grepai
Semantic Search & Call Graphs for AI Agents (100% Local)
No outside reports on file
Grepai opens your entire codebase to AI agents with semantic understanding, which is powerful but risky if the code contains secrets, false information, or if the AI misinterprets context.
Based on public adoption and transparency signals as of Oct 30, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesReads & writes local foldersREVIEW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (yoanbernabeu/grepai)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/yoanbernabeu/grepai ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-30.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Grepai
Grepai is a tool that searches through your code using natural language (AI-friendly) instead of regular text patterns. It also maps out how functions call each other in your codebase. Everything runs locally on your machine—no cloud uploads.
Who it’s for
Developers and AI agents who need to understand large codebases quickly. Useful for code review, refactoring, and helping AI assistants navigate unfamiliar projects.
Alternatives
- Ripgrep: Fast, traditional regex-based search (no AI, more transparent).
- AST-based tools (e.g., Tree-sitter): Parse code structure precisely without semantic guessing.
- Built-in IDE features: VS Code's symbol search and refactoring tools (already trusted, no new dependencies).
- LLM-powered code analysis (e.g., GitHub Copilot for code understanding): Integrated into familiar tools with clearer permissions.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/yoanbernabeu/grepai (opens external site) for installation and configuration steps specific to your setup.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.9k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Local file access: The tool reads all files in your project directory, so it can see secrets, API keys, or private code you don't intend to expose to AI agents.
- Semantic confusion: It finds code that means similar things, not just exact matches—an AI might misunderstand and apply wrong code patterns to your project.
- AI injection in code: If your codebase contains intentionally misleading comments or strings, an AI using this tool might act on malicious instructions hidden in the code.
- Data exposure through queries: Searching your codebase means descriptions of your functions, logic, and architecture flow through the semantic search—log files or debugging tools could leak these details.
- Supply chain: The tool itself is less mature (0 npm downloads tracked), so security patches may lag behind more popular alternatives.
How to lower the risk
Least-privilege permissions
- Run grepai in a restricted project directory, not your entire system.
- Remove or mask API keys and secrets before using it on sensitive repos.
Network isolation
- Confirm the tool runs fully local; disable any cloud or telemetry options.
- Block outbound network calls if your security setup allows it.
Monitoring
- Log which files and functions the tool accesses.
- Review AI agent outputs that cite code—check for misapplied or wrong suggestions.
Red flags to watch for
- AI agents confidently referencing code in ways that don't match your intent.
- Unexpected dependencies or network requests from the tool.
- Slow performance (may indicate hidden background activity).
Questions
How do I install Grepai?
Grepai does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/yoanbernabeu/grepai.
Are there security reports about Grepai?
No reports found for this package in our research (last checked 2026-10-30). Grepai currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include local file access, semantic confusion, ai injection in code.
Is Grepai actively maintained?
Grepai has 1.9k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/yoanbernabeu/grepai before pinning it in production.
What are alternatives to Grepai?
Notable alternatives to Grepai include Ripgrep (Fast, traditional regex-based search (no AI, more transparent)), AST-based tools, Built-in IDE features (VS Code's symbol search and refactoring tools (already trusted, no new dependencies)), LLM-powered code analysis. You can also compare Grepai side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Grepai? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/yoanbernabeu-grepai)HTML embed:
<a href="https://agentarmorhq.com/skills/yoanbernabeu-grepai"><img src="https://agentarmorhq.com/api/badge/yoanbernabeu-grepai" alt="AgentArmorHQ Risk Grade for Grepai" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "yoanbernabeu-grepai"Share with your security lead
Need sign-off to use grepai? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: grepai
- **Listing URL:** https://agentarmorhq.com/skills/yoanbernabeu-grepai
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.9k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** Reads & writes local folders
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (yoanbernabeu/grepai)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/yoanbernabeu/grepai
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 30, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- yoanbernabeu
- Source code
- github.com/yoanbernabeu/grepai
- Est. context load
- ~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
- Popularity
- 1.9k GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-30
Community
Discussions for Grepai
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude