The old way to delegate work inside an agent was to nest another mini-agent loop inside one tool call.
MicroClaw is moving past that shape with session-native subagents: asynchronous runs with IDs, lifecycle state, limits, and follow-up controls.
MicroClaw has moved quickly in February, with significant updates across ClawHub integration, voice handling, path compatibility, modularization, web/auth hardening, and release automation.
This post summarizes the direction and outcomes based on the 50 most recent commits on main.
MicroClaw is no longer just a channel bot. In its current form, it is a Rust multi-channel agent runtime with a shared agent engine, provider abstraction, durable session state, and layered memory.
It supports Telegram, Discord, Slack, Feishu/Lark, IRC, and Web through adapters, while keeping one core execution path for reasoning and tool use.
Source code: https://github.com/microclaw/microclaw Quick Start: https://microclaw.org/docs/quickstart
If you are building a personal AI assistant around chat, you usually choose among three distinct paths:
This comparison is updated using publicly available docs/repos as of February 14, 2026.
MicroClaw is a Rust-based AI assistant that treats chat as an execution surface, not only a text interface.
It can run shell and file tools, browse the web, schedule jobs, and persist memory/session state so multi-step work can continue across turns.
