templates
generate_feature_templates(feature, help_dir=".help", project_root=".")
# 2. attune-rag — keyword + semantic retrieval keeps
# answers grounded. Mean faithfulness ≥ 0.97, CI-gated.
# 3. attune-help — read them at runtime. 1 dependency,
# no API key required. Embed anywhere.
from attune_help import HelpEngine
engine = HelpEngine(template_dir=".help/templates")
print(engine.lookup("security-audit"))
# 4. attune-gui — local dashboard tying it all together.
# pip install attune-gui && attune-gui --openSix Ways to Use It
The attune-ai framework, its Claude Code plugin, and the four-package documentation toolchain we built with it. Pick the piece that fits the job.
attune-ai
Full framework. Workflows, staleness detection, MCP server, and 17 auto-triggering skills for Claude Code.
attune-help
Lightweight reader. 1 dependency, 6 files. Embed progressive help in any CLI tool, notebook, or internal app.
attune-author
AI authoring companion. Generates 15 kinds of source-grounded templates with per-type polish prompts.
attune-rag
Keyword + semantic retrieval over your Markdown corpus. Mean faithfulness ≥ 0.97, CI-gated — answers stay grounded.
attune-gui
Local dashboard. Browse templates, edit specs, run commands, and watch jobs — one pane for the whole stack.
Claude Code Plugin
Type /coach in Claude Code. Progressive help in your terminal — no setup required.
Ready to make your docs live?
Install from PyPI. Generate templates from your code. Ship help that never goes stale.
Source hashes detect code drift. Stale templates regenerate automatically — your docs stay in sync with your codebase.
Edit generated templates freely, or write from scratch. The engine respects hand-written content and never overwrites your work.