Agents
2,229Autonomous AI agents that perform tasks independently
A Python SDK to transform Claude response to OpenAI response format
agent-revert
Anshul Basia <anshulbasia@alumni.iitd.ac.in>, Siddharth Goyal <goyal.siddharth22@gmail.com>
A simple decorator for tracking and reverting agent actions
Official library for AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
An Async Generator/Iterator Based FRP-Like Library for Python
Universal interface for AI agents to control ROS robots via natural language
Async routing library with pluggable routing strategies for multi-agent systems
Model-agnostic AI agent orchestration platform with unified interface for OpenAI, Anthropic, Google, xAI, Mistral and more
A governance and policy enforcement layer for AI agents and non-human identities
Safeguards for custom agents.
SPL (Safe Policy Lisp) evaluator for Agent-Safe capability tokens. 150 lines, zero deps, microseconds.
Production-grade safety boundaries for AI agents - policies, tracing, replay, and human-in-the-loop approval
MCP server for AI agent safety — cost guards, injection scanning, decision tracing, agent identity (KYA), and signed receipts
One-line safety middleware for AI agent APIs. Prompt injection scanning, cost budgets, decision audit trails. Works with FastAPI, Flask, and any ASGI/WSGI framework.
Python SDK for the All-in-One Sandbox API, >=1.3.0
Production-grade self-correcting AI agent platform with sandboxed execution
Your personal AI assistant that scouts the web for you — find deals, compare prices, track products, and more.
A lightweight, zero-dependency focused AI Agent Framework for Python.
In-process SDK runtime for agent-search with optional callback-driven Langfuse tracing
Human-agent interaction SDK with accessibility and dialogue management
Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring
Cross-session context persistence and resumption