ranausmanai

Agent Workgraph

Name: Agent Workgraph
Author: ranausmanai

AI community

SOURCE https://github.com/ranausmanai/agent-workgraph

Description

Turn AI coding sessions into reusable engineering memory, evals, briefs, and skills.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

[![npm](https://img.shields.io/npm/v/agent-workgraph?style=flat-square&color=818cf8&label=npm)](https://npmjs.com/package/agent-workgraph) [![node](https://img.shields.io/node/v/agent-workgraph?style=flat-square&color=34d399)](https://nodejs.org) [![license](https://img.shields.io/npm/l/agent-workgraph?style=flat-square&color=38bdf8)](LICENSE) [![local-first](https://img.shields.io/badge/local--first-no%20cloud-60a5fa?style=flat-square)](#privacy)

**WorkGraph** watches your Claude Code and Codex sessions and compiles everything useful into a structured memory directory — `.workgraph/` — that lives alongside your code.

When a new session starts, WorkGraph gives the agent a short **brief**: what was built, what broke, what to watch out for. No dumping old chat history. No context waste.

The problem it solves

Every time you start a new AI coding session, the agent starts from zero. It doesn't know what was tried last time, what rules emerged, what files were touched, or what traps to avoid. You end up re-explaining context, watching the agent repeat known mistakes.

WorkGraph turns those sessions into memory that compounds.

Web UI

Run `workgraph ui .` and open `http://127.0.0.1:8787` to see your project's full journey — every milestone, what was built, confidence levels, known traps, and files touched.

![WorkGraph Overview — milestone timeline](docs/screenshot-overview.png)

Switch to **Map** for the full force-directed knowledge graph:

![WorkGraph Map — knowledge graph](docs/screenshot-map.png)

The UI has five modes: