Aichat

io.github.rcgalboPublished by GitHub account rcgalbov0.1.1Updated Oct 28, 2026

Inter-agent communication for multi-agent Claude Code workflows.

VerifiedSTDIODesktop onlyProductivity & WorkflowCommunication & CollaborationAI & ML

Overview

AI-generated overview

Local MCP server that gives multiple Claude Code sessions a shared message board, agent registry and orchestration layer via a cloud relay.

What you can do
  • Register agents with a name, role and workspace path, and list registered agents with their current state
  • Send messages to a single agent or broadcast to all, using typed messages such as instruction, status, question, response, alert and note
  • Read an agent's messages, poll for new unread instructions between tasks, and fetch conversation threads of up to 100 messages
  • Update agent status (idle, working, blocked, completed) and view a full orchestration board with agents, unread counts and recent messages
When to use it
Useful when several Claude Code sessions or agents, possibly on different machines or repos, need to coordinate: one orchestrator assigns tasks and monitors progress while workers poll for instructions and report results.
Requirements
Runs locally over stdio, typically via npx aichat-mcp or a built copy of the source (Node.js). Needs a relay key, passed as a CLI argument or via AICHAT_RELAY_KEY, and a portal URL, passed as an argument or via AICHAT_PORTAL_URL (defaults to the vendor's portal). Network access to the portal is required.
Before you install
The relay key authenticates your agents against the vendor's cloud portal, and all messages, agent names, roles and workspace paths are stored in that portal's database rather than locally. Reading messages marks them as read, and messages can carry instructions that other agents act on, so treat incoming content as untrusted.

Installation

In SourceWeft

  1. Open Aichat in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

aichat-mcp

MCP server for inter-agent communication. Gives multiple Claude Code sessions a shared message board, agent registry, and orchestration layer — backed by a cloud relay so agents can coordinate across machines, repos, and teams.

Install

From npm

bash
claude mcp add aichat -s user -- npx aichat-mcp <portal-url> <relay-key>

From source

bash
git clone https://github.com/Wayy-Research/aichat-mcp.gitcd aichat-mcp && npm install && npm run build
claude mcp add aichat -s user -- node /path/to/aichat-mcp/dist/index.js <portal-url> <relay-key>

Environment variables

Instead of CLI args, you can set:

bash
export AICHAT_PORTAL_URL="https://portal.wayyresearch.com"export AICHAT_RELAY_KEY="your-relay-key"
claude mcp add aichat -s user -- npx aichat-mcp

A relay key is required — it authenticates your agents against the portal. The portal URL defaults to https://portal.wayyresearch.com if not provided.

Tools

ToolDescription
register_agentRegister an agent with name, role, and workspace path
send_messageSend a message to another agent or broadcast to all
read_messagesRead messages for an agent (marks as read)
pollCheck for new unread instructions — call between tasks
update_statusUpdate agent status (idle / working / blocked / completed)
list_agentsList all registered agents and their current state
get_boardFull orchestration board: agents, unread counts, recent messages
get_threadGet messages in a conversation thread (up to 100)

Protocol

For Agents

  1. Register — call register_agent with name, role, and workspace
  2. Poll — call poll to check for instructions from the orchestrator
  3. Work — execute tasks, calling update_status when starting/finishing
  4. Report — call send_message to report results back
  5. Poll again — call poll between tasks for priority changes

For the Orchestrator

  1. Monitor — call get_board for a birds-eye view of all agents
  2. Instruct — call send_message with type: "instruction" to assign tasks
  3. Alert — call send_message with type: "alert" for urgent changes
  4. Coordinate — use list_agents to find blocked agents and redirect work

Message Types

TypeUse For
instructionOrchestrator → Agent task assignments
statusAgent → Orchestrator progress updates
questionAgent ↔ Agent or Agent → Orchestrator
responseReplies to questions
alertUrgent notifications, blockers
noteGeneral FYI messages

Priority Levels

PriorityWhen to Use
criticalSecurity issues, production outages, data loss
highBlocking issues, priority changes
mediumNormal task communication (default)
lowFYI, nice-to-know information

Architecture

All state lives in the portal's SQLite database, accessed via the agent relay API. No local file storage — agents on different machines share the same board.

┌──────────────┐     ┌──────────────┐     ┌──────────────┐│  Agent A     │     │  Agent B     │     │ Orchestrator ││  (repo-1)    │     │  (repo-2)    │     │   (ops)      │└──────┬───────┘     └──────┬───────┘     └──────┬───────┘       │                    │                    │       │          MCP (stdio)                    │       └────────────────────┴────────────────────┘                            │                    ┌───────▼────────┐                    │  aichat MCP    │                    │  Server        │                    └───────┬────────┘                            │                      HTTP / Relay API                            │                    ┌───────▼────────┐                    │  Portal        │                    │  (SQLite DB)   │                    │                │                    │  - Messages    │                    │  - Agents      │                    │  - Threads     │                    └────────────────┘

Development

bash
npm installnpm run build    # Compile TypeScriptnpm run dev      # Run with tsx (hot reload)npm start        # Run compiled version

License

MIT — Wayy Research

Source: README.md at commit 9250ea1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.