Ataru — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by lovstudio · Agent Tool · ★ 358

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Ataru safe to install? View the security audit →

About Ataru

Ataru 在本地,快速找回过去 AI 对话中的答案。 Search the memory of your AI work. macOS · Windows · Linux 为什么是 Ataru · 产品路径 · 快速开始 · Agent Skill · 架构 · 开发 · 附录与 FAQ Why Ataru AI 编程过程中,真正有价值的答案经常已经出现过:一次故障排查、一条关键命令、一个架构取舍,或者一段几周前才讨论过的上下文。但这些内容分散在不同 Agent 的本地会话文件里,靠记忆、目录名和人工翻找很难重新定位。 Ataru 把这些已经发生过的对话变成本地可检索的记忆层: 从 Claude、Codex 等本地会话来源建立统一索引。 用关键词、字段、短语或自然语言描述找回相关上下文。 在 、、 三种粒度之间切换。 从命中片段回到原始会话、消息和行号,而不是只展示一段截断摘要。 默认离线运行;语义检索是可选增强,未配置或超时会清晰降级到关键词检索。 Ataru 的目标不是管理正在运行的 Agent,而是让过去的工作重新变得可用。 What it does 新消息写入后自动追赶索引,不需要每次从头扫描

agent-memoryai-memoryai-toolsclaude-codedesktop-appfull-text-searchlocal-firstmemory-retrievalragreact

Quick Facts

Stars358
Forks38
LanguageRust
CategoryAgent Tool
LicenseApache-2.0
Quality Score68.4818011205697/100
Open Issues15
Last Updated2026-08-24
Created2025-12-10
Platformsclaude-code, cli, rust
Est. Tokens~25k

Compatible Skills

These tools work well together with Ataru for enhanced workflows:

  • OpenCovibe — semantic(0.41)+complementary+same_lang+similar_pop+shared_platform (64%)
  • claudette — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)
  • monet — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • claude-code-trace — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
  • Codex-App-Manager — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (60%)

Ataru alternative? Top 6 similar tools

Looking for a Ataru alternative? If you're comparing Ataru with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • lovcode by MarkShawn2020 · ⭐ 303

    A desktop companion app for AI coding tools. Browse Claude Code chat history, manage configurations, commands,

  • Ori-Mnemos by aayoawoyemi · ⭐ 328

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

  • yume by aofp · ⭐ 150

    Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support

  • skills-hub by qufei1993 · ⭐ 1.7k

    A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ gl

  • vestige by samvallad33 · ⭐ 645

    The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h

  • docsagent by docsagent · ⭐ 623

    ⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, A

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is Ataru?

Ataru is High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus a desktop GUI. Tantivy + Jieba keyword search, optional semantic recall, stable Turn/Run/S. It is categorized as a Agent Tool with 358 GitHub stars.

What programming language is Ataru written in?

Ataru is primarily written in Rust. It covers topics such as agent-memory, ai-memory, ai-tools.

How do I install or use Ataru?

You can find installation instructions and usage details in the Ataru GitHub repository at github.com/lovstudio/Ataru. The project has 358 stars and 38 forks, indicating an active community.

What license does Ataru use?

Ataru is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Ataru?

The top alternatives to Ataru on Agent Skills Hub include lovcode, Ori-Mnemos, yume. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools