Python agents

Awesome all-in-one research skills for AI agents — covering every academic discipline. Works with Claude Code, Codex, Gemini CLI & Cursor.

SpecMem: 🧠 Unified Agent Experience and Cognitive Memory for Every Coding Agent

PsyChat 是一款基于范例引导与Agentic RAG的智能 AI 心理咨询助手。基于高度匹配的Few-shot与学习笔记，应用理性情绪行为疗法（REBT）帮助用户识别并调整非理性信念，缓解负面情绪。

Claude Code skills for founders building B2B SaaS — covering GTM, product, engineering, design, and content.

[ICML'26] Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation

Claude Cortex

SEO Content Engine for LLMs - a prompt-engineering system that turns any capable AI into a world-class SEO strategist: generate, rewrite, and audit content against 49 ranking factors with multilingual support.

国内公募基金数据采集与AI辅助分析工具 — 全栈FastAPI+React，集成AKShare多源数据、风险评分引擎、回测验证、LLM可选分析

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

Panacea is a framework for building collaborative, intelligent multi agent AI systems. The framework provides a robust infrastructure for creating and managing multiple AI agents, and enables developers and organizations to build, deploy, and optimize AI agents that work well in dynamic, complex environments.

Open APA (Open Agentic Process Automation) is built on top of our first-place performance in the OSWorld Benchmark. It provides a practical and extensible framework for building computer use agents that can reliably execute long-horizon, real-world tasks across applications, interfaces, and workflows.

Conversational black-box reverse-engineering agent on the pi coding agent — analyzes apk/.o/.hex/exe with a self-provisioning toolchain (radare2 · Ghidra · angr · jadx). Static analysis. Claude Code & Codex compatible.

A private, offline 'second brain' for the people, projects, and decisions you juggle — and it keeps score of whether your judgment was right. 本地私密的人际情报与决策记忆系统。

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 lines of Python.

[ICLR 2026] Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

[ECCV2026] Official Implementation of "VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement"

Claude Code plugin for EODHD financial data — 150k+ tickers, 70+ exchanges, OAuth MCP server with 80 tools, 7 workflow skills, financial-analyst agent, 5 slash commands. MIT.

Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

The operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.

Crewplane is a provider-neutral control plane for human-designed coding-agent workflows—reviewable before execution, observable while running, and traceable afterward. It works with Claude Code, Codex, Gemini, Copilot, or any CLI.

Token-efficiency analyzer for AI coding agents (Claude Code, OpenAI Codex CLI): cost estimates, cache analysis, and savings advice. Zero dependencies.

🦅 5-Layer Intelligent Skill Retrieval for Hermes Agent — hard triggers, FTS5, synonym dictionary, dense embedding, RRF fusion. Zero core modification.

生意参谋 sycm.taobao.com 数据抓取 + Excel 导出 CLI · 19个已核实子命令(客服/评价/销售/商品/新品) · cookie 直读无需登录

Give your AI agent a real phone number. Open-source telephony API with voice calls, SMS, MCP server, and skill file. Built with FastAPI + SignalWire + Deepgram.

gradio gradio-custom-component Chatbot chatbot agents streaming tools region:us

transformers safetensors gguf mistral text-generation pytorch

transformers safetensors llama text-generation en fr

transformers pytorch safetensors llama text-generation facebook

transformers pytorch safetensors llama text-generation facebook

transformers pytorch tensorboard gpt2 text-generation code

Agent-native course marketplace and skill registry for executable AI-agent curricula

Measured, monotonic, lossless input savings for Codex.

Digital Life · Life Engineering — A runtime framework for persistent, autonomous LLM agents

Reusable AI video production recipes for agents—storyboard, generate, edit, subtitle, and QA short videos with Codex, Claude Code, OpenClaw, and more. | 面向 AI Agent 的可复用视频生产配方：完成短视频分镜、生成、剪辑、字幕和质检，支持Codex、Claude Code、OpenClaw 等 Agent。

AI-powered SQL query diagnostics across PostgreSQL, MySQL, Oracle, SQL Server and SQLite. No database connection required.

GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中，并为多用户场景提供用户自带 API Key（BYOK）能力。

Damn Vulnerable AI Application - For LLM Red Team Training. LLM testing, RAG testing, Multimodal testing, Agent testing, LLM paload generation

Claude Agent SDK + LLM-wiki，就是最强大的agentic RAG 。让 AI 当一个“知识编译器”，先把你的所有资料读一遍，整理成一本结构清晰、彼此关联的百科全书。以后你再提问，AI 直接翻这本百科书就行了。 本项目主要展示了我制作的 llm-wiki 怎样通过 Claude Agent SDK 转为 agentic rag， 效果非常好的。使用方法：.venv\Scripts\Activate.ps1; python 7_wiki_writer.py --request "怎样拼搭微型车"

Zerolinear — AI research lab and home of the Zeline open-source agentic AI framework.

A feature-rich, mobile-first UI for ComfyUI, powered by a recipe-driven engine that turns complex workflows (Image, Video, 3D) into simple APIs/MCP tools for LLMs & AI Agents.

轻量级多智能体协作系统 —— AI Agent 开发入门实战项目

Let's Qitos! A torch-like agent-native framework for researchers.

Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting

Agent-native embedded systems lab for pluggable simulation, evidence-driven validation, and controlled evolution.

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

Integrating Rasa Core with Django backend and finally using Webchat for chatbot user interface

Light but flexible templating and FSM framework. This repo is @promplate itself.

OpenAI functions + Chainlit + Streaming responses. Chain multiple functions in one query.

AppleHealthLLMBot is a personal health assistant bot designed to interact with users through conversational queries, providing personalized insights into their health activities and metrics.

This repository `II-Commons` contains tools for managing text and image datasets, including loading, fetching, and embedding large datasets.

Multi-agent stock analysis framework using LangGraph — specialized agents for technical analysis, news sentiment, and synthesized investment recommendations.

This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DPO and KTO.

Atlan AI Agent Toolkit

Skill Scan Agent — Automated scanning, identification, and assessment of SKILL security risks.

Official implementation of the paper: "Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts"

ChatIQ is a versatile Slack bot using GPT & Weaviate-powered long-term memory to accomplish various tasks.

A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.

Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information Extraction (IE) applications with LLMs

GroqStreamChain is a real-time AI-powered chat app using FastAPI, WebSocket, and Groq. It streams AI responses for interactive, low-latency communication with session management and a clean, responsive frontend. Ideal for building AI-driven chatbots.

An OpenAI-compatible API server for AutoGen

xLLM 2.0. No Blackbox, secure, accurate, auditable Enterprise AI, developed by BondingAI. Built from scratch. With proprietary agents.

AgenticSearch operates within an agentic workflow, utilizing Gemini 2.0 and an extensive tool registry to handle complex questions. By integrating and synthesizing data from multiple APIs, it delivers cohesive and detailed answers, enabling a robust and intelligent search system.

A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.

💬 Chatbot made using Django web framework with OpenAI's GPT-3.5 language model

OpenAI GPT-4o Mini TTS – Home Assistant Integration

YouTube video summarization using Whisper audio transcription and GPT-based summaries.

An AI-powered marketing campaign generator using OpenAI's gpt-4o-mini, FastAPI for the backend, and Streamlit for the user interface. Containerized for deployment with Modal.

Generate Clips with captions of videos via AI and automatically upload them as youtube shorts!

Semantic Code Search tool. Query your codebases using natural language

An completely Free & Unlimited unofficial Python SDK for the OpenAI API, providing seamless integration and easy-to-use methods for interacting with OpenAI's latest powerful AI models, including GPT-4o (Including gpt-4o-audio-preview & gpt-4o-realtime-preview Models), GPT-4, GPT-3.5 Turbo, DALL·E 3, Whisper & Text-to-Speech (TTS) models

📚 Build knowledge bases for RAG

Hawx Recon Agent is an intelligent, autonomous reconnaissance system powered by a Large Language Model (LLM). Designed for offensive security workflows, it automates initial triage and guided follow-up based on live service data.

Minimal FastAPI + Pydantic AI project template for building LLM-powered agents

A Python framework for building AI agent systems with robust task management in the form of a graph execution engine, inference capabilities, and caching. We support advanced features like State Snapshotting, Middleware, LLM Directed Graph Execution, Open Telemetry Integrations and more.

Code for CVPR 2025 paper: TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception

Code for ECCV 2020 paper - LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities

This is the official repo for [CoRL 2024] Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation

Agent PR Replay takes merged PRs from any repository, reverse-engineers the task prompt, runs Claude Code against it, and compares what the agent did versus what humans actually shipped. The result is targeted, empirical guidance.

Function Calling Leaderboard for Traditional Chinese (zh-tw)

Draft42 - Streamlit chatbot with function calling

The DPAB-α Benchmark

This code is an implementation of a simple chatbot using TensorFlow, which is a machine learning framework developed by Google. The chatbot is trained using a neural network to classify user inputs into predefined intents and provide appropriate responses based on the detected intent.

[TGRS'25] AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval

Streamlit-based UI Demo Kit app to showcase capabilities of Azure AI Foundry's Agent Service framework.

A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark

A toolkit to build AI Agents that proactively interact w/ the world

AI-native security copilot for Python developers. Scans for secrets, vulnerabilities, and dependency CVEs — then tells you how to fix them.

Open Skills is a modular, Anthropic-style skills framework that lets agents dynamically discover, select, and execute user-defined capabilities. It runs as a standalone FastAPI service or embedded Python library, providing full skill lifecycle management, versioning, and context-aware prompt integration.

这是一个由LangGraph协议主导的因果分析Muti-Agent，结合MCP,RAG等多种工具进行辅助进行因果分析，提供给用户一份完善的因果分析的分析报告和因果图

Mental health support companion

The official Implementation of HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems

Ralph Loop Optimizer: an AI-driven framework that turns any evaluatable codebase into a self-improving optimization loop for strategies, models, prompts, and workflows

Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)

[NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario

自動每日更新, 讓你的LLM有面對openclaw疑難雜症處理的能力。This is an Agent Skill designed for AI coding assistants (like Claude with Antigravity). Once installed, the AI assistant gains deep knowledge of OpenClaw and can help you