Search

Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.

Estimate hallucination risk in LLM answers from uncertainty language, unsupported specifics, citations, and context coverage. Python port of @mukundakatta/hallucination-risk-meter.

Detect flaky LLM eval cases across repeated runs. Pass-rate + standard-deviation per case, with per-case severity. Python port of @mukundakatta/eval-flake-detector.

Stable semantic cache keys for LLM requests. Invariant to whitespace, casing, and key ordering; sensitive to model swaps, tool list, and retrieval context. Python port of @mukundakatta/semantic-cache-key.

Typed HTTP client for Engram Cloud — persistent semantic memory for AI agents.

Score (query, document) pairs for vector/RAG poisoning signals: vector-text mismatch, instruction-like payloads, NaN, suspiciously round numbers. Python port of @mukundakatta/vector-poison-score.

Heuristic quality metrics for RAG retrieval and grounded answers. Python port of @mukundakatta/rag-quality-kit.

Stryda governance as a LangGraph node — plug it between the agent LLM and the tool executor.

Local Python access to OAuth-authenticated Codex and Claude Code agents

Drop Stryda governance into a LangChain agent — wrap a BaseTool, or attach a callback to an AgentExecutor.

Estimate LLM request cost and enforce per-request or per-session budgets. Python port of @mukundakatta/llm-cost-guard.

LangChain toolkit for reliable Web3 execution via KeeperHub

Phone numbers for AI agents. Dead simple.

Validate LLM tool-call payloads with small JSON-like contracts. Python port of @mukundakatta/tool-call-contracts.

CLI tool for the Agent Payment API

TypeScript SDK for the x402 gateway: unified JSON-RPC and HTTP APIs with on-chain USDC settlement; typed modules and 402 automation for programmatic clients and AI agents

A protocol-level unified VFS for AI agents with L0/L1/L2 tiered storage.

Terminal UI for Agentic AI!

Small local jailbreak and prompt-injection fixture set for tests. Python port of @mukundakatta/jailbreak-corpus-mini.

Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.