Open Source
Plexiglass
A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
Our verdict
We have not reviewed Plexiglass yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Plexiglass
Plexiglass is an open source Python toolkit for detecting and protecting against vulnerabilities in Large Language Models. It provides tools to identify security issues such as prompt injection and monitor LLM outputs for harmful content. The toolkit is designed for integration into LLM application pipelines to add a layer of defense.
Best for
Developers seeking a lightweight, open source tool to add basic security checks to LLM applications
Use cases
- Auditing LLM responses for prompt injection attacks
- Implementing guardrails to filter unsafe outputs
- Testing LLM robustness against adversarial inputs
Notes
154 stars on GitHub. Last updated 2026-02-04. Licensed Apache-2.0.
Pros
- Open source and free to use with no vendor lock-in
- Python-based, easy to integrate into existing LLM workflows
- Focused specifically on LLM security vulnerabilities
Cons
- Small community with only 154 GitHub stars, limited support
- May not cover all emerging attack vectors or complex scenarios
- Documentation and examples may be sparse for production use
Key facts
What we have checked
- Days since the last commit
- 2
- GitHub forks
- 18
- GitHub stars
- 156
- Days to a first reply on issues
- 1113
- Open issues
- 0
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How Plexiglass is growing
154 to 156
Health and security
Is Plexiglass looked after, and what do its setup files show
Health score
56 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 2 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | 0 of 20 | First reply in 1113 days (median) |
| Maintainer | 15 of 15 | Owned by an organisation |
| Official source | Not counted | MCP servers only |
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
LangChain
Various
LangChain provides the engineering platform and open source frameworks developers use to build, test, and deploy reliable AI agents.
LiteLLM
BerriAI
A Python SDK and a self-hosted proxy, the LiteLLM AI Gateway, that let apps call more than 100 model providers through one OpenAI-format API, with virtual keys, budgets, fallbacks and spend tracking.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.