lakeraai / chainguard
Guard your LangChain applications against prompt injection with Lakera ChainGuard.
☆20Updated 3 weeks ago
Alternatives and similar repositories for chainguard:
Users that are interested in chainguard are comparing it to the libraries listed below
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- A benchmark for prompt injection detection systems.☆99Updated last month
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆50Updated 3 weeks ago
- Official repo for Customized but Compromised: Assessing Prompt Injection Risks in User-Designed GPTs☆24Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆116Updated 2 weeks ago
- LLM Security Platform.☆10Updated 5 months ago
- Red-Teaming Language Models with DSPy☆178Updated last month
- Supply chain security for ML☆133Updated this week
- ☆71Updated 5 months ago
- Security and compliance proxy for LLM APIs☆46Updated last year
- Every practical and proposed defense against prompt injection.☆413Updated last month
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆109Updated last year
- Lakera - ChatGPT Data Leak Protection☆22Updated 9 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆352Updated last year
- Project LLM Verification Standard☆41Updated 11 months ago
- Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.☆62Updated 5 months ago
- Modular, open source LLMOps stack that separates concerns: LiteLLM unifies LLM APIs, manages routing and cost controls, and ensures high-…☆92Updated last month
- A better way of testing, inspecting, and analyzing AI Agent traces.☆30Updated this week
- LLM model runway server☆13Updated last year
- A community wiki for all things AI/ML bill of materials (MLBOM, AIBOM) and transparency into AI/ML models.☆39Updated 4 months ago
- Secure Jupyter Notebooks and Experimentation Environment☆72Updated last month
- BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps☆57Updated last year
- Python client for PromptWatch.io - LLM tracking platform☆28Updated 10 months ago
- Enrich data by prompting LLMs☆10Updated 3 months ago
- [Corca / ML] Automatically solved Gandalf AI with LLM☆48Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆289Updated 2 months ago
- Dropbox LLM Security research code and results☆221Updated 10 months ago
- Tool suite for secure and robust agent development☆165Updated last week
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆369Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆63Updated 11 months ago