Auth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
Agents
Designing, evaluating, and shipping autonomous AI agents.
7685 posts
AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, and safety gates. TypeScript. Zero config.
Give your AI agent a real browser identity. MCP server with persistent personas, anti-detection browser, and credential vault.
Trust infrastructure for AI agents — constitution enforcement and cryptographic receipts. Python SDK.
Get better Estonian writing results from your AI agent. Offline MCP server (no third-party calls) wrapping EstNLTK + EKI Reeglid. 21 NLP too...
Agent-facing Bicameral MCP tools for ingest, preflight, binding, and review commands
We’re build a swarm of agents for all data tasks. That anyone can use for free, open-source community version.
Open-source CLI scanner for agentic AI components such as skills, MCP servers, system prompts
自然 ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph an...
Resources for connecting agents to the right tools, APIs, and documents with context-aware toolset selection, efficient token usage, and bui...
Multi-agent orchestrator with cyclic personal-to-org memory · Apache 2.0 · Python 3.11+
Production-ready ServiceNow MCP server — 450+ tools + 26 AI capabilities, multi-transport (stdio/SSE/HTTP), A2A protocol, dynamic schema dis...