AgentConnect launches open-source multi-agent collaboration platform
New CapabilitiesSelf-hosted, Apache 2.0 platform brings Claude Code, Codex, and other agents into existing team tools
Yesterday: Public launch announcedNew here? Follow stories to track developments over time. Create a free account to get updates when stories you care about change.
Overview
Updated 49 minutes agoAI agents have mostly been single-user tools: one developer, one terminal, one session. AgentConnect launched August 26 as an open-source platform for running multiple agents together inside team channels already open in Slack, Discord, or GitHub.
The platform connects any Agent Client Protocol-compatible agent, including Anthropic's Claude Code, OpenAI's Codex, and xAI's Grok Build. Each agent gets a distinct role with its own model, memory, tools, and permissions. Work can begin from a message, pull request, webhook, or schedule, and agents can call one another.
The launch is a direct challenge to proprietary multi-agent platforms such as Anthropic's Claude Tag. AgentConnect is Apache 2.0 licensed and self-hostable, so teams keep agent execution on their own infrastructure instead of routing it through a vendor.
Why it matters
If self-hosted agent orchestration catches on, teams can run multi-agent workflows inside their own infrastructure instead of routing work through a single AI vendor's platform.
Questions about this story
Free account needed to ask — your question is kept and asked for you right after sign-up. Answers are public.
No questions yet — be the first to ask.
Key Indicators
Voices
Curated perspectives — historical figures and your fellow readers.
Play
Exploring all sides of a story is often best achieved with Play.
Higher or Lower
A number from this story, against one from elsewhere in the news — guess which is bigger, then keep the chain going. 5 rounds, 3 strikes; a miss costs a strike and resets your streak.
Keyboard: ↓/L lower · ↑/H higher
0 points — sign up to put that on the leaderboard.
Connections
Sixteen names from the news. Find the four hidden groups of four. Four mistakes max.
Sign up to keep a daily streak — a new puzzle lands every day.
Exit debate?
Your progress in this debate will be lost.
- 1 Two AI personas square off on this story.
- 2 You predict who'll win each round — correct picks earn XP.
- 3 One crossfire question is yours to fire. Pick it carefully.
Couldn't generate a topic
Select Your Champions
Choose one persona for each side of the debate
DEBATE TOPIC
Choose personas with different perspectives for a more dynamic debate.
Select debater for this side:
No debate personas available right now.
Select debater for this side:
No debate personas available right now.
Who's Got This Round?
Make your prediction before the referee scores
The referee scores both sides on
Round Results
Set the Crossfire
Pick the question both personas must answer in the final round
Debate Oracle! You called every round!
Sharp Instincts! You know your debaters!
The Coin Flip Strategist! Perfectly balanced!
The Contrarian! Bold predictions!
Inverse Genius! Try betting the opposite next time!
XP Breakdown
Prediction History
People Involved
Organizations Involved
An open-source, Apache 2.0 licensed platform for running multiple AI agents inside team collaboration tools.
AI research company behind Claude Code and the Claude Tag multi-agent platform.
Makes Codex, an agent runtime that can run inside AgentConnect deployments.
Timeline
July 2026 August 2026
-
Public launch announced
Latest AnnouncementAgentConnect announces the platform as an open-source, self-hosted alternative to Claude Tag, with press release and documentation.
-
Repository created on GitHub
LaunchAgentConnect opens its GitHub repository under the Apache 2.0 license with initial platform code.
Historical Context
3 moments from history that rhyme with this story — and how they unfolded.
Red Hat (1993-2019)
Red Hat built an enterprise business around freely licensed Linux software, becoming the first open-source company to pass $1 billion in annual revenue. IBM acquired it in 2019 for $34 billion.
Red Hat proved open-source infrastructure could be sold to the Fortune 500 at scale.
The acquisition showed open-source layers become valuable consolidation targets once they demonstrate traction.
A possible endgame for AgentConnect: if self-hosted agent orchestration catches on, the project or its team becomes an acquisition target for a cloud provider or AI vendor.
Kubernetes (2014)
Google open-sourced Kubernetes in June 2014, a system for orchestrating containerized applications. It competed with Docker Swarm and Apache Mesos, and within a few years became the default orchestration layer for cloud-native software.
Kubernetes won the container-orchestration war; Docker Swarm and Mesos faded from the market.
An open-source project governed by a foundation now runs much of the world's production software.
AgentConnect makes a similar bet: that the orchestration layer for AI agents can be an open-source, community-run project rather than a proprietary vendor product.
Model Context Protocol (2024)
Anthropic released MCP, an open protocol for connecting AI models to external tools and data. OpenAI, Google, and Microsoft adopted it within months, making an Anthropic-invented standard the industry norm.
Developer tooling and agent frameworks standardized on MCP for tool connections.
The protocol layer for agent-tool integration is open, even as the models themselves are proprietary.
AgentConnect bets the same pattern repeats for ACP, the agent-host protocol it uses, which would let one platform run any vendor's agent.
