Search

NotiLens callback handler for LangChain — automatic run tracking, token metrics, and error alerting

Define and control AI agents in markdown with full prompt transparency, persistent memory, and integrated tools via the Claude Agent SDK.

Python agent harness — 5 LLM providers, 7 real tools, sub-agent spawning, hooks, skills"

A governed coding agent CLI built on Claude Code. Runs inside an isolated Docker container with operator-controlled policy baked into the image, per-tool-call audit logging, and QA gates enforced before every session is accepted.

AI Agent Orchestration + GUI Automation Framework - Claude Code's Tengu brain + OpenClaw's device hands = autonomous computer-use agents

Build Your Own AI Hedge Fund from Scratch. 6 agents, 10 chapters, ~650 lines of Python. No frameworks.

Provide a terminal-based AI tool to perform controlled, measurable engineering tasks directly on real codebases.

A system-level defense framework for AI agents that intercepts and blocks indirect prompt injection attacks using strict instruction provenance and dynamic policy enforcement.

Production-grade multi-agent orchestration framework. Model-agnostic, supports team collaboration, task scheduling, and inter-agent communication.

Audit OpenClaw agent spend, waste, and before/after improvements.

Framework-agnostic observability and debugging for AI agents. See every step, tool call, model call, token usage, cost, and decision in a clean local dashboard.

Self-healing agent runtime. PCEC engine + Gene Map persistent memory + AMP multi-agent protocol. The operating system for AI agents.

Official SprintLoop agent framework featuring reusable templates, multi-model orchestration, and enterprise-grade agent patterns.

🧠 Build a safe and supportive AI companion for mental health with SereneShield, part of the Kaggle × Google Agents Intensive 2025 Capstone project.

面向 Claude Code 的多后端高可用透明智能代理（支持 Claude Plans、GitHub Copilot、Google Antigravity、ZAI/GLM）

SIC_OS | Human & AI Partnership | ~~Babble Seed 🌱

Extension for SPADE to integrate Large Language Models in agents

LLM-augmented Agent-Based Social Simulation for modelling public discourse dynamics following a critical real-world event.

AI skill for three-pipeline publishing — GitHub + npm + PyPI in one command. Auto-detects project type, syncs versions, runs tests, and ships.

Sync AI agent skills from Git repositories to Claude, Codex, Kiro, and Cursor