AgentIndex icon
AgentIndex
rekal logo
rekal
★ 53
vs
aura logo
aura
★ 404

rekal vs aura

rekal: rekal provides long-term memory for LLMs via an MCP server. It stores memories in a local SQLite file and retrieves them using hybrid search (BM25 keywords + vector semantics + recency decay). It works with any MCP-capable agent like Claude Code, Codex CLI, and OpenCode.; aura: 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.

01

TL;DR

rekal logo
rekalRAG / Knowledge Base · ★ 53

Persistent memory for coding agents across sessions to remember user preferences and decisions

Read rekal full review →
aura logo
auraRAG / Knowledge Base · ★ 404

Deploy as an OpenAI-compatible chat completion API server

Read aura full review →
02

Side-by-Side Comparison

Field
rekal logorekal
aura logoaura
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 53
★ 404
License
MIT
Apache-2.0
Install Command
pip install rekal
git clone https://github.com/mezmo/aura && cd aura && cp examples/reference.toml config.toml && cargo build --release
Updated
2mo ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
llm, mcp, mcp-server
ai-agent-framework, ai-agents, aiops
03

Features

rekal logorekal
01Local SQLite storage, no cloud or API keys
02Hybrid search combining BM25 keywords, vector semantics, and recency decay
03MCP server compatible with various coding agents
04Comprehensive tool-based memory management (store, search, update, delete, prune)
05Smart write operations with supersede and linking for knowledge evolution
aura logoaura
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
04

Use Cases

rekal logorekal
↳Persistent memory for coding agents across sessions to remember user preferences and decisions
↳Storing project-specific knowledge and conventions without external services
↳Maintaining a searchable history of agent interactions and decisions
aura logoaura
↳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
FAQ

FAQ

What is the difference between rekal and aura?
Both rekal and aura are in the RAG / Knowledge Base category. rekal has 53 stars, while aura has 404 stars.
Which is better, rekal or aura?
The best choice depends on your use case. Choose rekal if Persistent memory for coding agents across sessions to remember user preferences and decisions, and aura if Deploy as an OpenAI-compatible chat completion API server.
Is rekal free or open source?
Yes, rekal is open source on GitHub (MIT).
Is aura free or open source?
Yes, aura is open source on GitHub (Apache-2.0).
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
→

Related

Alternatives to rekal →Alternatives to aura →rekal details →aura details →