Tag
Explore by tags
Runs AI-generated code in secure, isolated cloud sandboxes you control via Python or JavaScript SDKs; supports self-hosting (Terraform) and AWS/GCP, enabling agents and code-interpreting workflows to execute real-world tools safely.
Declarative CLI and library to evaluate and red-team LLM apps: run test cases against prompts and models, compare providers side-by-side, and scan for jailbreaks, prompt injection, and data leaks — with CI/CD and pull-request code scanning built in.
Probes LLMs for failure modes — prompt injection, jailbreaks, data leakage, toxicity, hallucination — the way nmap scans a network. Ships 20+ attack probes that run against Hugging Face, OpenAI, Bedrock, Cohere, or any REST endpoint.
Runs LLM-generated Python in a Rust sandbox that starts in tens of microseconds (~60µs), with no container overhead. Filesystem, network, and environment access are blocked, and state serializes for pause/resume with per-run resource limits.
Detects file content types with a compact deep‑learning model that runs in milliseconds on a single CPU. Trained on ~100M samples across 200+ content types; offered as a Rust CLI plus Python, JS, and Go bindings for large‑scale security and file‑routing use.
Runs reproducible evaluations of large language models through a Python API with built-in solvers, scorers, and model-graded grading. Ships 200+ ready-to-run evals spanning capability and safety testing, and connects to most major model providers.
Packs a Git repository into a single AI-friendly file for easy ingestion by LLMs. Offers per-file and total token counts, optional Tree-sitter compression, secret scanning, and multiple interfaces (CLI, web, browser extension, Docker, MCP) for AI-driven code review and analysis.
Extends the Wand (WeMod) desktop client’s local configuration and UI with a remote web panel, injected renderer scripts, automated compatibility patches and client-side AI features; runs entirely locally and does not publish official executables (build your own).
Runs penetration tests autonomously: a multi-agent system (researcher, developer, executor) plans attacks, writes and runs exploit code, and chains 20+ tools like nmap, metasploit and sqlmap in isolated Docker containers — for authorized testing only.
Runs a self-hosted meeting bot and transcription API that joins Google Meet, Teams and Zoom and streams speaker-attributed transcripts in real time. Compiles meetings into a git-backed Markdown workspace and runs sandboxed agents on your infrastructure; Apache-2.0 and air-gap capable.
Lets AI agents like Claude Desktop and Cursor explore schemas and run SQL across Postgres, MySQL, MariaDB, SQL Server, and SQLite through one MCP server. A read-only mode stops the agent mutating data; no per-database drivers to wire up.