7 posts tagged with "Runtime"

The previous release (Hermes Catch-up) filled in the runtime's plumbing: a user model, a skill lifecycle, prompt-cache economics, checkpoints. This one is about something harder to measure and easier to feel — making MicroClaw behave like a person, and specifically like a very capable person who happens to have a team behind them.

The thesis, lifted from the design docs that drove this release: "being human" is two layers, and the magic is in the contrast between them.

On the surface they chat with you casually, lightly, in short replies. But the moment you need something real, they quietly pull in a mathematician, an illustrator, a researcher — several lines running at once — and come back with "done, here's the answer."

MicroClaw used to be robotic on both layers: it dumped long answers up top, and although it could run sub-agents concurrently, it worked in silence until everything was finished. This release reworks both — and gates every outward-facing, proactive behavior behind a default-off switch.

The Hermes Catch-up release is MicroClaw's largest single-branch update so far: 37 commits, 8400 lines, 53 files. The headline number is misleading, though — what matters is which layers of the agent runtime got filled in.

The inspiration is hermes-agent v0.10.0. Hermes runs on Python; several of its design decisions land more naturally on a Rust + SQLite stack: FTS5 ships with bundled SQLite, cargo audit / cargo deny lock dependency posture at compile time, and the artifact pattern (large tool result on disk, fetch slices by id) costs almost nothing in a single-binary deploy.

So this isn't a port — it's a re-application of patterns hermes already validated, drawn against MicroClaw's engineering boundaries.

The latest maturity hardening pass in MicroClaw is not a flashy new model integration or another channel adapter. It is the kind of release work that makes the next ten releases safer: dependency audit gates, operator-visible risk checks, explicit support policy, and stricter release verification.

For an agent runtime, that matters. If your bot can execute tools, store memory, expose Web APIs, and run background work, "it compiles" is not enough. You also need repeatable checks around security posture, release shape, and operator safety defaults.

MicroClaw now includes a dedicated HTTP hook trigger surface for external automation.

This closes a common integration gap: webhook systems and scripts can trigger agent runs directly, without relying on chat-native ingress or static scheduler-only flows.

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.

Telegram forum groups are useful until every thread shares one agent memory buffer.

MicroClaw's Telegram topic mode fixes that by routing each forum topic as its own chat session, while still replying inside the original Telegram thread.

This weekly update summarizes what changed in MicroClaw during February 20, 2026 to February 26, 2026.

The pace was high: channel coverage expanded, runtime reliability was hardened, and setup/config workflows became much better for multi-account bot operations.