rara
agent
Uyari
Health Uyari
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 5 GitHub stars
Code Gecti
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
- Permissions — No dangerous permissions requested
Purpose
This project serves as a "kernel" for AI agents. It provides an OS-like architecture to manage an agent's lifecycle, tool orchestration, append-only memory, and multi-channel interfaces like Telegram, Web, and TUI.
Security Assessment
The overall risk is rated as Low. A light scan of 12 files found no dangerous code patterns, hardcoded secrets, or requests for excessive permissions. However, by its very nature as an orchestration framework, the tool processes data, manages tools, and relies on multi-channel network interfaces (such as Telegram and WeChat). While the base code is safe, developers should still audit any external plugins or specific LLM credentials they connect to it.
Quality Assessment
The project is actively maintained, with its most recent push happening today. It uses a standard, permissive open-source license (Apache-2.0). However, it currently suffers from extremely low community visibility, possessing only 5 GitHub stars. Furthermore, the developers explicitly mark the project as a Work In Progress (WIP), warning that APIs and behaviors are unstable and subject to sudden change.
Verdict
Use with caution.
This project serves as a "kernel" for AI agents. It provides an OS-like architecture to manage an agent's lifecycle, tool orchestration, append-only memory, and multi-channel interfaces like Telegram, Web, and TUI.
Security Assessment
The overall risk is rated as Low. A light scan of 12 files found no dangerous code patterns, hardcoded secrets, or requests for excessive permissions. However, by its very nature as an orchestration framework, the tool processes data, manages tools, and relies on multi-channel network interfaces (such as Telegram and WeChat). While the base code is safe, developers should still audit any external plugins or specific LLM credentials they connect to it.
Quality Assessment
The project is actively maintained, with its most recent push happening today. It uses a standard, permissive open-source license (Apache-2.0). However, it currently suffers from extremely low community visibility, possessing only 5 GitHub stars. Furthermore, the developers explicitly mark the project as a Work In Progress (WIP), warning that APIs and behaviors are unstable and subject to sudden change.
Verdict
Use with caution.
Proactive developer agent with tape memory, tool orchestration, and multi-channel interfaces
README.md
rara
your agent, harnessed by kernel
Website · Getting Started · Tape Systems
Work in Progress — APIs, behavior, and module boundaries may change at any time.
Think of an agent as a process. Rara is its kernel.
An operating system doesn't tell a process what to compute — it provides scheduling, memory, I/O, and protection. Rara does the same for agents: lifecycle, memory, tool access, channels, and guardrails. You define the behavior. Rara runs it.
Highlights
- Kernel architecture — OS-inspired event loop: LLM, Tool, Memory, Session, Guard, EventBus
- Tape memory — Append-only fact model with anchors, handoffs, and sessions (tape.systems)
- Proactive — Heartbeat-driven background actions, not just request-response
- Multi-channel — Telegram, Web, TUI, WeChat — one agent, many I/O surfaces
- Skills — Extensible capability system without touching core
- Gateway — Supervisor that boots, restarts, and auto-deploys on git updates — like a bootloader for your agent OS
Inspired By
- Kernel architecture inspired by OpenFang
- Tape memory system from bub — see tape.systems
License
Apache-2.0
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi