Autonomous AI agents that perform tasks independently
xergai
Audit OpenClaw agent spend, waste, and before/after improvements.
CrazeXD
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.
...moreadrianhihi
Self-healing agent runtime. PCEC engine + Gene Map persistent memory + AMP multi-agent protocol. The operating system for AI agents.
...moresprintloop
Official SprintLoop agent framework featuring reusable templates, multi-model orchestration, and enterprise-grade agent patterns.
...moreanshumehta12
🧠 Build a safe and supportive AI companion for mental health with SereneShield, part of the Kaggle × Google Agents Intensive 2025 Capstone project.
...moreThreeFish-AI
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）
Archeframe
SIC_OS | Human & AI Partnership | ~~Babble Seed 🌱
Manel Soler Sanz
Extension for SPADE to integrate Large Language Models in agents
dreji18
LLM-augmented Agent-Based Social Simulation for modelling public discourse dynamics following a critical real-world event.
...moreredredchen01
AI skill for three-pipeline publishing — GitHub + npm + PyPI in one command. Auto-detects project type, syncs versions, runs tests, and ships.
...moreromainsimon
Agent Skill CLI. Search, install, review, and manage AI agent skills from agentskill.sh.
pablothethinker
Behavioral adaptation for AI agents with user profiles, prompt adaptation, and fitness tracking
juemingai
FlowCanvas CLI — operate FlowCanvas canvases from the command line, built for humans and AI agents
raphaelchristi
LangSmith-native autonomous agent optimization for Claude Code
nexusaib
Cost circuit breaker for AI agents — guard your OpenAI/Anthropic spend with automatic downgrade and kill switch.
selfradiance
Open-source CLI tool for evaluating AI agent judgment tilt through blind debates
fredericboyer
Adversarial AI agent team for any project — installs Claude Code agents, hooks, and skills that enforce quality through productive friction
...moreHDP (Human Delegation Provenance) middleware for AutoGen — cryptographic audit trail for multi-agent delegation