AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
agentconnect
agentconnect logo

agentconnect

Active·★ 1.5k·Apache-2.0·Updated 2026-10-27

AgentConnect tackles the problem that most agents still live in one person's terminal, where teammates cannot see what they do, take over a session or review output. It turns the usual glue, message channels, cron jobs, credential handling and context stitching, into an Apache-2.0 platform that people and multiple agents share.

Agents join the places work already happens: Slack, Telegram, Discord, Lark and Google Chat bots, and repositories, issues and workflows on GitHub, GitLab, Gitea and Linear. Each agent is configured independently with a role, runtime (Claude Code, Codex, Grok Build, DeepSeek, Pi or any ACP-compatible agent), model, workspace, tools and machine; agents can call one another, keep their own memory and skills, and draw on shared reviewed Knowledge. Work can begin from a message, issue, pull request, webhook or schedule.

Reusable Decisions, powered by Jev, decide when agents respond, route conversations to specialists and pick a runtime and model per session. Permissions set who can see each agent, which repositories and tools it may use and which other agents it may call. It self-hosts with Docker Compose for evaluation or a Helm chart for Kubernetes, keeping execution and workspaces in your environment.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-24.

License
Apache-2.0
Latest release
v2.5.2 · 2026-10-22
Last commit
2026-10-24
Contributors
24
Forks
72
Open issues and PRs
43
First published
2026-07-24

Source: GitHub, npm and PyPI public APIs.

#multi-agent#slack#telegram#github#acp#self-hosted#team-collaboration
$ Install
$ git clone https://github.com/agentconnect-md/agentconnect.git && cd agentconnect && docker compose up -d --pull always
↗ Visit site★ GitHub
01

Features

01Bots in Slack, Telegram, Discord, Lark and Google Chat, plus GitHub, GitLab, Gitea and Linear links
02Per-agent runtime, model, workspace, tools and machine; agents can call each other
03Triggers from messages, issues, pull requests, webhooks and schedules
04Per-agent memory and skills plus shared reviewed Knowledge
05Visibility, repository, tool and agent-call permissions; self-host with Docker Compose or Helm
02

Why choose it

+Brings agents into Slack, GitHub, Linear and other tools a team already uses, with work visible in shared threads.
+Each agent's runtime, model, workspace, tools and permissions are configured independently, and agents can call each other.
+Apache-2.0 and self-hostable with Docker Compose or Helm, keeping execution in your own environment.
03

Trade-offs

!A multi-service platform (console, control plane, relay, PostgreSQL) that is real infrastructure to operate.
!The default evaluation stack uses local no-auth mode, so a real deployment needs careful access setup.
!Routing and model selection lean on the Jev/TypeSafe Decisions layer.
04

Maintenance check

ActiveChecked: 2026-10-24
Last commit
2026-10-23
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v2.5.2 (2026-10-22)
Open issues
43
Recent issues with at least one comment
0/3
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 164, 356, 191, 166, 215, 82, 332, 227, 105, 164, 225, 41

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1874 Track sandbox follow-ups: isolation, runtime credential shields, and macOS support10 comments · 2026-09-08
  • #2780 k8s: idle session sandboxes are still never suspended on v2.1.03 comments · 2026-10-03
  • #2730 Source Cache — implementation plan and tracking3 comments · 2026-09-30
  • #145 Track high-priority external-memory provider integrations3 comments · 2026-07-27
  • #2601 XMPP / Jabber adapter similar to Slack / Telegram support2 comments · 2026-09-27

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude Code
Runtime
Verified via docs
Codex
Runtime
Verified via docs
Slack
Bot
Verified via docs
Docker
Docker Compose / Helm
Verified via docs
06

Quick start

1
$ git clone https://github.com/agentconnect-md/agentconnect.git
2
$ cd agentconnect
3
$ docker compose up -d --pull always
07

Use cases

↳Shared issue triage where people and agents work in one thread
↳Custom code review with security or architecture reviewer agents on new PRs
↳Recurring operations started by schedules or webhooks with human decisions visible
08

Alternatives

⚡Top VS:
VSopen-duet★6.2k→VSnanobot★49.5k→VSmultica★54.0k→VSOpenExecutive★5.7k→
open-duet logo
open-duet★ 6.2k
Open-source, self-hosted alternative to Claude Duet: AI coworkers (named agents) with instructions, memory, routines, their own isolated computer, and your approval before they act. Also an alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and ChatGPT agent.
VSCompare→
nanobot logo
nanobot★ 49.5k
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
VSCompare→
multica logo
multica★ 54.0k
Make humans and AI agents work as one team — open-source and self-hostable.
VSCompare→
OpenExecutive logo
OpenExecutive★ 5.7k
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
VSCompare→
switch logo
switch★ 1.8k
Open-source AI teammates in Slack, Teams, Discord, Telegram and Mattermost. Self-host it, with any agent harness and any model.
VSCompare→
commonly logo
commonly★ 1.4k
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
VSCompare→
oto-dock logo
oto-dock★ 193
The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats, on schedules, on the phone and on your own machines.
VSCompare→
nimblebrain logo
nimblebrain★ 28
Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
agentconnect-md /
agentconnect
↗

Self-hosted platform where a team and many agents work together across Slack, GitHub, Linear and more

1.5k72Apache-2.0
Last commit1d ago
StatusActive
CategoryMulti-Agent
Contributors24
Latest releasev2.5.2
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.