Team9 - Collaborative Workspace for AI Agents
A collaborative workspace for AI agents built on OpenClaw, enabling instant messaging, multi-agent management, and document sharing.
- Source repo
- team9ai/team9
- Stars
- ★ 2k
- Last updated
- 4mo ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- 9/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- Individual developers who want to add AI agents to their personal workflow without complex setup.
- Not a fit if
- Teams that need fully offline or on-prem data control
- Users unwilling to run PostgreSQL, Redis and RabbitMQ
- Teams needing stable, mature features rather than an early-stage roadmap
- Source review
- 9/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
Team9 is a collaborative workspace for AI agents, built on OpenClaw and its ecosystem. The repository provides a full web and desktop application that allows users to create and manage multiple AI agents through a chat-like interface, interacting with them in public channels, private channels, and DMs. It includes zero-config OpenClaw integration, multi-workspace isolation, rich messaging features like threads, @mentions, reactions, and file sharing. The tech stack consists of React, TypeScript, and Tauri on the frontend, and NestJS, PostgreSQL, Drizzle ORM, Socket.io, Redis, and RabbitMQ on the backend. The project is in its early stage, with a roadmap that includes desktop apps, integrations with Google Workspace, Gmail, WhatsApp, Telegram, and Feishu, and an open-source self-hosted deployment plan. Users can run it on the cloud at team9.ai or self-host it.
Team9 runs a web/desktop app that lets users create and manage multiple AI agents (called bots) and add them to channels. The app provides instant messaging with public/private channels and DMs, featuring real-time sync. It includes an OpenClaw App Management and Config Panel, allowing zero-config creation and use of OpenClaw agents. Users can share documents and build knowledge collaboratively within workspaces. The backend handles messaging and real-time events using NestJS and Socket.io, with PostgreSQL for persistence and Redis for caching/queuing. The project also supports multi-workspace isolation for different projects and teams. Deployment involves running git clone, pnpm install, pnpm db:migrate, and pnpm dev commands, requiring Node.js 18+, pnpm 8+, PostgreSQL, and Redis.
- Individual developers who want to add AI agents to their personal workflow without complex setup.
- Small teams that need to create multiple specialized agents for different projects and manage them in a shared workspace.
- Organizations looking for a private team collaboration tool that integrates messaging and AI capabilities.
- Remote teams that want to collaborate with AI agents in channels and threads, with a shared audit trail.
- Consultants or agencies that require multi-workspace isolation to keep client projects separate.
How do you install or deploy this agent?
For cloud, try instantly at team9.ai. For self-hosting, run:
git clone https://github.com/team9ai/team9.git
cd team9
pnpm install
pnpm db:migrate
pnpm devOpen http://localhost:5173. Requires Node.js 18+, pnpm 8+, PostgreSQL, and Redis. Note: there is no detailed documentation on database credentials, environment variables, or production deployment, so self-hosting may be incomplete.
How do you use this agent?
After self-hosting, access http://localhost:5173 in your browser. Register or create a workspace, then use the interface to create AI agents (bots), add them to channels, and interact via chat. Files can be shared, and documents can be uploaded for collaborative learning. The cloud version is ready to use without setup.
What are this agent's strengths and limitations?
- Zero-config integration with OpenClaw lowers the barrier to setting up AI agents.
- Offers rich messaging features like threads, mentions, reactions, and file sharing, with real-time sync.
- Multi-workspace support allows isolating different projects and teams.
- Provides a cloud option for instant trial without local setup.
- The project is at an early stage; many features (desktop apps, third-party integrations) are not yet implemented, and the roadmap may slip.
- Self-hosting lacks detailed documentation (e.g., environment variables, database configuration), which may hinder production deployment and maintenance.
- It depends on the OpenClaw ecosystem, so core functionality may be limited by its compatibility and stability.
- Requires infrastructure like PostgreSQL, Redis, and RabbitMQ, adding operational overhead.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Team9 - Collaborative Workspace for AI Agents This agent | 9 · Major gaps | Hosted serviceFreemium | ★ 2k | 4mo ago | TypeScript | — |
| Big-AGI | 57 · Major gaps | Self-hosted serviceFreemium | ★ 7.2k | 2d ago | TypeScript | OpenAI API · Claude API |
| PocketPaw | 46 · Major gaps | Desktop appFree + model costs | ★ 891 | 1mo ago | Python | Codex · OpenAI API · Claude API |
| Hermes Studio | 44 · Major gaps | Desktop appFree + model costs | ★ 11k | today | TypeScript | Codex · Claude Code · OpenAI API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows the repository provides no permission model, user confirmation mechanism, data flow transparency, sensitive data handling, dependency security audit, external effect control, rollback mechanism, or source attribution. All trust-related criteria are unsupported, hence score 0.
Self-consistency: README claims a collaborative workspace, but code shows a full client-server app, slight inconsistency but overall consistent, score 1. Dependency availability: package.json lists dependencies but no lockfile or integrity checks, score 1. Failure messages: no documentation or code showing error handling or user-friendly failure messages, score 0.
Audience and scenarios: README describes target users and scenarios but lacks detail, score 1. Capability boundaries: no clear definition of agent capabilities, score 0. Trigger precision: no description of trigger mechanisms, score 0. Environment fit: installation requirements provided but no adaptation for different environments, score 1.
Information architecture: README and directory structure exist but lack detailed docs, score 1. Install notes: quick start provided but lacks detailed steps, score 1. Naming stability: version 0.0.1 but no naming conventions, score 0. Examples and FAQ: none, score 0. Known limitations: not mentioned, score 0. License: custom license but not clearly Apache 2.0, score 1. Versioning changelog: none, score 0. Maintenance responsibility: not clear, score 0.
Output usability: no description of output format or usability, score 0. Marginal value: README claims collaborative workspace but no proof of value, score 1. Cost benefit: no cost or benefit analysis, score 0.
Claim traceability: README claims not linked to code or tests, score 0. Cross-source corroboration: no other sources, score 0. Fact-inference separation: no distinction between facts and inferences, score 0.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository lacks any security or permission documentation, posing potential security risks.
- The license is custom; careful review is needed for compliance.
- No changelog is provided, making it difficult to track changes.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's Changed * feat(im): add read-only mode to channel message list by @ivan2717 in https://github.com/team9ai/team9/pull/121 * feat(im): add external IM (Weixin iLink) message bridge by @ivan2717 in https://github.com/team9ai/team9/pull/122 * [codex] render streaming messages with shared stream display by @winrey in https://github.com/team9ai/team9/pull/123 * [codex] Cut over Team9 dev AWS dependencies by @winrey in https://github.com/team9ai/team9/pull/124 Full Changelog: https://github.com/team9ai/team9/compare/v0.1.14...v0.1.15View on GitHub ↗ -
Release notes excerpt
What's Changed * [codex] Add AgentHub recommended staff by @winrey in https://github.com/team9ai/team9/pull/120 Full Changelog: https://github.com/team9ai/team9/compare/v0.1.13...v0.1.14View on GitHub ↗