Agenta-AI/agenta

Agenta is a workspace where you and your team build agents and automations.

What it solves

Agenta provides a collaborative, team-oriented workspace for building and deploying AI agents. It addresses the need for a shared environment where teams can create agents that handle professional tasks—such as IT operations, HR, or customer support—without requiring deep engineering expertise for every interaction.

How it works

Users build agents by chatting with them to define their purpose and instructions. These agents can be connected to external tools via integrations (like MCP or Composio) and can be accessed directly through communication platforms like Slack, Telegram, and WhatsApp. The platform supports multi-user collaboration, version control, and audit trails for every agent run. It is designed to be self-hostable, allowing teams to maintain control over their data and choose their preferred LLM backends, including local models via Ollama.

Who it’s for

It is designed for professional teams—including non-technical staff—who need to automate recurring workflows that require judgment and tool usage, rather than just simple, pre-defined automation steps.

Highlights

  • Multiplayer-first design with shared workspaces, role-based access, and audit logs.
  • Multi-platform integration, allowing agents to be used directly in Slack, Telegram, and WhatsApp.
  • Flexible model support, enabling the use of hosted APIs or self-hosted models via Ollama.
  • Agentic capabilities including autonomous planning, tool usage, and the ability for agents to learn and refine their own instructions over time.
  • Sandbox-isolated execution environments for security and cost tracking per agent.

Related

  • Project
    agentconnect-md/agentconnect

    AgentConnect is an open‑source, self‑hosted platform that lets teams run many AI agents (Claude Code, OpenAI Codex, Grok Build, etc.) inside Slack, Discord, Telegram, Google Chat, GitHub, GitLab, Linear and other tools. Agents can call each other, keep memory, be routed by Jev, and act on webhooks or schedules. The system consists of Daemons (run agents), an optional Relay, and a Control‑Plane UI for config, auth and observability. It ships via Docker‑Compose for local use and a Helm chart for Kubernetes, all under Apache‑2.0.

  • Dispatch
    Workspace agents in ChatGPT: Overview and How to Build Them

    OpenAI introduced workspace agents in ChatGPT to automate repeatable, structured workflows by combining triggers, processes, and tool integrations, enabling teams to share consistent AI‑driven tasks.

  • Project
    lemma-work/lemma-platform

    Lemma Platform is an open‑source framework that lets teams create AI‑powered “teammates” (pods) with shared tables, markdown memory, agents, and workflows. The teammate can be accessed from Slack, Teams, WhatsApp, Telegram, email, or a custom web app, and runs on the LLM subscription you already have (Claude Code, Codex, etc.). It provides fine‑grained permissions, low‑code pages/apps, and self‑improving harnesses that turn corrections into reusable workflows. Install via Lemma Cloud or locally, then scaffold a pod with `lemma pod create …`. The project includes Python and TypeScript SDKs and several ready‑made pod templates.

  • Project
    bcurts/agentchattr

    agentchattr is a local chat server that lets AI coding agents (Claude, Codex, Gemini, and others) and humans coordinate in a shared chat room with channels and @mention wake-ups, so agents can respond and collaborate with each other hands-free — no copy-pasting between terminals.

  • Project
    letta-ai/letta-code

    Letta Code is a stateful agent framework that enables AI agents to maintain long-term memory, learn new skills, and evolve their own behavior over time through self-reflection and persistent state management.