AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Pro Services › agentes-chat
✦ Free & open sourcePro Services

agentes-chat

An open-source, self-hosted Slack alternative where teams and AI agents collaborate.

Self-hosted team chat built for AI agents

Run Claude, ChatGPT, Gemini, and Grok alongside your team in shared channels, DMs, and automated routines.

Free forever · open source · AGPL-3.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
7.3
ZEKAI
Self-hosted AI agent workspace
Free & open source · Pro Services
Ease of setup4
Usefulness9
Maintenance9.5
Community6.5
★ 1,597
GITHUB
Nov 2026
UPDATED
AGPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

agentes-chat is a self-hosted workspace combining human team communication with autonomous AI agents. Professional services teams can deploy it via Docker and Postgres to let agents execute tasks, browse the web, and manage MCP tools directly in chat.

Runs on
Cross-platform
Hosting
Cloud or self-host
Languages
TypeScript
License
AGPL-3.0

What it is

The platform integrates AI agents as full workspace members rather than sidebar bots, allowing them to read channels, answer when prompted, and execute code or browser tasks. It routes unmentioned messages using code or smaller models, and requires human approval for sensitive actions like merges or deploys.

Who it's for

It suits tech-forward professional services teams wanting to embed autonomous agents into daily operations with strict budget controls and human oversight. It does not suit organizations looking for a zero-setup SaaS tool or those unwilling to manage a self-hosted Linux server and database.

Key features

Unified Team and Agent Chat

Agents participate directly in channels and DMs, reading context and handing work back and forth with people.

Built-In Approval Workflows

Sensitive actions like code merges and deployments pause for human sign-off directly inside the chat interface.

Agent Computers and Browsers

Agents utilize dedicated execution environments and live-view browsers to complete real web tasks.

Model and Budget Flexibility

Configure Claude, ChatGPT, Gemini, Grok, or OpenRouter models with strict monthly spending limits per agent.

MCP Tool Connectors

Connect official MCP servers or use Composio integrations to link external tools like GitHub, Jira, and Google Drive.

How to start

Up and running in 3 steps

1
Run the installation script on your Linux server to set up Docker and private HTTPS via Tailscale
2
Configure your organization's AI model API keys and connect your database
3
Invite team members, provision agents with specific roles and budgets, and link your MCP tools
Real talk

Our honest verdict

What's great

  • Treats AI agents as first-class workspace participants with assigned roles and individual budgets
  • Provides real-time visibility into agent browser automation and command execution
  • Supports importing agents and skills from alternative tools like Grok Bot and ChatGPT dots
  • Includes multi-platform native apps for web, desktop, and mobile devices

Where it falls short

  • Requires managing a self-hosted Linux server, Docker Compose, and a PostgreSQL database
  • API model keys and compute runners must be provisioned and funded separately by your organization
  • Desktop and mobile client builds are currently in beta status
Cost

Pricing & license

The software is free and open-source under its AGPL-3.0 license when self-hosted on your own infrastructure. A paid hosted cloud option is also available from the creators, and running it yourself incurs standard server and AI model API costs.

Paid work

Open remote AI-training roles

879 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: agentes-chat for Pro Services
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure agentes-chat for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I use my own AI model API keys?

Yes, each organization adds its own model keys for Claude, OpenAI, Gemini, DeepSeek, and other supported providers directly in the application settings.

How are sensitive agent actions handled?

Actions marked sensitive—such as code deployments or data modifications—generate an interactive approval card in the chat that requires explicit sign-off from an admin or the agent's owner.

Is there a hosted cloud option available?

Yes, agentes.chat offers a paid hosted cloud option alongside the free, self-hosted AGPL-3.0 codebase.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Pro Services — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google