Python agents

AI news tracking skill for Agents like Claude Code, Openclaw, and more. Tracks AI entities across 9 sources and generates daily structured reports.

Open, MIT-licensed food, nutrition & agricultural science research skills for Claude Code, Codex, MiniMax Agent, OpenClaw & Grok Build — multi-agent literature/systematic review, journal-aware writing, peer review, proposals, figures & editable PPTX, plus author guidelines for 150+ journals. From the Food Science Group, Univ. of Melbourne.

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

A high-accuracy, rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate sentence segmentation.

Free AI-powered Amazon product research & marketplace intelligence for 6 platforms. Hidden Profit Index — Sorftime's proprietary algorithm for finding overlooked high-margin products. 80+ MCP tools. Amazon FBA, Walmart, TikTok Shop, Shopee, TEMU, 1688. Claude Code, Codex, Cursor, OpenClaw. Open source.

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

transformers safetensors mistral text-generation conversational en

通用个人知识库 vault，配合 cognition-hub Obsidian 插件与 Claude Code Agent 工作流，构成完整的认知生产管线。

AI Agent engineering and quantitative finance knowledge base: source-level architecture analysis, Agent-to-Agent protocol research, runnable code experiments, industry insights. Obsidian vault, ready to clone.

Autonomous AI research: an LLM agent searches for the best algorithm to fit the Mandelbrot set.

给AI伴侣增强时间感的小器官（电脑端专用）

CPU-oriented Python library for discrete Active Inference experiments in radCAD and cadCAD: deterministic grid worlds, multi-agent transitions, generative-model helpers, and fail-closed validation.

The Python scripts in this repo use MongoDB Vector Search with Retrieval-Augmented Generation (RAG) architecture to build a Question Answering application. They use the LangChain framework, OpenAI models, as well as Gradio in conjunction with MongoDB Vector Search in a RAG.

Email automation tool that extracts job listings and generates personalized emails with relevant portfolio links.

Your agent still returns the right answer -- but now it calls 3x the tools. Maida is the pre-merge behavioral regression gate for AI agents: baseline agent traces, gate PRs in CI, block behavior regressions before merge. Local-first, no cloud.

Catch silent failures in AI agents before your users do

CROW - Your AI Agent. MCPs, OpenRouter, Any Model or local. It's your choice.

Operational tooling & discipline for multi-agent AI engineering fleets — mutation-proven guards, a Textual terminal monitor, generalized skills, and specs. Every check ships with proof it can fail.

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.

Autonomous multi-market trading agent for Hyperliquid

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

⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and human decision-makers to co-exist in a multi-agent environment.

AI Agent Skill for B2B lead research, decision-maker discovery, customs checks, outreach drafting & controlled sending. Works with Claude Code, Cursor, Cline & Hermes.外贸客户挖掘 AI 技能包：找海外买家、挖决策人、查海关信号、写开发信、受控发送。支持 Claude Code / Cursor / Cline / Hermes 四平台。

Symbio is a self fine tuning AI agent that gives power to users through seamless interaction with their machines. This flexible system adapts to commands, continually learning and evolving based on user input and allows it to learn emperical data.

Configuration-driven evaluation, regression testing, replay, and load testing for SSE-streaming LLM agents

Repo of "Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems" (ACL 2026)

面向企业合同全生命周期的生产级 AI Agent 平台，支持合同解析、条款结构化、风险审查、HITL 人工确认、版本管理、客户回传 Diff、谈判辅助及 PDF/Email 交付；基于 LangGraph + RAG + ContractPolicy + Agent Workflow，实现可追溯、可恢复、可审查的合同智能处理闭环

Autonomous multi-market trading agent for Hyperliquid

端到端 QA 验收编排器 · Agent Skill：上下文 → 风险 → 用例 → 脚本 → 执行 → 审查 → 报告，全程自动衔接，只在用例确认时停下等你审核。支持 Claude Code / Codex / Cursor

Chatbot Answering from Your Own Knowledge Base: Langchain, ChatGPT, Pinecone, and Streamlit

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

Official Repo for Chat AI

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.

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

✨Kubewizard is An AI-Agent for automated Kubernetes troubleshooting, and management, based on LangChain and k8s related tools.

Github自动收集比较热门的项目,并自动阅读项目,生成相关报告发送到自己的飞书中

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.

这是一个结合了RAG（Retrieval-Augmented Generation）和网络搜索功能的Agent项目，能够同时检索本地知识库和进行网络搜索，为用户提供全面的信息服务。项目通过API调用大语言模型进行推理，同时使用本地的bce-embedding-base_v1嵌入模型和Chroma向量数据库处理本地知识库检索，并采用ms-marco-MiniLM-L-6-v2交叉编码模型进行结果重排序。支持多角度查询和抽象查询等高级检索策略，提升检索准确性和回答质量。

📚 Build knowledge bases for RAG

[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.

Chat to LLaMa 2 that also provides responses with reference documents over vector database. Locally available model using GPTQ 4bit quantization.

Multimodal RAG based on Llama 3.2

RAGify is designed to enhance search capabilities using Retrieval-Augmented Generation (RAG). By combining traditional web search with AI-driven contextual understanding, RAGify retrieves relevant information from the web and generates concise, human-readable summaries.

This is a complete website in which you can chat with pdf, extract meta data, text, links, image, and lot more . Check my blog for more details: https://medium.com/@amit.2503719/allaboutpdf-tool-for-data-extraction-and-talking-to-pdf-using-chatpdf-feature-f2daea15a59c

Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Service

LangChain and Streamlit RAG Demo App on Community Cloud showcases

AppifyAi: Transform conversations into stunning web apps. Dynamic code generation + intuitive interface. Unleash your creativity effortlessly. Use the power of GPT OpenAI LLM and 🦜️🔗 LangChain ⚡and ChromaDB.

Retrieval-Augmented-Generation of over 1700+ pages of Unreal Engine documentation served through FAISS + OpenAI with LangChain

A generalist agent that can go online and accomplish complex tasks using semantic-kernel and autogen.

Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.

Project-agnostic, composable AI workflow automation via pi packages and Claude Code plugins.

Claude Multi-Agent Project Management Framework - AI-driven orchestration with LangGraph and OpenAI integration

A Ros Package for Human-centered Interactive Intelligent Humanoid Robots

A Concourse resource that can trigger and pass parameters to jobs using slack

a tiny, exploitable chatbot that can use tools

This is the final year project of university, in which my group is developing a chatbot for university admissions using LLMS and RAG. The bot is powered by Langchain and FastAPI. The UI and frontend is developed in Next.js.

Prompt Injection Attacks against GPT-4, Gemini, Azure, Azure with Jailbreak

Process 1000 calls to ChatGPT API in 2m

Let ChatGPT (Large Language Models) Serve As Data Annotator and Zero-shot/few-shot Information Extractor.

A Python framework for GPT-driven automations, with an early emphasis on mass file operations.

CSVs of the Huggingface and LMArena LLM leaderboards, along with the code to generate them in Python and R.

A minimalistic web app to generate transciption for audio built using Python

Small tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature. Very quickly made, you should not rely on this on prod.

Generate Tableau Workbooks using AI

AI-powered code reviews

Pre-commit hooks collection that utilizes ChatGPT and OpenAI platform to validate changes made to the codebase.

A neural network based file sorter. Trains an autoencoder to sort images or audio based on the similarity of their encodings, or uses the OpenAI CLIP model.

LLM Evaluation and Observability System for Football Content

Network Analysis through LLMs for Knowledge Extraction

A "chat with your data" example: using a large language models (LLM) to interact with our own (local) data. Everything is local: the embedding model, the LLM, the vector database. This is an example of retrieval-augmented generation (RAG): we find relevant sections from our documents and pass it to the LLM as part of the prompt (see pics).

TheNZT is a powerful multi-agent finance query processing system designed to process and respond to finance-related queries efficiently. Leveraging advanced LLM multi-agent collaboration, it provides intelligent solutions for Finance, Company-specific, and Market-related queries.

Autonomous GPU kernel optimization system driven by AI agents.

Joint Multipath++(2nd) for Sim Agent in waymo competition 2023 of CVPR workshop

An open source benchmark for Multi Agent Reinforcement Learning

MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.

This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.

[ICRA2023] The official implementation of paper "Bridging the Domain Gap for Multi-Agent Perception"

Locally hosted AI Agent Python Tool To Generate Novel Research Hypothesis + Titles + Abstracts

Lightweight AI agent library. Turn Python functions/classes into AI tools instantly. No verbose configs or complex abstractions.

Code repo for "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding"

Official Code for "Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction (AAAI 2021)"

Eden is building autonomous creative agents.

Build domain AI assistants with annotated dialogue examples - 通过标注对话示例，低成本构建可靠智能体

A simple Tinode chatbot framework.

Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG, anche multimediali (audio, video, immagini e OCR). It is an Italian and English framework, which allows you to chat with your documents in RAG, including multimedia (audio, video, images and OCR).

An NVDA Add-on for Integration with OpenAI, MistralAI, and OpenRouter APIs

Cumulative Agentic Skill Creation through Autonomous Development and Evolution

Multi-agent deliberation plugin for Claude Code - council, debate, and deliberation modes

[ICLR'26] EduVisAgent: A Benchmark and Multi-Agent Framework for Pedagogical Visualization

[CVPR2024] Multi-agent Collaborative Perception via Motion-aware Robust Communication Network

[AAAI 2025 Oral] Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin | Version 3.1.0 | Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.

OpenMindedChatbot is a Proof Of Concept that leverages the power of Open source Large Language Models (LLM) with Function Calling capabilities to provide comprehensive and flexible responses to user queries.

Official repository for ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use

[COLM'24] Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

An open-source framework for building monolithic or distributed agentic systems, ranging from simple LLM calls to compositional workflows and autonomous agents.

REFRAG: LLM-powered representations for better RAG retrieval. Improve precision, reduce context size, same speed.