For teams · Shared memory

Your team's agents
should share a brain.

When one developer's agent discovers a gotcha, fixes a bug, or makes an architecture decision — every other agent on the team should know about it. Persistent shared context across every AI coding session.

Getting Started
Chapter I · The cost of amnesia

Multiplied across
every developer.

01 — Time

Context dies between sessions

Your agent spends the first five minutes of every session re-discovering what the last session already knew. Multiply that by every developer on your team.

02 — Knowledge

Knowledge stays siloed

Dev A fixes a tricky deployment issue. Dev B hits the same issue next week. Their agents have no way to share what was learned.

03 — Visibility

No visibility into AI work

Team leads have no idea what their agents are doing — what tasks are in progress, what decisions were made, or what's blocking progress.

Chapter II · Shared by default

Everything your
team needs.

Shared task board

Tasks, in sync.

Drag-and-drop Kanban visible to the whole team. When one agent creates or completes a task, every team member's agent sees it instantly.

Notes & decisions

Pin once, share forever.

Architecture decisions, gotchas, and bug patterns captured as persistent notes. Pin critical context so every agent reads it at session start.

Session history

See every run.

See what every developer's agent worked on — token usage, tool calls, and session summaries. Full transparency into AI-assisted work.

Semantic search

Search by meaning.

Vector + keyword hybrid search across your indexed codebase. Every agent on the team can search by meaning, not just string matching.

Activity feed

Real-time visibility.

Real-time visibility into what's happening across the team — task updates, note creation, session activity, and code changes.

Role-based access

Lead, contribute, view.

Invite team members as leads, contributors, or viewers. Control who can create tasks, edit notes, and manage the team.

Chapter III · Up & running

Three steps,
minutes to ship.

i

Request team access

Join the official release waitlist, then create your team and invite developers once access opens.

ii

Connect your CLI

Each developer adds the CodeFire MCP server to their AI coding CLI. One command for Claude Code, a config snippet for Gemini CLI, Codex CLI, or OpenCode.

iii

Start coding together

Every agent on the team now shares tasks, notes, session context, and code search. Context accumulates — sessions get smarter over time.

Give your team shared memory.

Free to start. Team plans available in-app.

Getting Started