qwen-code is an open-source AI coding agent available through a terminal, editors, desktop app, browser and chat channels. It supports multiple model APIs, with headless execution and SDKs for development automation.
← Back to Category
AI Coding
agentconnect
agentconnect is an open-source platform that brings multiple AI agents into a team's chat, repository, and task workflows. People and agents collaborate in shared conversations, with work triggered by messages, issues, pull requests, webhooks, or schedules.
Directory information is for reference. Check the official site for current features, pricing and availability. Listing does not imply hands-on testing or a purchase recommendation.
About this product
Agents take defined roles, call on one another, retain what they learn, and retrieve reviewed organizational knowledge when needed.
A shared operations interface manages agents, sessions, schedules, tools, knowledge, and daemons.
Key Features
- Run Claude Code, Codex, Grok Build, DeepSeek, Pi, and other ACP-compatible runtimes side by side.
- Connect agents to Slack, Telegram, Discord, Lark, Google Chat, GitHub, GitLab, Gitea, and Linear.
- Configure each agent's runtime, model, workspace, tools, and machine independently.
- Use reusable Jev-powered Decisions to control responses, route conversations, and select runtimes and models for new sessions.
- Equip agents with individual memory and skills, plus reviewed knowledge available on demand.
- Set visibility and access boundaries for agents, sessions, repositories, tools, and calls to other agents.
- Self-host the stack and operate agent execution and workspaces in your own environment.
Use cases
- Route support issues to specialist agents and keep investigation, fixes, and verification in a shared thread.
- Bring engineers from a trusted Slack workspace into a Telegram support conversation and return the resolution to its origin.
- Trigger recurring operations with schedules or webhooks and surface exceptions for human decisions.
- Assign general, architecture, or security reviewers to GitHub pull requests with separate models, tools, and sandbox policies.
Who it is for
- Teams incorporating several AI agents into shared workflows.
- Support and engineering teams coordinating across trusted chat workspaces.
- Software teams customizing code review or maintaining private forks.
Requirements
- The Docker deployment route uses Docker Compose to start the services.
- Kubernetes deployment requires a namespace, secrets, and a deployment values file.
- Source development requires Node >= 26.0.0 and pnpm 11.
Quick Start
- Clone the repository, enter the agentconnect directory, and start the base services with docker compose up -d --pull always.
- Open http://localhost:3000, add a daemon in the console, run its generated command, and create your first agent.
- Open Setup Server at http://localhost:8091 to configure browser authentication, platform apps, and sign-in methods.
- Set deployment images, ports, public URLs, database settings, and bootstrap secrets in compose.env or Helm values.
Limitations and considerations
- The default Docker stack binds only to 127.0.0.1 and uses local no-auth mode for evaluation.
- During a Control Plane outage, established sessions and daemon-local schedules continue, but new assignments and configuration changes await reconnection.
License and links
Code license: Apache-2.0
Privacy and data
- Except for explicitly approved organizational knowledge and bounded skill bundles, the Control Plane stores coordination metadata rather than message bodies, attachments, pending Dream proposals, or ACP session streams.
- The daemon sends model-provider traffic directly; the optional Relay forwards message ingress without durable storage.
Sources
Source review: 2026-11-08
Related Tools
AI Coding
SUZENT is an open-source, local-first personal AI agent that keeps memory in files you control. You can set rules for its actions, choose cloud or local models, and have it follow up on projects while you’re away.
GitHub Copilot is an AI assistant for software development. It can suggest code, explain repositories, edit files, review changes, and work on assigned tasks that developers can inspect as pull requests.
Cursor is a desktop development tool with an AI coding agent. It can read project files, explain a codebase, make requested edits, and support a workflow of reviewing diffs and running project checks.
v0 is Vercel’s AI application builder. It turns natural-language ideas, wireframes, or mockups into web apps that can be refined through previews, code views, and design controls, connected to services, and published.
The former Codeium website now points to Devin Desktop, the renamed Windsurf IDE. It combines a code editor with local and cloud agent management for organizing tasks, reviewing progress and inspecting changes.