AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
RAG / Knowledge Base/
aura
aura logo

aura

Active·★ 404·Apache-2.0·Updated 2026-10-27

Aura is a production-ready framework for building AI agents using TOML configuration. It supports multi-provider LLM, dynamic MCP tool discovery, RAG pipelines, and serves an OpenAI-compatible API. The framework is built on Rig.rs with enhancements for reliability and operability.

aura sits in the RAG / Knowledge Base category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Declarative agent composition via TOML with multi-provider LLM support and multi-agent serving. A representative use case is Deploy as an OpenAI-compatible chat completion API server. The listed license is Apache-2.0. GitHub stars are currently 404. Relevant tags include ai-agent-framework, ai-agents.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#ai-agent-framework#ai-agents#aiops#devops#harness#llm#llmops#mcp
$ Install
$ git clone https://github.com/mezmo/aura && cd aura && cp examples/reference.toml config.toml && cargo build --release
↗ Visit site★ GitHub
01

Features

01Declarative agent composition via TOML with multi-provider LLM support and multi-agent serving
02Dynamic MCP tool discovery across HTTP, SSE, and STDIO transports
03Automatic schema sanitization for OpenAI function-calling compatibility
04RAG pipeline integration with in-memory and external vector stores
05Embeddable Rust core independent from configuration layer
02

Why choose it

+Declarative agent composition via TOML with multi-provider LLM support and multi-agent serving
+Dynamic MCP tool discovery across HTTP, SSE, and STDIO transports
+Deploy as an OpenAI-compatible chat completion API server
+Supports 3 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Linux
Linux
Verified via docs
macOS
macOS
Verified via docs
Windows
Windows
Verified via docs
05

Quick start

1
$ git clone https://github.com/mezmo/aura
2
$ cd aura
3
$ cp examples/reference.toml config.toml
4
$ cargo build --release
06

Use cases

↳Deploy as an OpenAI-compatible chat completion API server
↳Serve multiple agents via configuration directory
↳Embed Aura core in custom Rust applications for agent functionality
07

Alternatives

⚡Top VS:
VSpost-cortex★20→VSjdocmunch-mcp★207→VSmcp-ts-core★152→VScompass★73→
post-cortex logo
post-cortex★ 20
Post-Cortex provides durable memory infrastructure with automatic knowledge graph construction, intelligent entity extraction, and semantic search powered by local transformer models.
VSCompare→
jdocmunch-mcp logo
jdocmunch-mcp★ 207
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
VSCompare→
mcp-ts-core logo
mcp-ts-core★ 152
TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.
VSCompare→
compass logo
compass★ 73
Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it discoverable and queryable for both humans and AI agents.
VSCompare→
rekal logo
rekal★ 53
Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
VSCompare→
synaptic-memory logo
synaptic-memory★ 33
Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.
VSCompare→
shellguard logo
shellguard★ 24
MCP server that gives LLM agents read-only shell access over SSH
VSCompare→
ContextGraph logo
ContextGraph★ 22
Shared memory bus for MCP-compatible agents with permissions, subscriptions, and optional payments.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
mezmo /
aura
↗

A production-ready framework for composing AI agents from declarative TOML configuration, with MCP tool integration, RAG pipelines, and an OpenAI-compatible web API.

404Apache-2.0
Last commit1d ago
StatusActive
CategoryRAG / Knowledge Base
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.