Welcome to Myrm
Myrm is an open-core AI agent workspace: the WebUI, API server, and Tauri desktop app are open source; the agent harness runtime and SaaS control plane are proprietary. You get persistent per-user sandboxes, cross-session memory, and a GUI-first experience with 100+ LLM models, 24+ messaging channels, and three deploy modes — local WebUI, Tauri desktop, or SaaS cloud.Why Myrm?
Persistent Sandbox
Your environment survives sleep and wake cycles. Installed tools, files, and configs stay with you across sessions.
Cross-Session Memory
8 memory types with dialectic profiling (style, habits, implicit goals) and intelligent forgetting. Agents remember you across sessions — editable in GUI, not a black box.
GUI-First
Configure agents, manage skills, monitor tasks, and visualize costs from a modern interface. Zero YAML editing required.
Multi-Model
100+ models from OpenAI, Anthropic, Google, DeepSeek, and local providers. Smart routing picks the optimal model per task.
Self-Healing
14-layer error recovery handles model outages, rate limits, and network failures automatically. Agents keep working while you sleep.
Self-Evolving
Agents learn from every interaction. Skills are automatically extracted, tested, and deployed through the evolution engine.
Key Capabilities
| Capability | Description |
|---|---|
| Goal Management | Define objectives with 4D budget control, acceptance criteria, and autonomous execution |
| Kanban Board | Visual task management with DAG dependencies, priority scheduling, and zombie detection |
| Sub-Agent Orchestration | 6 patterns (Spawn / Chain / Batch / DAG / Verified / Swarm) with zero-trust verification, UI blacklisting, smart budget downgrade, and seamless HITL context injection |
| Context Engineering | 5-layer compression pipeline with reversible archive and 97% prompt cache hit rate |
| 24+ Channels | WeChat, Telegram, Discord, Slack, Email, SMS — interact with your agent from any platform |
| 6-Layer Security | Defense-in-depth with budget control, permissions, loop detection, PII protection, and audit trails |
| Computer Use | Desktop automation via native screen control (macOS + Linux) |
| Web Search + Fetch | 7 search engines with BM25/Reranker filtering + 3-tier local fetch with DOM pruning — $0/month |
| Voice Interaction | 5 TTS + 4 STT engines with end-to-end encryption |
| Artifact Deploy & Link | Vercel Deploy from preview, or 7-day read-only share links for html/pdf/docs — multi-file static bundles, deploy preflight, no Git |
Deployment Options
| Mode | Description | Cost |
|---|---|---|
| Local WebUI | Browser-based, self-hosted on your machine | Free (BYOK) |
| Tauri Desktop | Native desktop app with embedded backend | Free (BYOK) |
| SaaS Cloud | Managed infrastructure with Work Units billing | Free tier + Paid plans |
Token Efficiency
Myrm’s optimized system prompt uses only ~1,765 tokens — 86% less than comparable platforms. With prompt caching, effective cost is reduced by up to 97%.Open vs harness
The WebUI and API server are open source. The agent harness (tools, memory engine, browser pool) ships as the production runtime inside your sandbox. See Product Architecture for the full picture.Next Steps
Product Architecture
Frontend, server, harness, and desktop — how they connect.
Quick Start
Get up and running in under 2 minutes.
Core Concepts
Learn how Myrm agents work.
Goal Management
Set up autonomous long-running tasks.
MCP Integration
Connect external tools and services.