Python agents

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

An AI driven debugging assistant specially designed for x32/x64dbg, it helps to double the efficiency of reverse engineering, vulnerability mining, and malware analysis, making it your intelligent copilot.

基于 Muye Multi-Agent SDK 的多服务 Agent 脚手架，可一条命令基于知识库创建Agent。A multi-service Agent scaffolding based on the Muye Multi-Agent SDK, which can create an Agent from a knowledge base with a single command.

A Python library for multi-agent planning and pathfinding: CBS, PIBT, LaCAM, LNS, space-time A*, plus decentralized NMPC, velocity obstacles and swarm behaviors

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

Behavioral testing for AI agents.

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

A simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities in the most "Code-Centric" and "Context-Centric" manner. LLM As Function, Prompt As Code.

a simple message reply suggestion system

WhatsApp Python Bot. Key features include sending and receiving messages, as well as support for images, files, documents, videos, and product. Group functionality is fully supported — you can create new groups and interact with them programmatically. Additionally, the bot can be integrated with ChatGPT to enable AI-powered conversations

OpenAI API -> Ollama API (original idea: https://github.com/microsoft/vscode-copilot-release/issues/7518#issuecomment-3043670968)

vector-ai-agents-lab

Compact and Agent-Native MoE Training System

An implementation of Emergence of Grounded Compositional Language in Multi-Agent Populations by Igor Mordatch and Pieter Abbeel

Customer support chatbot based on seq2seq model.

一个对话类 AI Agent，利用如 LLaMA 3 等大模型为全球超过 100 种语言的个性化学习提供支持，特别适用于全球旅行和生活场景。

[EMNLP 2024 (Findings)] mABC: multi-Agent Blockchain-inspired Collaboration for root cause analysis in micro-services architecture

COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.

Run AI Agents in the cloud

AI Voice Assistant: Talk to an AI agent that helps you with event scheduling, contact management, accessing your knowledge base, and web searches using simple voice commands

RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM reranking, query enhancement agents, CrewAI orchestration, Qdrant vector search, Redis/Mongo sessioning, Celery ingestion pipeline, Gradio UI, and an evaluation suite (Hit-Rate, MRR, hybrid configs).

AI agent for trading on prediction markets (specifically, Omen on Gnosis and Polymarket on Polygon)

Training LLMs to reason and analyze data with notebooks

Self-hosted platform for Claude Agent SDK agents. Container isolation, real-time execution tracking, and Web UI dashboard

Loom is an AI harness, that can be used with local or cloud LLMs, for complex tasks. It decomposes work, drives execution through a verification harness, and keeps models on track with structured state instead of history. It can route between thinking and acting models, verifies outputs, and exposes an APP/TUI/API/CLI/MCP for both humans & agents.

Hooks for Claude Code and Cursor for secrets scanning

Python-based implementation to generate Proof of Work (PoW) tokens and Sentinel tokens for bypassing security mechanisms in OpenAI's ChatGPT and Sora private APIs

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable system — designed for building real, production-grade AI applications.

Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolated sandboxes, DAG dependencies. Open-source, self-hostable, model-agnostic (Claude / Gemini / Codex).

from vibe coding to agentic engineering - practice makes gemini perfect

由 LLM Agent 驱动的本地 Markdown 文献库管理与学术综述自动化系统

SGLang model provider for Strands Agents.

A Security Benchmark for Claude Code Agent Skills

GPS-aligned AI prompts and Agent Skills for genealogical research (CC-BY-NC-SA-4.0)

Expose agent CLIs (Codex, Cursor Agent, Claude Code, Gemini) as an OpenAI-compatible /v1 API gateway.

🌐 Real-browser web fetching for AI agents.

A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or bring your own backend.

Open library of legal AI skills (SKILL.md) for MCP-compatible agents — 39 jurisdictions, 200+ plugins, Apache-2.0.

gradio region:us

transformers safetensors gguf gemma2 text-generation llama-factory

transformers pytorch safetensors llama text-generation license:other

transformers safetensors qwen2 text-generation code codeqwen

Transformer-powered hashtag segmentation with beam search, RRF ensembles, and agent-ready MCP workflows. A scalable alternative to heuristic splitters and massive LLMs.

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek models in Codex CLI or any OpenAI client. Cross-platform, single-file, no auth changes.

My Personal AI OS — local-first chat, agents, video analysis, research & email triage on your own machine

Cross-border e-commerce AI knowledge base, read by people and installed by agents: 69 trilingual guides, 878 prompts, a 100-entity / 322-constraint ontology, and 9 skills as a Claude Code plugin or over MCP. Factual claims are dated and CI-verified. CC0.

Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

Ask questions against any git repository, and get a response from OpenAI GPT-3 model.

Retrieval Augmented Generation API using Open LLMs and FastAPI

📍🗺️ A Python library for Multi-Agents Planning and Pathfinding (Centralized and Decentralized)

Integrates OpenAI with BinaryNinja via a plugin.

auto-wing is a tool that uses LLM to assist automated testing

python flask app serving as webhook for whatsapp business accounts making prompts to openai api

Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.

Self-hosted AI assistant with multi-channel support, scheduled tasks, and extensible skills

Context-central multi-agent framework with PyTorch-like API. Build intelligent agent systems with minimal code.

Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.

MoEL: Mixture of Empathetic Listeners

🤗 Code for our EMNLP 2021 paper: "Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes"

A quickstart for the trader agent for AI prediction markets on Gnosis

multi-agent data collection and distributed learning in CARLA simulation

A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation of Genie with enhancements

ScoutAPM Python Agent. Supports Django, Flask, and many other frameworks.

Research-backed orchestration system for Claude Code — structured workflow, session memory, quality gates, and 118+ proven patterns.

Simple GUI around whisper.cpp for voice-to-text on Linux

Responses API on Azure OpenAI samples

Example Agent Applications by Relari.ai

Chemist AI Agent for Developing Materials Datasets with Natural Language Prompts

A Model Context Protocol service for TikTok video discovery and metadata extraction.

Claude Code for DSPy: Comprehensive CLI to Optimize Your DSPy Code. our AI-Powered DSPy Development Assistant

Codes for paper "SafeAgentBench: A Benchmark for Safe Task Planning of \\ Embodied LLM Agents"

a personal knowledge management system that collects and retrieves knowledge from files, webpages, papers, emails, and notes. It features intelligent tag extraction, semantic search, RAG-powered Q&A, and automated knowledge mining with entity extraction, relationship discovery, and topic clustering. Runs entirely locally.

🏛 An agent-first web browser

open source free interview copilot for windows 11 using OpenAI api. 开源免费AI面试助手适用Windows11支持API

A self-paced bootcamp for engineers building AI into production systems. Starts from fundamentals (tokenization, embeddings, prompting) and builds to RAG, Agents (LangGraph, tool design, memory, multi-agent), and LLMOps. Depth over breadth.

Framework for agentic coding supporting many popular agent coding tools.

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

项目描述：构建⼀个能够⾃动撰写多模态呈现、具备专业性和深度、数据融合与事实溯源、规范 有逻辑的各类⾦融研报的智能 Agent 系统。 主要负责：根据赛题思路，对目标公司生成金融研报，通过 LLM 获取目标公司的竞争对手，用 akshare 获取数 据源的的三大报表数据，通过 duckduckgo 获取公司信息、行业信息、股份信息等，通过设计数据分析师智能 体，包含三个动作代码生成和执行、收集图片、完成动作，用 pyplot 生成金融报表。最后通过 word 形式文件 展示多模态研报。包括目标公司财务状况、关键财富指标分析、财务问题等，在天池大赛 A 榜单获得前百。

外贸B端全链路AI自动化获客转化Agent系统

Describe it or draw it — Kiln makes it real. The open-source MCP server for 3D printing: AI agents (Claude, Codex, Cursor, or any MCP client) design, generate, slice & print on Bambu Lab, Creality, Prusa, Elegoo, Klipper/Moonraker, OctoPrint, Duet/RepRapFirmware & any Marlin printer.

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

A collection of AGENTS.md configurations, skills, and prompts tailored for Data Scientists to maximize productivity with AI coding assistants.

A repository for agentic world building to roleplay in. A world seed template is used for the pipeline and the output is a Silly Tavern ready character cards, world info and system settings.

A toolkit of Claude Code skills for doing economic theory with LLMs: math-proof (single-pass proving), codex-math (adversarial verification), and co-math (multi-agent proof projects). With a VCG-for-grade-inflation case study.

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.

transformers pytorch safetensors llama text-generation japanese

transformers safetensors llama text-generation en fr

gradio region:us

gguf llama.cpp llama-cpp minicpm minicpm5 minicpm5-1b

探索任务之间如何直接通信、交接并长期协作，同时提供一个真正可用的终端 AI 编程工具。 CodePlus 并不是为了直接复刻 Codex。我希望通过这个项目持续探索新的 Agent 协作方式，同时吸收现有工具中已经得到验证的优秀实践，并逐步把自己的理解变成可以公开、可以使用的技术实现。