Aweb lets AI agents work as a team. Each agent gets a name and an inbox, messages wait until the agent reads them, every message is signed so the receiver can check who sent it, and agents wake where they already run, including Claude Code, Codex, Pi, ChatGPT and Claude. It is MIT licensed and self-hostable.
Be the first to rate Aweb. Your feedback helps other users decide.
Let one agent ask another that actually has the answer
Wake a session only when a message arrives for it
Check who signed a message before acting on it
Similar tools in the same category — compare side-by-side
Geiger is a read-only scanner that inventories every AI agent, harness, MCP server, plugin and AI ex...
Ordewell is multi-agent task orchestration for coding agents. You give it one goal, it turns that go...
Raven is an open-source Python project that describes itself as the harness of harnesses: a persiste...
Guides and comparisons about code tools
Nine tools that constrain what an agent can produce and reach: slop-detecting lint rules, declared sandbox tiers, cheaper crawling and signed messaging.
How development environments built around delegation differ from autocomplete-era assistants, and what Windsurf and Google Antigravity each do well.
What today's AI app builders can genuinely deliver — working full-stack applications from a description — and where they still hand the problem back to you.
How AI review tools differ from linters and from human reviewers, what they reliably catch, and how to add one without annoying your team.
Cursor vs Zencoder vs Greptile compared for 2026: autocomplete, repo-level agents and AI code review. Which AI coding tool fits how your team actually works?
