Aura

Aura: Self-hosted AI agent platform in Go featuring temporal graph memory, scheduled jobs, and multi-channel access.

Aura is a self-hosted, multi-user AI agent built in Go that runs on infrastructure you control. It manages tools, document retrieval, temporal graph memory, and scheduled jobs through an embedded web cockpit and command line interface. Users can choose from various model providers including OpenRouter, ChatGPT plans, local llama.cpp servers, or Ollama. The platform features isolated identities, per-identity sandboxes, a streaming agent loop, and mounted Model Context Protocol servers. It suits individuals and teams requiring private, continuous AI assistance with durable memory and autonomous task execution.

Aura at a glance

Best for: Software engineer
Runs on: Web, Linux, macOS, Windows, CLI, self-hosted, open source
Pricing: Open source under MIT license
Released: October 2026
Category: AI agent tool
Website: github.com/chetto1983/aura

Key features

Streaming agent loop with step and time budgets
Deferred tools and toolsearch with MCP support
Graph-native memory in ArcadeDB with temporal paths
Document retrieval with source hashes and citations
Scheduler for reminders and agentjob runs
Per-identity sandbox for secure command execution
Multi-channel access via CLI, Telegram, and web cockpit
Studio for image and video generation and editing

Use it for

Automating scheduled recurring tasks and reminders
Managing documents and retrieving information with citations
Executing terminal and file operations securely
Generating and editing images and videos in a cockpit

Alternatives to Aura

Lightpanda — Lower memory footprint and faster execution than Chrome for automated workflows.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
Ego Lite — Executes browser automation in isolated workspaces using existing logins.
memU — It gives every connected agent a shared and inspectable memory layer.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
EverOS — It enables agents to learn from experience and improves over time without manual coding.
Rinkata — It keeps humans and AI agents aligned on intent as work evolves.
GoClaw — It offers Go-native performance with multi-tenant isolation and 5-layer security.
Cognee — Persistent memory for AI agents using graph, vector, and relational retrieval.
Starnet — Visual agent management with transparent, persistent on-disk logs and state.
FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.

All Aura alternatives