recall — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 zippoxer · Codex Skill · ★ 194

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

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

About recall

recall    Search and resume your Claude Code conversations. Also supports Codex, OpenCode and Factory (Droid). Tip: Don't like reading? Tell your agent to use and it'll search for you. Install Homebrew (macOS/Linux): WinGet (Windows): Cargo: Binary: Download from Releases Use Run: That's it. Start typing to search. Enter to jump back in. Ask it to Search for You Simply tell your agent: Example: MCP No MCP required. The CLI fulfills the same purpose. See Ask it to Search for You. Customize recall's resume commands can be configured with environment variables. For example, to resume conve

claudeclaude-aiclaude-codeclaudecodecodexcodex-cliopenai-codexopenai-codex-cli

Quick Facts

Stars194
Forks21
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score66.7258287611252/100
Open Issues10
Last Updated2026-01-14
Created2025-11-27
Platformsclaude-code, cli, codex, rust
Est. Tokens~342k

Compatible Skills

These tools work well together with recall for enhanced workflows:

  • codexia — semantic(0.58)+complementary+rare_topics+similar_pop+shared_platform (64%)
  • talkito — semantic(0.45)+complementary+rare_topics+similar_pop+shared_platform (60%)
  • open-responses-server — semantic(0.45)+complementary+rare_topics+similar_pop+shared_platform (60%)
  • skrills — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)
  • codex-mcp-server — semantic(0.38)+complementary+similar_pop+shared_platform (53%)

recall alternative? Top 6 similar tools

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

  • talkito by robdmac · ⭐ 55

    TalkiTo lets developers interact with AI systems through speech across multiple channels (terminal, API, phone

  • codexia by milisp · ⭐ 913

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

  • code-notify by mylee04 · ⭐ 288

    Cross-platform desktop notifications for Claude Code, Codex, and Gemini CLI. Install via Homebrew, npm, or scr

  • codemap by JordanCoin · ⭐ 688

    a project brain for your AI. Give LLMs instant architectural context without burning tokens

  • ccproxy by starbaser · ⭐ 350

    Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is recall?

recall is Full-text search and resume for Claude/Codex conversations. It is categorized as a Codex Skill with 194 GitHub stars.

What programming language is recall written in?

recall is primarily written in Rust. It covers topics such as claude, claude-ai, claude-code.

How do I install or use recall?

You can find installation instructions and usage details in the recall GitHub repository at github.com/zippoxer/recall. The project has 194 stars and 21 forks, indicating an active community.

What license does recall use?

recall is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to recall?

The top alternatives to recall on Agent Skills Hub include talkito, codexia, code-notify. 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 Codex Skill tools