Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By RubiYH
Team memory for humans and their coding agents — opt-in slash commands, Channels delivery, and queue-first conflict coordination.
npx claudepluginhub rubiyh/teamem --plugin teamem<!-- Parent: ../AGENTS.md -->
Fetch the current Teamem briefing (current plan, active claims, recent decisions, active risks, recent progress).
Clear all your pending_edit rows in this space (the auto-skip waiting list). Cleared entries produce no peer event; the only effect is that you stop receiving conflict_resolved alerts for those queued paths.
Set your coordination preference for scope conflicts. `auto-skip` is the only active plugin mode; `auto-discuss` is postponed pending a future negotiator-runtime return.
Record an architectural / process / product / plan decision so teammates see it in their next briefing.
Hand a claimed scope from the user to a specific teammate — release my claim, post a discussion message explaining the handoff, optionally request the teammate to claim it next. Use when the user is stopping work mid-feature and wants someone else to pick it up.
Walk a first-time user through Teamem setup — create or join a space, write credentials, verify the bridge resolves. Use when the user has just installed the plugin and has no `~/.teamem/credentials.json` yet, or when `/teamem-setup` is invoked.
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete developer toolkit for Claude Code
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Tired of merge conflicts on every PR, even with coding agents?
With Teamem, no more "my Claude Code edited that first," "can I edit this file now?", "how did you fix that?", or "wait, are we skipping the user page implementation? I never heard of that!"
Teamem is team memory for humans and their coding agents. It is built to help teammates using Claude Code in the same repository share work context, coordinate code-editing scope, record important decisions, and keep work moving safely without conflicts.
Teamem is useful when:
Teamem requires a shared server. Set that up first. Use a server your team already runs, or clone this repository and self-host it.
With Docker Compose:
git clone https://github.com/RubiYH/teamem.git
cd teamem
cp .env.example .env
# Set TEAMEM_JWT_SECRET in .env. For local testing:
# openssl rand -hex 32
docker compose up --build -d
Or directly with Bun:
git clone https://github.com/RubiYH/teamem.git
cd teamem
bun install
cp .env.example .env
# Set TEAMEM_JWT_SECRET in .env. For local testing:
# openssl rand -hex 32
mkdir -p data
bun run server
After the server is available, install Bun on each teammate machine if it is not already available:
curl -fsSL https://bun.sh/install | bash
Then install the bootstrapper CLI and run the guided Claude Code setup:
npm install -g @rubiyh05/teamem
teamem init
teamem cc
teamem init checks prerequisites, adds or refreshes the teamem-alpha Claude
Code marketplace, installs the teamem@teamem-alpha plugin, runs the space
create or join setup flow, and can install Teamem git hooks. teamem cc
launches Claude Code with the Teamem development channel enabled.
[!WARNING] Teamem currently uses Claude Code's experimental Channels feature for live delivery. Channel behavior may change, be unavailable in some environments, or require fallback to
/teamem-briefing,/teamem-status, and unread notifications.
Inside Claude Code:
/teamem-on
/teamem-on --persist
/teamem-briefing
Use /teamem-on --persist when this repository should default to Teamem being
on in future Claude Code sessions. From there, edit normally. Teamem hooks claim
paths before edits, release on_commit claims after commits, and surface
conflicts or queued work through the plugin.
flowchart LR
subgraph Clients[" "]
direction TB
TA["Teammate A<br/>Claude Code<br/>plugin + bridge + git hooks"]
TB["Teammate B<br/>Claude Code<br/>plugin + bridge + git hooks"]
TC["Teammate C<br/>Claude Code<br/>plugin + bridge + git hooks"]
end
S["Teamem server"]
DB["SQLite event store"]
TA <-->|tools / events| S
TB <-->|tools / events| S
TC <-->|tools / events| S
S <--> DB
style Clients fill:transparent,stroke:transparent
Claude Code plugin + git hooks
-> local Teamem bridge
-> shared Teamem HTTP server
-> SQLite event store and projections
The main tool is teamem.get_briefing, which agents should call at session
start and before non-trivial edits. Write coordination flows through
teamem.claim_scope, teamem.release_scope, decisions, findings, discussions,
and space-management tools.
| Feature | What it does |
|---|---|
| Briefings | Shows the current plan, active claims, recent decisions, risks, and progress. |
| Scope claims | Lets agents reserve files or modules before editing them. |
| Git handoffs | Releases normal claims on commit and pauses or resumes claims on branch checkout. |
| Decisions and gotchas | Captures durable team knowledge through /teamem-decide and /teamem-gotcha. |
| Discussions | Sends direct or broadcast coordination messages with /teamem-discuss. |
| Space rules | Exports team rules into a local TEAMEM.md cache for agent prompts. |