Search

OpenAI Agents SDK 的腾讯云 CLS Agent 可观测接入 —— 一行初始化，无需手动埋点

Emit a Testimony Record from a CrewAI crew, so the record can say who approved an action and what was refused.

Emit a Testimony Record from an OpenAI Agents SDK run. The SDK has the approval gate; this makes the record say who opened it.

Autonomous Zero-Vector Memory Framework for AI Agents with Biological REM Consolidation (Gemini, Anthropic, OpenAI-compatible, xAI)

Guardrail extensions for Agentic Driver: advisory review, bounded Herdr communication, and guarded worker lifecycle.

Language-agnostic LLM cost metering via HTTP proxy — track spend per customer and feature

A framework-free LLM engineering toolkit: provider adapters, prompt and context engineering, structured outputs, tools, and a bounded agent loop

Autonomous LLM-free project capability analyzer and interactive knowledge graph synthesizer.

A lightweight, in-process circuit breaker for LLM token and cost budgets. Part of the agentbelt suite.

阅影：把视频变成 AI 能读的文字稿和关键帧，让 Claude Code / Cursor 等编程助手看懂视频

A robust, enterprise-grade, drop-in security & safety guardrail layer for AI agents and LLMs.

Multi-agent cost governance CLI toolkit

Safe privileged execution for pi — sudo_exec tool with masked password prompt and bash-sudo guard

AI-Commander: a ralph-loop AI agent giving LLMs shell access via function calling (TUI + CLI)

Suppress helpdesk welcome emails in response to auto-generated emails

Boot-time integrity check for AI agent memory & convention files — catch silent convention loss, injection dilution, broken rollback anchors.

Pipeline log watcher, VCF/QC interpreter, and multi-agent debate platform for wet-lab NGS teams

n8n community node for creating Allowly authorizations and checking agent actions

Python client and agent-framework tool wrappers for the LinkedIn Toolkit local HTTP API.

Production-grade AI ecosystem — 20+ LLM providers, 7-role agent pipeline, 2000+ tools, advanced RAG, web dashboard, plugin system. More powerful than npmai.