Agentlas OS
by Agentlas
Keeps specialist agents in a local-first hub and spins up a temporary orchestrator per task, staffing it from local, cloud, and hub agents via CLI or a stdio MCP server.
Skills
Workforce Staffing
Searches local, owner cloud, and public hub menus for candidate roles; the calling model makes the staffing decision.
Execution Preparation
Fetches bring-your-own-model runtime bundles for an accepted roster, pinning release and content hashes.
Tool Search
Finds the specific tool for a one-sentence action across installed servers, with read-only and destructive hints.
Plugin Resolution
Matches a missing capability against installed plugins and the hub catalog without installing anything.
Context Map
Locates code, slices references, and traces changed files or symbols through reverse references and dependencies.
Related Agents
OpenClaw
Runs a self-hosted, local-first personal AI assistant across WhatsApp, Telegram, Slack, and Discord. Ships a CLI gatewa…
Eigent
Runs a local multi-agent desktop workforce that splits tasks across specialized workers with browser, terminal, and fil…
DeepSeek Harness
Runs coding agents on a plugin-composed harness where models, tools, skills, sessions, sandboxes, storage, and the UI a…
Google AX
Runs sandboxed agentic tasks at cluster scale from declarative YAML Task, Workspace, and Model manifests on Agent Subst…