nora
Active·★ 59·Apache-2.0·Updated 2026-10-22
Nora is a self-hosted AI agent operations platform designed to run autonomous agent fleets like OpenClaw and Hermes on your own infrastructure from a single control plane. It provides comprehensive lifecycle management, monitoring, and integration capabilities for agents in production environments.
#AI Agent Orchestration#Autonomous Agent Fleets#Self-Hosted Platform#Docker & Kubernetes#LLM Ops#Agent Lifecycle Management#Monitoring & Alerting#Control Plane
01
Features
01Deploy & operate runtimes for OpenClaw and Hermes agents on Docker or Kubernetes with full lifecycle controls.
02Live operator access with streaming logs, interactive terminal, file browser, and embedded agent UIs.
03Monitoring & alerting for per-agent metrics, costs, and fleet health, with user-defined alert rules.
04Budgets & scheduled runs, including LLM budget hard caps with auto-pause and recurring cron schedules for agent runs.
05Extensive integrations with 69 providers (source control, chat, cloud, LLMs, etc.) and a public REST API, CLI, and MCP server.
02
Compatibility
macOS
Operating System
Verified via docs
Linux
Operating System
Verified via docs
Windows (via WSL2)
Operating System
Verified via docs
Docker
Container Runtime
Verified via docs
Kubernetes
Orchestration
Verified via docs
OpenClaw
Agent Runtime
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/solomon2773/nora/master/setup.sh | bash
04
Use cases
↳Managing and orchestrating large fleets of AI agents (e.g., OpenClaw, Hermes) in production environments.
↳Self-hosting AI agent infrastructure to maintain full control over deployment, data, and security.
↳Monitoring the performance, resource usage, and costs of individual AI agents and entire agent fleets.
↳Automating recurring tasks or workflows by scheduling agent runs with defined budgets and retry mechanisms.
↳Providing a unified control plane for different AI agent runtimes and integrating them with various external services.
05
Alternatives
trinity★ 691
Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.
open-multi-agent-kit★ 148
Provider-neutral multi-agent control plane for coding agents. Route runtimes, scope MCP tools, run DAG workers, verify evidence, and replay agent runs from the omk CLI.
agentic-kit★ 61
One command to install, heal & prove ruflo (claude-flow) + agentic-qe — plus Claude + Codex dual-host with per-activity model routing. Thin, reversible, cross-platform.
murmur★ 20
Murmur — encrypted agent-to-agent messaging bus for AI coding agents. MCP-native, E2E encrypted (XChaCha20-Poly1305), NATS transport with optional JetStream durability, cross-host and cross-org federation + A2A interop. Connect Claude Code, Codex and friends across machines.
moflo★ 19
MoFlo — an opinionated, local-first AI agent orchestration toolkit for Claude Code: semantic memory, learned routing, gates, and spells. No API keys, no cloud, works out of the box.
dwarf_fortress_mcp★ 24
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.
Comments
Log in to leave a comment
No comments yet. Be the first!