Our agents already live in the terminal. What changes in Slack?

Visibility: teammates can see what an agent is doing, take over a session, and review its output in the conversation where the work happens, instead of context living on one person's laptop.

Does every reply need Jev, or can I use it selectively?

Selectively. Jev powers reusable Decisions — when agents respond, conversation routing, runtime and model choice per session — while channels, memory, skills, and scheduling work without it.

How do I stop an agent from acting on its own?

Gate behavior with Decisions: configure when agents respond and which runtime, model, tools, workspace, and sandbox policies each session gets, and keep the human decision visible in the shared thread.

Can agents from different runtimes work together?

Yes. Claude Code, Codex, Grok Build, DeepSeek, Pi, and any ACP-compatible runtime run side by side, can call on one another, and swapping one does not rebuild the workflow around it.

What license is it and where does it run?

Apache-2.0 and open source. It links agents to bots in Slack, Telegram, Discord, Lark, and Google Chat, or to repositories, issues, and workflows on GitHub, GitLab, Gitea, and Linear.

What are reusable Decisions?

Decisions are powered by Jev and let you decide when agents respond, route new conversations to specialist agents, and choose a runtime and model for each new session.

How do knowledge and memory work?

Each agent gets its own memory and skills, and reviewed Knowledge can be published for every agent to find on demand, so context carries forward instead of staying on one laptop.

CommunityJev Agents & MCP

Agentconnect

Open-source platform that puts ACP-compatible agents such as Claude Code, Codex, and Pi inside the team's Slack, Telegram, Discord, and GitHub workflows, with reusable Jev decisions for routing, response gating, and reviewer selection.

See highlights

Open github.com

Stars: 1.5k
Language: TypeScript
License: APACHE-2.0
Published by: Community
Author: agentconnect-md
Last verified: Oct 2026

agentconnect-md/agentconnect

Organization repository on GitHub

View on GitHub

The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, they work alongside your team, learning as they go.

Forks: 65
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

The open-source, multi-agent alternative to Claude Tag. @ any agent. Wherever work happens, your agents work alongside your team and each other, learning as they go. FROM                                  WITH                                  …    AND   

Quoted from the project's README. Read the full README.

Tagscommunity jevbest

Works forJev for Classification Jev for Tool calling Jev for Routing

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Reusable Decisions powered by Jev decide when agents respond, route conversations to specialists, and pick the runtime and model per session.
Code review mode uses Jev to select reviewers and the runtime and model for each review session.
Each agent keeps its own memory and skills and can call other agents; work starts from messages, issues, PRs, webhooks, or schedules.
Support triage runs in shared threads and private forks stay current as agents assess upstream changes. Apache-2.0 licensed.

Watch out

A broad platform, not a Jev-only tool: most features work without Jev. Copy reviewed against the repo README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

488

A coding agent built on pi that hands its non-code decisions — what enters the context, whether a command is safe, whether the work is done — to a small judge model at 35 decision points per turn.

Jev Agents & MCP#community#jevbest

Community

qybaihe/muTypeScript

duet-agent

Agent harness for work that outlives one chat, with resumable turns, routed state machines, and observational memory across sessions and processes.