Metadata-Version: 2.4
Name: aidebrief
Version: 0.2.2
Summary: AI decision audit trail for engineering teams — capture, search, and review decisions from every coding AI
Author-email: Deepan Karthik <deepankarthik@gmail.com>
License: MIT
Project-URL: homepage, https://github.com/deepankarthik/aidebrief
Project-URL: repository, https://github.com/deepankarthik/aidebrief
Project-URL: changelog, https://github.com/deepankarthik/aidebrief/releases
Keywords: ai,conversation,search,mcp,sqlite,fts5,copilot,claude,opencode
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 :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Version Control
Classifier: Topic :: Text Processing :: Indexing
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: mcp>=1.0.0
Provides-Extra: test
Requires-Dist: pytest>=7.0; extra == "test"
Requires-Dist: ruff>=0.4; extra == "test"

# aidebrief

**AI decision audit trail for engineering teams.**

Every AI coding conversation — from Copilot, Claude Code, opencode — makes
decisions about your codebase. None of them leave a durable record.

aidebrief captures every conversation, extracts structured engineering
decisions, and gives you a queryable audit trail across all your AI tools.
No cloud, no telemetry, no infrastructure.

Think `git log` for AI decisions.

## Quick start

```bash
pip install aidebrief
aidebrief init
aidebrief review
```

## The problem

AI coding agents increase code throughput. They also introduce:

- **Cognitive debt** — approving AI-generated code without understanding it
- **Intent debt** — losing the original goals and constraints that shaped the code
- **Architectural debt** — different AI sessions making conflicting decisions

aidebrief resolves this by preserving the **ground truth** of every AI
interaction so you can review, search, and audit what was decided.

## Features

| Command | What it does |
|---------|-------------|
| `aidebrief review` | Browse recent sessions with decisions per session |
| `aidebrief review --decisions` | Decisions grouped by topic across all sessions |
| `aidebrief decisions` | Search extracted engineering decisions (table output) |
| `aidebrief decisions --json` | Same, raw JSON for piping |
| `aidebrief summarize <id>` | Narrative summary of a single session |
| `aidebrief search <query>` | Full-text search across all conversations |
| `aidebrief context <query>` | Retrieve relevant past sessions |
| `aidebrief contradictions <query>` | Check if a proposal conflicts with past decisions |
| `aidebrief list` | List recent sessions |
| `aidebrief status` | Database summary |

## How capture works

Copilot and Claude Code hook files are written to disk when a conversation
ends. On your next `review`, `search`, or `status` call, SyncManager processes
them lazily — ingesting the transcript, indexing it with FTS5, and extracting
structured engineering decisions. No background daemon needed.

An MCP server exposes the same database via tools accessible to AI agents.

## Quick tour

```bash
# What happened in the last week?
aidebrief review --since 7

# Does any session conflict with "use SQLite"?
aidebrief contradictions "use PostgreSQL instead of SQLite"

# Search across every AI tool
aidebrief search "why did we use WAL mode"

# Show all decisions about "sqlite"
aidebrief decisions sqlite
```

## Requirements

Python 3.11+ and `mcp>=1.0.0`. No other dependencies.
