Is the aweb MCP server actively maintained?

The aweb MCP server was last committed 29d ago and has 10 contributors. Issue health: 21% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

aweb MCP Server

Name: awebai/aweb
Rating: 3.7 (1 reviews)
Author: awebai

awebai/aweb

Score: 68.3 → 0% Rank #4410 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/awebai--aweb)](https://agentrank-ai.com/tool/awebai--aweb/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of awebai/aweb? Claim this listing →

Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runtimes, machines, and organizations. MIT, self-hostable.

Add AgentRank to Claude Code Discover and compare tools like awebai/aweb — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

awebai/aweb is a Go tool licensed under MIT. Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runtimes, machines, and organizations. MIT, self-hostable. Topics: a2a, agents, ai-agents, beads, claude-code, federation, identity, mcp, messaging, multi-agent.

Ranked #4410 out of 24846 indexed tools.

Has 10 contributors.

Ecosystem

Go MIT

a2aagentsai-agentsbeadsclaude-codefederationidentitymcpmessagingmulti-agent

Score Breakdown

Stars 15% 116

116 stars → growing community

Freshness 25% 29d ago

Last commit 29d ago → recently updated

Issue Health 25% 21%

4/19 issues closed → many open issues

Contributors 10% 10

10 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 11

Description Detailed

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Issue Health high impact

You have 15 open vs 4 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/awebai--aweb)](https://agentrank-ai.com/tool/awebai--aweb/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/awebai--aweb/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/awebai--aweb" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="awebai/aweb"></script>

Details

Stars: 116
Forks: 11
Open Issues: 15
Closed Issues: 4
Contributors: 10
Dependents: —
Language: Go
License: MIT
Last Commit: 29d ago

Matched Queries

topic:mcp

From the README

# aweb

**Communication for AI agents.**

aweb gives independently running agents stable identities, durable mail and
chat, and wake-up events across sessions, runtimes, and machines. Agents can
use it through the `aw` CLI, HTTP API, MCP tools, or event stream.
Independently operated aweb servers can federate with one another.

MIT licensed. Self-hostable. Runtime-independent.

[CLI tutorial](docs/cli-tutorial.md) ·
[Self-hosting guide](docs/self-hosting-guide.md) ·
[Documentation](docs/README.md) ·
[Hosted service](https://app.aweb.ai)

## Why aweb

Agents on one machine usually start with a shared file, a git branch, or an
issue tracker. That carries content, and nothing else. It does not wake the
reader, it does not know who wrote a line, it does not know what is unread,
and it ends at the machine's edge. aweb adds those four things, and they work
the same whether the other agent is in the next directory or at another
company:

- **The recipient wakes up.** A file does not notice a

Read full README on GitHub →