hieuchaydi

hieuchaydi / DecisionGraph

Public

DecisionGraph is an engineering decision memory system that captures evidence from GitHub/Slack/Jira, answers “why” questions, and runs pre-change guardrails via CLI/API/MCP.

docs-decisongraph-9td9eo59f-hieuchaydiis-projects.vercel.app cli docker llm mcp-server python
10
1
100% credibility
Found Apr 25, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

DecisionGraph captures engineering decisions and reasoning from git history, GitHub PRs/issues, Slack, Jira, and text files, enabling queries, guardrails, contradiction detection, and reports via CLI, web API, or chat interface.

How It Works

1
📖 Discover DecisionGraph

You hear about a helpful tool that remembers the reasons behind your team's code choices so no one repeats past mistakes.

2
🚀 Set it up in minutes

You follow simple steps to get it running on your computer with example team stories already loaded to try right away.

3
📂 Add your team's history

You point it to your folders, chats, or tickets, and it pulls in past notes and changes to build your memory bank.

4
❓ Ask any why question

You type a natural question like 'Why limit retries here?' and instantly see the decision, who made it, and supporting facts.

5
🛡️ Check changes safely

Before updating code, you describe your plan and get warnings about old risks or forgotten reasons to pause.

✅ Team remembers forever

Your group now answers why-questions fast, avoids repeat errors, and builds confidently with full context.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is DecisionGraph?

DecisionGraph is a Python-based engineering decision memory system that captures evidence from GitHub PRs/issues, Slack exports, Jira JSON, git history, and local files to answer "why" questions about code changes. It extracts decisions with tradeoffs, assumptions, and risks, then runs pre-change guardrails to flag contradictions or stale assumptions before refactors. Access it via CLI for chat/query, HTTP API for automation, or MCP for tool integration, all with Docker quickstart.

Why is it gaining traction?

It stands out by turning scattered chat/PR notes into searchable decision graphs with confidence scores and evidence links, unlike generic search tools that miss context. Developers hook on the CLI chat mode for instant "why did we cap retries?" answers and guardrail checks that block risky changes. Multi-interface (CLI/API/MCP) plus demo seeding makes prototyping dead simple.

Who should use this?

Staff engineers querying rationale before touching legacy payments/auth code. Platform leads watching assumptions against live metrics like queue volume. Engineering managers generating reports on contradictions across components for sprint planning.

Verdict

Try it for solo prototyping or small teams—solid docs, passing benchmarks, and CLI demo hook you in minutes, despite 10 stars and 1.0% credibility signaling early maturity. Production needs more battle-testing on real org data.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.