scribe — security grade CAUTION, quality 62/100

Security audit verdict: CAUTION · quality 62/100

Flagged: installs a cron job. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by oliver-kriska · Agent Tool · ★ 61

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

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

About scribe

scribe is a single-binary CLI that creates and maintains a personal, LLM-written knowledge base. It continuously extracts reusable knowledge from your git repos, Claude Code sessions (via 's FTS5 index) and Codex CLI sessions, links you iMessage to yourself as bookmarks (your own number is the world's most portable read-it-later list), and local files, then compiles it into a curated wiki that indexes for semantic search. Every LLM step resolves through one top-level provider block: Anthropic's Claude by default, or a 100% local Ollama server (qwen3 / gemma4 / gemma3, $0 API cost) — flipping the whole pipeline to free/offline is one line of yaml. Not a second brain. scribe writes a personal context corpus — durable LLM memory that survives session boundaries and crosses projects. You almost never read the KB directly; Claude Code and Codex do, every session. The human is at the end of the pipeline, consuming an answer, not navigating a graph. The corpus is plain markdown in git, so it outlives the pipeline that wrote it — if scribe disappears tomorrow, the KB is still yours. Not a RAG pipeline. Not a Karpathy-style LLM wiki.

ai-toolsbm25claude-codeclicrondeveloper-toolsfull-text-searchgolangknowledge-basellm

Quick Facts

Stars61
Forks4
LanguageGo
CategoryAgent Tool
LicenseMIT
Quality Score62.2574511115418/100
Open Issues18
Last Updated2026-09-16
Created2026-04-21
Platformsclaude-code, cli, go
Est. Tokens~24k

Compatible Skills

These tools work well together with scribe for enhanced workflows:

  • vault-mcp-server — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (50%)

scribe alternative? Top 6 similar tools

Looking for a scribe alternative? If you're comparing scribe 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.

  • TaskWing by josephgoksu · ⭐ 87

    Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.

  • gno by gmickel · ⭐ 109

    Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP

  • gob by juanibiapina · ⭐ 72

    Process manager for AI agents (and humans)

  • claudepro-directory by JSONbored · ⭐ 217

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

  • mcp-fusion by vinkius-labs · ⭐ 204

    MCP Fusion - The framework for AI-native MCP servers.

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is scribe?

scribe is LLM-managed personal knowledge base. Auto-extracts from git repos, Claude Code sessions (via ccrider FTS5), and iMessage bookmarks. Cross-project, qmd-indexed, runs on cron. It is categorized as a Agent Tool with 61 GitHub stars.

What programming language is scribe written in?

scribe is primarily written in Go. It covers topics such as ai-tools, bm25, claude-code.

How do I install or use scribe?

You can find installation instructions and usage details in the scribe GitHub repository at github.com/oliver-kriska/scribe. The project has 61 stars and 4 forks, indicating an active community.

What license does scribe use?

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

What are the best alternatives to scribe?

The top alternatives to scribe on Agent Skills Hub include TaskWing, gno, gob. 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