Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
7 daysStars68524h gain-Score0.0
Search
Find trending repositories by name or description.
6 results for “tool-call”
RankRepository7 daysStars24h gainScore
[ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings
7 daysStars50924h gain-Score0.0
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com
7 daysStars89524h gain-Score0.0
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
7 daysStars81924h gain-Score0.0
Pi coding-agent extension for pruning tool-call trees
7 daysStars19924h gain-Score0.0
Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
7 daysStars48124h gain+10Score0.0