decision-log

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review.

Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force.

Keep your team's AI coding agents coordinated — without sharing source code.

The knowledge your codebase doesn't contain — a Claude Code skill that records project state, decisions, and dead ends so a new session resumes instead of re-reading the codebase.

SpecFirst é um framework documental em Markdown, distribuído como template, para governar projetos tocados por humanos e agentes de IA.

Open-source, self-hostable system of record for team decisions capture the why, review the outcome.

Capture the why behind AI-generated code. Generate decision logs from Claude Code sessions for PR reviews.

Local-first workflow protocol for non-coding knowledge work, decision tracking, and resumable project state.

An append-only ledger that records why decisions were made.

A Claude Code Harness that maintains the brain of your project i.e. decisions, flow, and TODOs - so any agent gets up to speed fast and helps you keep track of the code flow

Your code knows what. Lore knows why. — CLI tool that captures the why behind code changes.

Put the "why" in version control. git why records the reason behind each commit as native git trailers — it survives clone/push and shows in git log.

Keep the decision. Keep the why. Engineering decisions in Markdown: a Rust CLI for people and AI agents, with a local dashboard.

Architecture decision records (ADRs) that show up in the pull requests they govern. CLI, linter, static site and GitHub Action. adr-tools and MADR compatible, English and Thai templates.

Answer your AI agents' questions from a web page behind Cloudflare Access: lock answers as rulings, settle stale ones, review your dashboard page and pull requests, and run panels (roar, refine, drill). A Claude Code / Desktop plugin plus a small self-hosted server; it runs no git and no project code.

Archived/reference-only portable AI-agent governance template; active implementation: pm-dispatch.

Branch-aware AI decision logging for development projects — AGENTS.md-canonical, link-integrity CI, skills.sh integration.

Capture decisions with full context, metadata, and confidence scores. Includes outcome tracking, notes, and CSV export.

AI-ready project/product management toolkit for turning project chaos into structured prompts, docs, decisions, risks, and execution plans.

An append-only reasoning log for LLM-assisted research. Record the why behind decisions — with falsifiability conditions, confidence tags, and failure-first philosophy.