Agent infrastructure
superagent
superagent-ai/superagent
An open-source SDK for AI agent safety that blocks prompt injections, redacts PII and secrets, and scans repositories for threats. Developers embed it via TypeScript, Python, or an MCP server to guard agent deployments.
Topics
Related projects
open-swe11.2kAn open-source asynchronous coding agent that investigates code, implements changes, validates them and delivers pull requests.
ruby_llm4.5kA Ruby AI framework unifying 19 providers with chat, tools, agents, workflows, evaluations, and Rails integration.
any-llm2.2kA Python SDK that lets developers call any LLM provider through one unified, framework-agnostic completion interface.
notte2.1kA full-stack framework for building reliable web automation agents, combining AI-driven browsing, Playwright-compatible scripting, stealth sessions, scraping, and credential vaults.
ClawRouter6.7kAn open-source local LLM router for autonomous agents that picks the cheapest capable model in under a millisecond with wallet or card billing.
axonhub5.4kAn open-source AI gateway that lets developers call more than 100 language models through familiar SDKs, with built-in failover, load balancing, cost controls, and end-to-end tracing.