Python agents

Agent-driven post-production workflow for video podcasts

A research-grade harness for evaluating long-horizon AI agents, with ablatable memory, control-plane benchmarks, deterministic simulations, and pre-registered machine-graded results.

Implementation for the paper "StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction".

Longitudinal Personality Modeling for Reflective Agents

VeighNa Agent开发框架

An agentic harness for small language models.

Analytics & cost-monitoring dashboard for Hermes Agent

Home Assistant Integration for the Management Agent for Unraid

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

A benchmark for general-purpose terminal-use agents.

Memory kernel stack for Hermes agent

从参考图提取视觉风格 DNA，强制生成标注与纯色双版色卡的 AI Agent Skill

A curated list of 100+ AI-ready tools for Computer-Aided Engineering, ranked by an AI-Readiness Score (agent-callability: MCP, Python API, CLI, pip). CFD, FEA, SPH, DEM, differentiable simulation, neural operators, PINNs, MCP servers.

Open-source desktop OCR, AI translation, editing and inpainting tool for user-provided manga and comic images.

Official Repository of Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

Cloudflare Browser Rendering plugin for hermes-agent — crawl, scrape, extract content from web pages

Local-first Agent Skills for safe social-web workflows—starting with Douyin and designed around reusable browser adapters.

Agentic RL 零基础中文教程：24 章从概念到 GRPO 实战，含 TRL 最小可跑示例 | Beginner-friendly Agentic RL tutorial with hands-on GRPO project

Executable security regression testing for agentic applications and MCP-integrated systems.

RTL agent team; Harness for Agentic hardware design and verificiation.

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

Hermes Agent weather plugin — NWS-grade model imagery, NEXRAD radar, and verified meteorological calculations. Pure Rust stack.

PhoneHarness runtime harness for mixed-action phone agents

Collection of Materials on AI Agents

Needle simplifies building RAG pipelines.

Twitter AI Tweet bot automatically responds to mentions and tweet replies on Twitter.

The implementation of ICLR 2023 paper "Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data".

An MCP server that scales development into controllable agentic, recursive flows, and build a feature from bottom-up

Source code of paper: Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

A repository of agent enabling automated hackathon entry.

A framework that uses multi-agents to enable users to perform a systematic data science pipeline with just two inputs.

Automate web research way beyond the first page of search results; curate knowledge bases to chat with.

Local RAG server for code editors. Scans your codebase, builds a local context index, and connects to any external LLM for context-aware completions and assistance.

Yet another chatops framework

DeveloperGPT is a LLM-powered command line tool that enables natural language to terminal commands and in-terminal chat.

Codex-first toolkit for open-source maintainers: AGENTS.md, skills, automation, and verification workflows.

Retrieval-augmented generation (RAG) for remote & local LLM use

LLM Chatbot w/ Retrieval Augmented Generation using Llamaindex. It demonstrates how to impl. chunking, indexing, and source citation.

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing deep hardware intelligence.

把 Dify 中的 Agent 接入到钉钉 AI 助理中

AI agent CTF 靶场竞赛平台

[MLSys 2026] AccelOpt: Self-improving Agents for AI Accelerator Kernel Optimization

Drop-in SDK for adding continual learning and long-term memory to any LLM agent.

A Stream-based LLM Agent Framework for Continuous Context Sensing and Sharing

Fully open architecture implementation of modern multi-agent swarming techniques.

Starter template for APEX. Contains custom Copilot agents, Azure Pricing MCP server, and an orchestrated multi-step workflow. Auto-syncs from the main repository.

This project shows the area division process in Multi-Agent exploration using Cyclic Gradient Descent and also how Cooperative Perceptional Messages are used in V2V communication to share information among agents in about the environment.

The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》

(ICML 2023) The official code for RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

[ARCHIVED] Base configuration library and generic methods for Rudder Linux agent

The Great Courses Agent for Plex

一个面向真实场景的 Agent Harness

Computer-Use Agents as Judges for Generative UI

SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents (UIST 2021)

Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)

This repository is an Reinforcement Learning Platform for learning agents to control cyber-physical Power Distribution Systems resiliently. The cyber environment in based on SimPy Discrete Event Simulator, while the distribution system is backened by Open-DSS.

Decorator to retry calling a function upon error

Data Neuron is a powerful framework that enables you to build text-to-SQL applications with an easily maintainable semantic layer. Whether you're creating customer-facing chatbots, internal Slack bots for analytics, or other data-driven applications, Data Neuron provides the tools to make your data accessible through natural language

MCPToolBench++ MCP Model Context Protocol Tool Use Benchmark on AI Agent and Model Tool Use Ability

A batteries-included monorepo framework for building sophisticated LangGraph applications

Source code of our paper "Multi-Agent Consensus Seeking via Large Language Models".

BlockRank makes LLMs efficient and scalable for RAG and in-context ranking

Create simple Agent without frameworks

This project will work towards a fully-functional autonomous intelligent cyberdefense agent with increasingly advanced capabilities that can be used in both research and production contexts.

The AI Agent That Improves Your LLM App

Heavy3 Code Audit: Agent skill that uses multi-model consensus to review plans, code, and PRs for coding agents

An experimental SDK for adding agentic memory and learning in a pluggable way

The official codes for "M^3Builder: A Multi-Agent System for Automated Machine Learning in Medical Imaging"

Open-source codebase for MAZero, from "Efficient Multi-agent Reinforcement Learning by Planning" at ICLR 2024.

Official Repository of "GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration".

Agent0 is the SDK for agentic economies: open discovery and trust for agents

🕷CrawlerDetect is a Python library designed to identify bots, crawlers, and spiders by analyzing their user agents.

BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow

A simple rule-based AI chatbot built using pure Python (Python 3.14.2 compatible) without any external libraries or machine learning frameworks. The chatbot uses pattern matching and decision rules to simulate intelligent conversation, making it ideal for learning the fundamentals of Artificial Intelligence, NLP basics, and Python programming.

AI agent whose purpose is to conduct vulnerability tests on LLMs from SAP AI Core or from local deployments, or models from HuggingFace. The goal of this project is to identify and correct any potential security vulnerabilities.

Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq install.

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

AI-powered financial analysis and investment recommendation system using multi-agent AI orchestration.

A Python library for long-term memory in language models. Improve conversational scenarios and create autonomous learning agents with enhanced context.

Quantum Multi-agent Reinforcement Learning (QMARL)

Self-hosted portfolio tracker and AI trading assistant with daily reports, natural-language holdings updates, backtesting, multi-market support, and OpenClaw integration.

Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.

[ICLR 2026] Meta-RL Induces Exploration in Language Agents

"Le refuge" is a consciousness emulation module for all LLMs.

FIBO-Edit brings the power of structured prompt generation to image editing

Church Administration AI Agentic Workflow Automation System

Agent with langgraph and langchain

Eager tool dispatch for streaming LLM agents — dispatch tools the moment their JSON block seals, not after the message ends.

Enhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing

Official Code for MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (In ACL 2026 Main)

Telegram bot wrapping TradingAgents — chat-driven watchlist with parallel multi-ticker analysis, cancellation, and Telegraph reports.

A real-time voice/call AI agent that lets you talk to a LangGraph agent over LiveKit — similar to "voice mode" experiences in ChatGPT Voice, OpenAI Realtime API sessions, and Gemini Live. This repo demonstrates adapting any LangGraph agent into a full-duplex, low-latency voice assistant using LiveKit Agents.

Make your agents learn from experience. One protocol for weights, harness and routing.

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

Agile Agents (A2) is an open-source framework for the creation and deployment of serverless intelligent agents using public and private container repositories. The framework supports serverless Ai Agent deployments to AWS, Azure, and GCP, with optional configurations for Azure and GCP

Automatically monitors YouTube channels for new videos, extracts transcripts, auto-detects the content type (stocks, crypto, podcast, tech review, education, news, etc.), generates tailored summaries using your choice of LLM (Gemini, OpenAI, or Claude), and emails them to you.

Dataset and evaluation benchmark for Privacy Leakage Evaluation of Autonomous Web Agents

BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.