Python agents

An assistant for Slack built with Arcade and Langgraph. Interact with Google Calendar, Mail, Github, Search Engines, Firecrawl and more all from within Slack

A tool for comparing tokenizers

📹 Collection of my Youtube Tutorials over the years! Read, write, and share what you create ✨🎈

DocumentGPT is a web application that allows you to chat over your research document using OpenAI's chat API and perform semantic search using vector databases. This tool provides a seamless interface for interacting with your research document, exploring search results, and engaging in a conversation with an AI chatbot.

TensorSwarm: A framework for reinforcement learning of robot swarms.

[EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering

HexAgent – An Agent harness that gives any LLM a computer to complete tasks the way humans do

Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games

Examples of Chat Bots using Panels chat features: Traditional, LLMs, AI Agents, LangChain, OpenAI etc

Python Agent DEvelopment framework

An assistant for Slack built with Arcade and Langgraph. Interact with Google Calendar, Mail, Github, Search Engines, Firecrawl and more all from within Slack

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.

Scalable and extensible reinforcement learning for LM agents.

Paper Arxiv 2026.02 Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

(WIP) Open Knowledge Layer(OpenKL): The Advance Knowledge and Memory for Personal Agents.

Ask questions about your Obsidian notes using local AI. Privacy-first RAG with Ollama, LM Studio, or any OpenAI-compatible server. Obsidian plugin + Docker + PyPI.

Home Assistant add-ons by Robson Felix. Includes Claude Code - run Anthropic's AI coding assistant directly in Home Assistant to create automations and manage your smart home.

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

(ICML 2026) Self‑Evolving LLM Agents through an Experience‑Driven Lifecycle

Agent Skill that turns messy notes into rendered strategy-consulting visuals, with SVG examples and validation.

transformers pytorch llama text-generation text-generation-inference endpoints_compatible

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.

FACET (Feature‑Aware Contracted Extension for Text) is a human‑readable, machine‑deterministic markup language for AI prompting, orchestration, and tooling

Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadashy)

This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Global Reward Games''.

[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

Local Reasoning Agent using LangChain + Ollama

A live benchmark and evaluation framework for open-ended deep research in the wild.

Integrate Open-AutoGLM's Android & iOS GUI automation into DeepAgents-CLI via LangChain Middleware, combining LLM orchestration with vision-guided GUI control.

Source codes for paper "MACRec: A Multi-Agent Collaboration Framework for Recommendation" at SIGIR 2024

[RAG训练营] u.geekbang.org/subject/airag/1009927 这是我用Cursor自行制作的RAG Framework，好处是可以掌控RAG每一个环节的教学细节。

S3, PostgreSQL, Azure Blob, GCS, MongoDB, and Redis remote backends for LangChain Deep Agents

AI Agent Skills for Security Auditing to generate triaged, industry grade report findings, code locations, pocs, attacker story flow graphs and more

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

A Simple Baseline for Video World Models with Memory

General Purpose Evaluation and Simulation Environment for all your AI related Workflows

Implementation for Decentralized Multi-Agent Systems with Shared Context

transformers gguf llama facebook meta pytorch

transformers safetensors deepseek_v2 text-generation conversational custom_code

A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."

Auditable AI agent for electromechanical maintenance with LangGraph, RAG, fault diagnosis and human-in-the-loop review.

Kernel-enforced authority and spend platform for AI agents

OpenCMO: An open-source, multi-agent AI Chief Marketing Officer built with OpenAI Agents SDK & Crawl4AI. Your BYOK alternative to $99/mo AI marketing agencies.

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

Claude_api is a Python package that provides a convenient way to interact with Claude 2 from Anthropic.

Remove Watermarks from SORA 2 Video Generations with LaMA inpainting. (RESEARCH AND EDUCATIONAL USE ONLY)

The simple yet powerful long-term memory manager between AI and you💕

Designing Multi-Agent Systems with Zero Supervision

OpenAI Python Library Tutorial by Datalumina®

A Simple, Distributed and Asynchronous Multi-Agent Reinforcement Learning Framework for Google Research Football AI.

Self-Hosted AI Agent for Kubernetes & DevOps. Approval-Gated. Deterministic Control Loop.

A Python CLI to test, benchmark, and find the best RAG chunking strategy for your Markdown documents.

Minimal and educational implementation of an LLM agent.

⚡ A local, privacy-focused AI desktop assistant for Windows. Control your PC remotely via Telegram or locally with Voice commands. Powered by Ollama.

🐤🐧 A declarative and highly modular Blackboard Multi Agent System 🐓 🦆

QuantConnect Algorithmic Trading Platform Orchestration MCP - Agentic LLM Driven Trading Strategy Design, Research & Implementation

A sophisticated multi-agent AI system for analyzing Indian NSE-listed stocks using real-time data, technical indicators, news sentiment, and advanced AI reasoning.

AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

MCP server for AI assistants to read and manage Coros fitness data: sleep, HRV, daily metrics, activities, and structured workouts via the unofficial Coros API

AgentRE-Bench is an agentic benchmark that evaluates state-of-the-art models on long-horizon reverse engineering tasks, measuring their ability to analyze binaries, use tooling effectively, and reason over multi-step execution artifacts

A library of Claude Code skills for teaching coding agents how to use various CAD tools

⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 | Approve your AI coding agent's risky actions from your Apple Watch, get buzzed when tasks finish

Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skill, reproducible benchmark.

Ready-to-use customizable multi-agent AI system with Telegram integration. Combines plug-and-play simplicity with framework-level flexibility.

A Discord Bot for chatting with LLaMA, Vicuna, Alpaca, MPT, or any other Large Language Model (LLM) supported by text-generation-webui or llama.cpp.

Simple cross-LLM AI Agent library

A framework for generative software.

🤝 The code for "Can Large Language Model Agents Simulate Human Trust Behaviors?"

Traefik with all the stuffing. Onramp is a docker compose setup designed to allow users to get up to speed quickly and securely using Traefik, LetsEncrypt, Cloudflare Tunnels and other popular self hosted home lab services.

An ever-evolving introduction to ChatGPT, AI, and machine learning (including prompt examples and Python-built chatbots)

mini-OpenCode is a lightweight experimental Coding Agent inspired by Deer-Code and OpenCode. It explores how LLMs can plan, reason, and iteratively write code with minimal infrastructure, aiming to provide a simple, hackable foundation for understanding and building agentic coding systems.

集成数据分析、流程图生成、浏览器自动化、视频内容总结、服务器监控、智能图表六大智能体，支持自然语言交互和智能路由。

A library of components to help agent builders boost their agent performance (tool-calling, instruction following, policy, etc.)

Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

A multi-model autonomous agentic engineering pipeline driven by linear. Claude + Codex + Linear

A Multi-Agent Framework for Writing Novels with Claude Code

人格蒸馏引擎 · 蒸馏自己看清自己，蒸馏亲友留住余温与回声 · Claude Code Skill

Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"

You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command.

An LLM-powered agent for Datasette

A toolkit for turning internship materials into resume-ready bullets and interview-ready project narratives, with achievement auditing, JD-based ranking, AI-heavy phrasing checks, and structured interview prep outputs.

AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI & skill for Claude Code, Cursor & AI agents.

AgentKernelArena provides an end-to-end siloed-benchmarking environment where different LLM-powered agents—such as Cursor Agent, Claude Code, Codex, SWE-agent, and GEAK—can be evaluated side-by-side on the same GPU kernel tasks, using objective and reproducible metrics.

gradio agent-demo-track region:us

transformers safetensors llama text-generation conversational arxiv:2506.03524

Reproducing and studying RL algorithms for LLM agents, including PPO, GRPO, GSPO, DAPO, OPD and beyond.

Run OpenClaw on a local model. Zero API cost. One OpenAI-compatible endpoint over Ollama, llama.cpp, vLLM or LM Studio — plus AirLLM for models bigger than your GPU.

An open-source agentic framework that enables AI to use computers like humans and can provide a multi-agent runtime environment as an infrastructure capability