Vet a bounty before you point an AI agent at it. Detects prompt-injection aimed at agents and repos that farm free work. Zero dependencies.
-
Updated
Jul 28, 2026 - JavaScript
#
ai-agents
An AI agent is a software system that autonomously perceives its environment, makes decisions, and takes actions to achieve goals — typically powered by large language models (LLMs). Unlike simple chatbots, AI agents can use tools, access external data, execute code, browse the web, and manage multi-step workflows without continuous human guidance.
AI agents range from coding assistants that edit files and run tests (Claude Code, Gemini CLI, Cursor) to browser automation systems (browser-use), computer-use agents (CUA), workflow builders (Activepieces), and multi-agent teams (CrewAI, deer-flow). The ecosystem includes memory layers (mem0), frontend toolkits (CopilotKit), sandboxed execution environments (E2B, Daytona), and full productivity platforms (Cherry Studio, LobeHub).
Here are 110,302 public repositories matching this topic...
-
Updated
Jul 28, 2026
Local stdio MCP server for Stet — draft, send, and measure Slack broadcasts from any MCP-capable agent.
-
Updated
Jul 29, 2026 - TypeScript
See what your agent actually did — drop an AI agent session transcript (JSONL) and get a visual debrief: tool-call timeline, tokens, cost, failures. 100% client-side.
-
Updated
Jul 29, 2026 - TypeScript
Hackathon team repository for Code Minions - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:code-minions]
-
Updated
Jul 28, 2026
Agent skill for the DunSocial CLI — schedule and publish social posts from coding agents
-
Updated
Jul 28, 2026
SuperGoal, SuperDev, and SuperReview: three Codex skills for acceptance-first goals, architecture-aligned AI coding, and main-agent code review with atomic repairs.
multi-agent developer-tools code-review software-architecture codex ai-agents ai-assisted-development ai-code-review ai-coding coding-agent spec-driven-development codex-skill
-
Updated
Jul 28, 2026 - Shell
🐘🐟 大象金魚模式 Agent Skill — 四角色分離與 CUJ 驅動開發，附客觀驗證腳本。工具中立，可移植至 Claude Code / Antigravity / Cursor。
multi-agent software-engineering ai-agents llm agent-skills ai-coding-assistant spec-driven-development
-
Updated
Jul 28, 2026 - Python
Agent-friendly Microsoft Graph requests from the terminal with predictable JSON output.
-
Updated
Jul 28, 2026 - Python
CLI for Foundry IQ: create knowledge sources and knowledge bases on Azure AI Search, test agentic retrieval, and wire them into Microsoft Foundry agents via MCP.
-
Updated
Jul 28, 2026 - Python
EU AI Act compliance runtime for AI agents. FRIA, Annex IV, PMM, QMS, EU-DB, data sheet, incident reporting, AI literacy. Ephemeral compute, signed cards, Art. 50 provenance. DE/EN. Live at agents.renemurrell.de.
-
Updated
Jul 28, 2026 - Python
Local-first session continuity and evidence-linked memory for Codex, Claude Code, and Kimi Code.
-
Updated
Aug 13, 2026
Sistema de gestao de trafego pago e organico em Claude Code — auditoria de conta, plano de midia, monitoramento continuo e publicacao de campanha via MCP
-
Updated
Jul 27, 2026
Four LLM agents — Search, Read, Write, Critique — collaborate end-to-end to turn a topic into a sourced research report. Built with LangChain, Mistral AI, Tavily, and a custom Streamlit frontend.
-
Updated
Jul 27, 2026 - Python
/seoaudit YOURSITE.COM for the last 30 days - The most complete SEO audit for your site. Run this in Claude, Code, Gemini
-
Updated
Jul 28, 2026 - Python
Privacy-first live monitoring and no-progress circuit breakers for Codex and Claude Code.
-
Updated
Jul 31, 2026 - JavaScript
Run parallel Claude Code agents in sandboxed Apple Containers with isolated git worktrees
-
Updated
Jul 28, 2026 - Python
- Followers
- 535 followers
- Website
- github.com/topics/ai-agent