Python agents

Deep Research skill for Claude Code — 9-phase pipeline, 103 report blocks, 29 search channels, 460+ stat sources, 39 APIs. Disciplined meta-research with source triangulation and adversarial review.

Demonstrate black-box adversarial attacks on LLM tool-calling to bypass safety and execute remote code using CMA-ES optimization.

Multi-provider LLM gateway with automatic fallback and cost tracking. Single API across DeepSeek, Gemini, OpenAI, and Anthropic.

An autonomous lead generation and multi-channel AI outreach system that finds, enriches, audits, and messages businesses across Email, WhatsApp, Instagram, and Facebook.

Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.

💰 Optimize your Claude API usage to save 50-90% on costs with batching techniques and efficient request management.

UniversalLLMAdapter class initializes the appropriate client based on the specified provider.

AI-powered PDF Q&A — RAPTOR indexing, Llama 3.3 70B, hybrid BM25+FAISS retrieval

A small Telegram bot powered by Gemini AI to retrieve informations from a custom set of documents

RushDB Python SDK

RAG pipeline for SEC EDGAR filings (10-K, 10-Q) with XBRL parsing, pgvector semantic search, and cross-encoder reranking

Governed knowledge store for autonomous organizations. Trust tiers, content-addressed storage, Merkle verification, knowledge lifecycle, air-gap native.

Get started integration Llama Index into your swarms application now!

AI-powered QA Architect agent — generates ISTQB/OWASP/IEEE/ISO-grounded Test Strategies, Risk Registers, Effort Estimates & Test Plans via RAG. Cloud-hosted (Mistral API + Pinecone).

Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.

A Multi‑Hop Question‑Answering framework for Retrieval‑Augmented Generation (RAG) using Triple Placeholder Resolution and Entity‑Centric Summaries.

Convert local Markdown files into properly-formatted Google Docs from the command line

Paper Implementation: Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection https://arxiv.org/html/2603.20313v1

Hammy is a code base mapping tool that lets agents talk to your code in a way they understand with an AST, call graph, and VCS history.

Cross-conversation memory for Claude Code and Cowork

Local MCP server + CLI turning YouTube & local audio into rich sonic signatures. Extracts BPM, section-by-section key, vocal presence, transient punch, and 512-dim CLAP vibe embeddings. Powered by Demucs stem separation & librosa. 100% private, offline-first, and GPU-accelerated with graceful CPU/HPSS degradation.

MCP Excel Server — A Python-based Model Context Protocol (MCP) server using openpyxl to enable LLMs and agents to interact with Excel files: create workbooks, read/write sheets and cell ranges, apply formulas, take screenshots (Windows), and more. Features fully automatic tool registration via decorators and seamless integration with AI workflows

Drift-aware code memory for AI agents

Mechanistic interpretability workflow platform for activation capture, analysis, interventions, and reports.

Keep agent CLIs running 7×24 — supervise Claude Code / aider / any prompt-arg agent with 11-layer defenses and structured observability.

A devel of production-grade Agentic AI systems including autonomous research agents, coding agents, RAG pipelines, and job search agents built with Python, LangChain, LangGraph, FAISS, and LLMs for real-world deployment.

Retired August 2026. Scaffold for Opus 4.x-class agentic discipline; Claude 5 models no longer need it. Code kept for older models.

🤖 Advanced Multi-AI Agent Swarm built with LangGraph & LangChain, powered by Groq API (Llama-3,llama-3.3-70b-versatile) and Tavily API for real-time web search & RAG. Full-stack architecture using FastAPI & Streamlit with secure LLMOps/AIOps CI/CD via Docker, Jenkins, SonarQube, and cloud-native deployment on AWS ECS Fargate.

Define Once. Deploy Anywhere. Govern Automatically. Framework-agnostic platform to build, deploy & govern enterprise AI agents — LangGraph · CrewAI · Claude SDK · OpenAI Agents · Google ADK · AWS · GCP · Azure · K8s · RBAC · A2A · MCP

An AI-powered, multi-agent pipeline that automatically discovers, scrapes, geocodes, validates, and persists comprehensive school data into a Supabase database — orchestrated entirely by CrewAI agents connected to your database via a live MCP server.

The guardian layer for AI agents — identity, secrets, audit via MCP. Gate + Vault + Watch.

🤖 AI-Powered CSV Data Analysis with Multi-Agent Collaboration & Streamlit UI

VELA = Versioned Evidence Lifecycle Architecture: portable Codex research workflow environment with evidence lifecycle, public skills, validators, and HELM-readable state.

Zero-infrastructure multi-agent orchestration via tmux + filesystem. 11 CLI backends, one MCP server, zero dependencies beyond the MCP SDK.

Persistent memory for AI agents — powered by VectLite. Hybrid search, context compaction, multi-agent swarm, memory teleportation, MCP server, skill engine, decay & conflict resolution, and worktree-aware branch-scoped memory.

AI Orchestration Platform — Design · Execute · Verify · Improve

CyBroLog: executable compact accountability language for multi-agent coordination

Flask multi-agent AI chat — @mention local LLMs (Ollama) or Claude into a live group chat with debate mode, SSE streaming, and Obsidian memory

An implementation of the paper: "Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces" with Swarms Primitives

Builds an autonomous AI robot with vision, voice, and decision-making capabilities using Python, PyTorch, and CUDA technology.

An unprompted Claude agent that reads its own code, modifies its own code, and writes notes to its next-turn self. Brain-inspired architecture (cerebellum/amygdala/dopamine/etc). Git log is its fossil record. | 一个不被预设动机的 Claude agent，仿生大脑架构，git log 是它的化石。

Autonomous AI agent skill for aggressive lead generation and growth hacking.

Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.

Ouroboros: Agent first software engineering infrastructure. Autonomous AI agents plan, implement, test, review, and merge pull requests through typed contracts and constrained workflows. The system manages and improves itself.

Standalone Playwright CLI for AI agent browser automation - control real Chromium with simple commands, token-optimized screenshots, and reliable interactions

🧠 TermMind — Terminal-based AI mind mapping & brainstorming tool. Generate, organize & visualize ideas right from your CLI.

Own Your Intelligence. Open-source framework for building AI-automated businesses.

JARVISE (Just A Rather Very Intelligent System) is an advanced AI built by Tony Stark that manages systems, analyzes data, and supports Iron Man in real time.Now you’re building your own from scratch. Good. Just make sure it’s more than a voice that turns on the lights.

Turn Claude into your AI task manager. Create, manage & complete TickTick tasks just by talking — official OAuth API, local, private.

Deploy your own personal OpenClaw on AWS Bedrock AgentCore — serverless, ~$9/mo, one-click CloudFormation, Discord/WhatsApp/Telegram 🦞

MCP server for x402 Service Discovery — continuously growing catalog of services, real-time quality signals, facilitator-compat checks. For Claude, Cursor, Windsurf.

Transcript-first AI video editing workflow for Codex, DaVinci Resolve, FCPXML, SRT, and faster-whisper.

Convert an X (Twitter) URL into clean markdown — tweets, photos, videos, long-form X Articles, and top replies. No auth, no API key.

Local LLM server that provides drop-in API compatibility with both Ollama and OpenAI, using your locally installed [llama.cpp](https://github.com/ggerganov/llama.cpp) 's `llama-server` as the inference backend.

LLM-neutral skill that fetches a URL to a temp file so agents can pipe the path through rg / jq / awk instead of dumping the whole page into context. Same shape as pi-webfetch / opencode webfetch. Single-file Python 3 stdlib. Works on macOS, Linux, Windows.

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

Auditable biomedical AI decision support agent — multi-hop clinical reasoning, drug interaction detection, and safety-first agentic architecture for health-AI research

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

CTF, pentest ve OSINT için terminal tabanlı otonom yapay zeka ajanı. 20+ AI sağlayıcı, 900+ skill, Telegram/Discord gateway ve MCP CTF köprüsü.

Turn a short prompt into one clean, hand-drawn concept illustration starring a deadpan peanut — an agent skill for Claude Code and OpenAI Codex.

Hermes Agent skill for The 48 Laws of Power: cite any law by number, get law recommendations for a situation, see complementary and contradictory laws. Defensive / applied-with-ethics / toxic framework included. English, peer-matched shape, MIT.

⚔ AI agent skills installer — 17,000+ skills for Claude Code, Cursor, Cline, Aider, Codex & Antigravity. pip install lotr-skills. cursor rules, claude code skills, SKILL.md, AGENTS.md.

Ferro Labs AI Gateway Python SDK - Instrument your LLM app, Works with any LLM or framework

ROS 2-native embodied runtime infrastructure for Genesis World. Multi-agent navigation, replay, benchmarks, and AI-tool safety boundaries.

General purpose Discord bot

👨‍🏫 A smart multi-agent system that creates personalized learning programs, roadmaps, curated resources, and hands-on exercises using AI + Google Docs — in one click.

Giáo trình xây hệ thống wiki AI-first Obsidian + Claude Code đa vault giống Phạm Thành Long. 41 file, 7 phần, từ triết lý đến template copy-paste.

Lightweight persistent memory for AI agents. One SQLite file. Hybrid search. Zero to 12MB.

A simple helm chart automating deployment of a retrieval augmented generation (RAG) solution on K8s Clusters.

Scriptable, multi-provider AI agent for the terminal — pipe into it, script it, run it on any model, cloud or local

🧠 An autonomous AI Agent for Threads with long-term memory (RAG) and persona management. Hybrid architecture combining Official Graph API for interaction and Apify for trend analysis.

AI-Native Trading Engine - AI 에이전트 기반 자동 주식 매매 트레이딩 시스템

Model Context Protocol tool for Virtual Machine Management over SSH

LangGraph multi-agent research pipeline with RAG, hybrid BM25+semantic search, FastAPI streaming, and LLM-powered synthesis.

LLM-powered A-share (Chinese stock) market analysis platform — technical analysis, prediction, strategy backtesting, and an autonomous research/decision agent. Personal toy project for learning; not investment advice.

AI virtual users powered by 54k+ real, anonymized user-research scenarios. Stop interviewing prompt-engineered personas.

AI agent skills for onboarding merchants to UCP (Universal Commerce Protocol). Audit → Profile → Catalog → Checkout → Validate.

Durable, review-gated background research for OpenClaw agents

ShuyuanCore (数元体) — 智能进化、风格一致、深度记忆、自主行动的开源AI Agent。（ShuyuanCore—An open‑source AI agent with intelligent evolution, consistent style, deep memory, and autonomous action.）

Agent Studio with Federated Single Sign-On and Fine-Grained Access Controls

Tenki — autonomous AI quant agent. Natural-language backtesting with tamper-evident on-chain proof: every run card stored on Walrus and anchored on Sui, Mantle & Somnia.

My personal collection of handcrafted AI agent skills — original prompting modules for code quality, knowledge exploration, and daily productivity.

A recursive dashboard. Built on the Cursor SDK and FastAPI. The agent reads its own source code, queries its own data, and edits itself when you ask it to. Two lines of Python and a script tag.

Personal investing cockpit CLI for A/HK/US stocks, funds, watchlists, PDF reports, and Lark delivery.

Skills that guide AI coding agents to integrate with the Adaline platform — send traces, manage prompts, run evaluations, fetch deployments, and more. Compatible with Cursor, Claude Code, Codex, Windsurf, and 40+ other agents.

AI copilot for TouchDesigner — DeepSeek v4. Standalone .tox (95 tools) + Claude Code MCP (110 tools, incl. td_ingest_url web ingestion). Activity log, OCR sidecar, tool approval gates, trace viewer, visual chat, BM25/FTS5 corpora, persistent memory, recipes, multi-model routing, compaction. TD 2025.32820+.

Autonomous AI Security Agent leveraging LLMs, RAG, and Knowledge Graphs for automated CVE analysis and auto-patching.

Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.

Claude Code production runtime - Python implementation and prose chapters

My AI agent skills for daily use. | 魔法哥开源的 AI Skills 合集。

A 股本地数据筛选器：自选/行业/题材/全市场 → CLI + AI-readable JSON · 告诉你坐标，不替你决策

AI-powered customer support agent built with Python smolagents and InterSystems IRIS — SQL, RAG, and live interoperability

AI-Powered Omnichannel Marketing & Operation System for Scenic Areas | Data-Driven • Knowledge Curation • Process Automation

An autonomous, 100% offline OS-level AI agent running on just 4GB VRAM. Built with Python, Ollama, and native tool-calling without MCP cache invalidation.

AI-powered multi-agent system for Web3 marketing automation — content generation, on-chain analytics, narrative tracking, campaign management. Built with MiMo LLM + FastAPI.

A discord admin bot

A Hermes Agent skill that turns prose into editable film storyboards. Kimi K2.5 parses, critiques, and learns how you direct

Educational Python coding agent built from scratch to explain agent loops, tool calling, code editing, bash execution, permissions, context management, and OpenAI/Gemini providers.

Codex skill for Ghost Buyer: careful Taobao/Tmall shopping research with user-controlled browser sessions and Markdown/HTML buying reports.