Python agents

[ICLR 2025] Benchmarking Agentic Workflow Generation

🪞 Personalized LLM Agents 🪞

AI-driven Yu-Gi-Oh! bot using deep reinforcement learning and LLMs

Synthetic Data Generation Toolkit for LLMs

StoryCraftr is an open-source AI-powered tool that helps writers craft stories, generate worldbuilding details, and create book outlines and chapters seamlessly through a simple CLI. Empower your creativity with AI!

Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.

Local personal memory for LLM agents

166 production-ready Claude AI skills organized by corporate role — executive leadership, finance, HR, marketing, sales, legal, operations, engineering, product, data, customer success, procurement & document processing

Self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic One handles the how — finding the right API, injecting credentials at runtime, and brokering the request

迅投 QMT 量化 AI 技能集（Agent Skills）：研报因子回测脚本生成等，适用于 Claude Code / Cursor / Codex / Kimi 等 70+ AI 编程工具

transformers safetensors qwen text-generation custom_code zh

OpenAI GPT based informational audiobook/podcast mp3 generator

Full stack advanced chatbot over LlamaIndex.TS documentation with preview feature using Multi-documents-agents, bootstrapped with create-llama

Scrape data from social media and chat with it using Langchain

(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.

[EMNLP 2024 (Oral)] Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"

Catch MCP server issues before your agents do.

一个基于微软AutoGen框架的企业级金融分析系统，使用多Agent架构提供全面的财务分析、风险评估和量化投资分析功能。 核心功能: 多源数据收集 : 整合Yahoo Finance、Alpha Vantage、Quandl等多个金融数据源, 智能财务分析 : 基于AutoGen的多Agent协作分析, 风险评估 : VaR计算、压力测试、蒙特卡洛模拟, 量化分析 : 因子模型、投资组合优化、机器学习预测, 实时监控 : 系统性能监控和告警, 数据可视化 : 交互式图表和报告生成,

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.

Context-aware knowledge-graph based chatbot using GPT4 and Neo4j

一个可以帮你订阅、查询快递物流、跟你闲聊Telegram机器人

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

This open-source repository offers reference code for integrating workplace datastores with Cohere's LLMs, enabling developers and businesses to perform seamless retrieval-augmented generation (RAG) on their own data.

Build Research and Rag agents with Granite on your laptop

Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.

[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"

The fastest Trust Layer for AI Agents

A Langchain app that allows you to ask questions to a CSV file

A Java backend engineer learning AI full-stack in public — Python · FastAPI · RAG · pgvector · Next.js

Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"

[ICLR2026] NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents

agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces

Persistent memory for Claude Code — identity, context, and continuity across sessions

103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other Agent Skills-compatible tools. Complete SKILL.md workflows—not a link directory.

SkillLens: a framework for studying model-generated agent skills across the full raw experience generation → skill extraction → skill consumption lifecycle.

Reverse-engineered Doubao (豆包) API → OpenAI-compatible REST service. Free multimodal chat, image/video/music generation, and file hosting for AI agents.

Browser-native AI agents for X (Twitter): multi-account, MCP-ready, no X API key required.

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semantic layer. 20/20 on an 80-table Spider run. Built-in tracing and scenario support.

High-level edge-cloud AI multi-agent framework for real devices, verifiable actuation and entropy-bounded recovery.

A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.

Multi-agent to generate LangGPT prompts.

支持查询主流agent框架技术文档的MCP server（支持stdio和sse两种传输协议）, 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai

[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications

Self-knowledge through numbers

Terminal-based AI Coding Agent, similar to Claude Code, OpenAI Codex etc. but works with many more LLMs e.g. Gemini, Groq, Deepseek

一种利用Langchain框架和本地向量库实现的对话式BI，它的目标是帮助用户寻找、理解数据知识，并能够分析数据、洞察结果，通过自然语言对话，降低数据分析的门槛。

AI-powered resume optimization using CrewAI. Analyzes job postings, scores resume matches, and provides tailored improvements with multiple AI agents. Built for job seekers to maximize their application success.

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.

This is an advanced Python tool that empowers you to effortlessly draft customizable PowerPoint slides using the Generative Pre-trained Transformer (GPT) of your choice. Leveraging the capabilities of Large Language Models (LLM), odin-slides enables you to turn the lengthiest Word documents into well organized presentations.

将 Z.ai Chat 代理为 OpenAI/Anthropic Compatible 格式，支持多模型列表映射、免令牌、智能处理思考链、图片上传等功能；Z.ai ZtoApi z2api ZaitoApi zai X-Signature 签名 GLM 4.5 v 4.6

Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tier memory, Agent Packs marketplace, zero telemetry. Python 3.12+, Apache 2.0.

Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.

A Home Assistant custom component that provides an AI-powered agent capable of generating automations based on natural language queries. The agent connects to all entities in your Home Assistant instance and uses OpenAI's or Llama API to translate user requests into valid Home operations including creating automations for you!

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.

World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.

CrawlAI RAG is an AI-powered website intelligence platform that allows users to crawl entire websites, index their content, and ask natural-language questions using Retrieval-Augmented Generation (RAG). It transforms static websites into queryable knowledge bases.

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

DevAgent Studio is a multi-agent workbench for software project understanding and engineering governance. It helps teams review pull request risks, onboard new developers, understand unfamiliar systems, and continuously identify architecture drift and technical debt.无论是新人接手陌生代码、开发者提交 PR，还是团队进行架构巡检，都可以通过多 Agent 协作生成可追踪、可审核、可沉淀的项目治理结果。

A voice chatbot based on GPT4All and talkGPT, running on your local pc!

Chat with PDF files with source highlights

PDFStract - Extract, Chunking and Embedding Layer in Your RAG Pipeline - Available as CLI - WEBUI - API

Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.

SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.

Open-source AI customer support platform — RAG knowledge base, multi-provider LLM agents, embeddable chat widget. FastAPI + Next.js + pgvector.

SearchAgent-Zero: A Scalable Multi-Turn Search Agent RL Framework

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

transformers pytorch gpt_neox text-generation en dataset:togethercomputer/RedPajama-Data-1T

Using Langroid's Multi-Agent Framework to Build LLM Apps

Python package for webscraping in Natural language

OpenClaw skill for scraping any URL using the Decodo Web Scraping API.

Automatically generate engaging AI podcasts from nothing but an episode title.

LLM <-> Python agentic runtime prototype

Intelligent Python system that extracts real estate property data as structured JSON using AI agents, Nebius Qwen LLM, and Bright Data MCP.

Local companion launcher and maintenance toolkit for the Codex desktop app.

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

🦡 codebadger is a containerized Model Context Protocol (MCP) server that gives AI agents and LLMs deep, queryable access to a codebase's structure and data flow through Joern Code Property Graphs (CPGs).

MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run numerical simulations through natural conversation

transformers pytorch safetensors mistral text-generation LLMs

gradio region:us

Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of your infrastructure.

WhiteLightning distills massive, state-of-the-art language models into lightweight, hyper-efficient text classifiers. It's a command-line tool that lets you create specialized models that run anywhere—from the cloud to the edge—using the universal ONNX format for maximum compatibility.

Local Topsha 🐧 AI Agent for simple PC tasks - focused on local LLM (GPT-OSS, Qwen, GLM)

PPO implementation for OpenAI gym environment based on Unity ML Agents

Fast similarity search using DuckDB

Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way of sampling and voting. Our method is called Agent Forest, as a tribute to the classic Random Forest.

Open Framework for AI Agents to play Red Alert through Reinforcement Learning

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

Academic Agents Studio 是一款面向学术研究人员、教育工作者和学生的新一代开源学术研究全流程智能体应用服务平台，基于多模型（GPT、Claude、Deepseek、Qwen等）与智能体协议，提供论文专利写作、文献综述、代码解析、多语言翻译、可视化图表和在线检索等一体化学术功能；基于 Gradio的界面，支持科技感输入区、插件扩展、自定义模型与外部 API，提供模块化、可扩展的系统，致力于帮助全球的研究者、教育者和机构专注于创新和探索，提高学术生产力，促进协作，推动知识创造和突破。

VividNode: Multi-purpose Text & Image Generation Desktop Chatbot (supporting various models including GPT).

Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI models to MCP servers via stdio and SSE

Pebblo enables developers to safely load data and promote their Gen AI app to deployment