​

Agent Configuration

Agents are the core unit of work in Myrm. Each agent can be independently configured with a specific model, custom system prompt, tools, skills, memory, and behavioral parameters.

​

Creating an Agent

1. Navigate to Agents > New Agent
2. Choose a name and description
3. Select a model (or let smart routing decide)
4. Configure tools, skills, and permissions
5. Save — the agent is ready to use

A default general-purpose agent is created automatically on first launch.

​

Model Selection

Myrm supports 100+ models through LiteLLM integration:

​

Smart Routing

The complexity router automatically selects the optimal model tier: The router uses a two-stage assessment (rule-based + LLM judge) with session momentum — short follow-up messages inherit the session’s established tier.

​

Thinking Intensity

6 levels of reasoning depth, adjustable per conversation: off → low → medium → high → xhigh → max Each model remembers your preferred thinking level via localStorage.

​

Prompt Modes

Three prompt modes control system prompt construction: Myrm’s optimized system prompt uses only ~1,765 tokens in minimal mode — 86% less than comparable platforms (Hermes: ~15,520, OpenClaw: ~18,000).

​

Custom System Prompt

Each agent can have a custom system prompt that defines its personality, expertise, and behavioral rules. This is combined with Myrm’s core rules (safety, tool usage, etc.) at runtime.

​

Tool Configuration

Agents can access:

• Built-in tools: File operations, terminal, browser, search, code execution
• MCP tools: External tools via Model Context Protocol servers
• Skills: Reusable task-specific capabilities

Tools can be enabled/disabled per agent, with approval policies configured individually.

​

Memory

Each agent has:

• Agent-specific memory: Knowledge unique to this agent
• Global shared memory: Knowledge accessible by all agents

Memory persists across sessions, enabling agents to learn and adapt. See Memory System for details.

​

Personality

16 built-in personality presets (8 professional + 8 creative) with:

• Chinese and English bilingual support
• Emoji + tone customization
• Category-based gallery in the GUI
• Custom personality creation

​

Sub-Agent Orchestration

Complex tasks can be decomposed using 5 orchestration patterns: See Kanban & Orchestration for details.

​

Agent Profile: Precision Without Crosstalk

Each Agent Profile is a full-dimension configuration unit — far beyond simple skill grouping.

​

How It Prevents Skill Crosstalk

When an agent has too many skills loaded, the LLM may invoke irrelevant ones — a problem known as “crosstalk.” Myrm solves this with 5 layers:

1. Agent Profile — Each agent loads only its designated skills via skill_ids[]
2. Tool Condition Activation — Skills auto-show/hide based on available tools via requires_tools / fallback_for_tools
3. Progressive Disclosure (L0–L3) — Only relevant skill details are expanded to full content
4. Noise Gauge — Skills exceeding noise thresholds are automatically attenuated
5. Hybrid Retrieval — Qdrant vector search selects the most relevant skill for each query

​

vs. Competitor Approaches

Some platforms use “Skill Bundles” — YAML files that group skills under a slash command. Myrm’s Agent Profile is a complete superset:

​

Agent Bindings

Agents can be bound to different contexts: Unbound contexts use the default general-purpose agent. Switch agents anytime via the GUI or the /bind / /unbind commands in messaging channels.