Channel-Agnostic Core
One shared agent loop drives Telegram, Discord, Slack, Feishu, and Web adapters.
Architecture
Channel-agnostic core with adapter-based delivery
Memory
AGENTS.md + SQLite structured memory with observability
Execution
Tool loop, native and ACP sub-agents, scheduling, and background tasks
Extensibility
Skills catalog plus MCP tool federation
Why teams pick MicroClaw
A runtime-centered stack that keeps your logic stable while channels, models, and tools evolve.
Tool-Using Agent Loop
The model can chain tools over multiple steps until the task reaches end_turn.
Native + ACP Subagents
Run delegated work inside MicroClaw or route it to external ACP workers with durable run state.
Memory With Quality Gates
File memory + structured SQLite memory with reflector extraction and dedupe lifecycle.
MCP + Skills Federation
Attach external tool servers and domain-specific skills without rewriting the core loop.
Operational Visibility
Usage, memory observability, and config self-check endpoints help teams track quality and drift.
Scheduler + Background Tasks
Cron and one-shot tasks run through the same runtime, not a separate automation stack.
Runtime architecture at a glance
The same engine powers every conversation, regardless of where users talk to your agent.
Ingest
Channel adapters normalize inbound events into a single runtime format.
Assemble Context
Session state, AGENTS.md memory, structured memory, and active skills are injected.
Reason + Tool Calls
Provider layer streams responses, reasoning output, and tool calls in a controlled loop.
Persist + Reflect
Conversations, sessions, and memories are persisted; reflector updates durable facts.
Deliver
Responses are split by channel limits and emitted with consistent delivery semantics.
Use MicroClaw for real workloads
From solo operators to platform teams, one core runtime can cover multiple paths.
Personal Infra Agent
Run one assistant across your chats with memory, scheduling, and shell/file tooling.
Read implementation detailsTeam Operations Bot
Use permission-aware tools and session history to support recurring internal workflows.
Read implementation detailsProduct Prototyping Runtime
Ship new channels and tools quickly on a shared Rust core instead of fragmented bots.
Read implementation detailsShip a production-grade Rust agent stack.
Follow Quickstart for setup, then move into tools, permissions, memory, and channel deployment.