Skip to main content

The Problem

Your team uses different AI coding agents. Alice prefers Cursor, Bob uses Claude Code, and Charlie swears by Copilot. Each agent has its own config format, so you end up with fragmented, inconsistent instructions — or no shared instructions at all.

The Solution

Drevon gives every team member the same context regardless of which agent they use. One config, every agent in sync.

Setting Up for a Team

1. Initialize in Project Mode

The team preset configures agents with a collaborative posture:

2. Enable All Agents Your Team Uses

Or enable them all at init:

3. Add Team-Specific Instructions

Edit drevon.config.json:

4. Commit Everything

Commit both the config file and the generated agent files. This way, team members get instructions immediately without needing to run drevon sync first.

Team Workflow

When Updating Instructions

When a New Member Joins

The new team member gets everything automatically when they clone the repo — all agent configs are already generated and committed. If they want to add their personal agent:

Memory in Teams

The v2 project-mode topic files under .drevon/memory/topics/ work well as shared team context. Commit topics/ — the log/ segments are episodic and can get noisy:
Because each decision is its own file under topics/decisions/<date>-<slug>.md, PR review and merges stay clean — teammates rarely touch the same file, so there are no merge conflicts on a single monolithic decisions.md.
Memory is designed for single-agent use. In team settings, be intentional about what you commit: the topics/ tree works well as shared docs, while the episodic log/ segments can get noisy.