FreeLLMagentes.chat launches open-source self-hosted Slack alternative with AI agent support
agentes.chat delivers a free, self-hosted Slack alternative where AI agents powered by Claude, ChatGPT, Gemini or Grok collaborate in channels, with budgeted model calls and approval workflows.
agentes.chat is an open‑source project on GitHub that provides a self‑hosted Slack‑style workspace where people and AI agents converse in shared channels and direct messages.
Agents can run on Claude, OpenAI’s ChatGPT/Codex, Google Gemini, Grok or any OpenRouter model, each with its own role, monthly budget and approval process, plus a personal computer and browser.
Features include threaded channels, memory that records decisions, scheduled routines, file storage in Postgres or S3‑compatible buckets, and MCP connectors to services such as Linear, Notion, Stripe, Google Drive and many more.
The repository records 7,967 commits and is released under the AGPL‑3.0 license, allowing free self‑hosting or use of the hosted cloud service at agentes.chat.
Ce que cela signifie pour vous
Because the platform accepts any model key, users can connect top‑ranking free models like Kimi K3 or Kimi K3.1 Pro, enabling low‑cost AI assistance without a paid subscription.
Sur FreeLLMArena
From our rankings on 12 Nov 2026, based on Arena's blind votes:
- Kimi K3.1 Pro (Max): #2 among free chat models
- Kimi K3 (Max): #1 among free chat models
Sources
- agentes-chat/agentes-chat: Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP too, GitHub trending, 9 Nov 2026
Rédigé automatiquement à partir des sources ci‑dessus, puis vérifié par notre code : chaque nombre et chaque nom doivent y figurer, et aucune phrase ne doit copier une source. Une erreur ? Signalez‑la.
Quelle IA pouvez‑vous utiliser gratuitement aujourd’hui ?
Tous les modèles IA gratuits, classés par votes humains anonymes, avec la mémoire et la vitesse dont ils ont besoin sur votre propre GPU.