Python agents

Starter App to Build Your Own App to Query Doc Collections with Large Language Models (LLMs) using LlamaIndex, Langchain, OpenAI and more (MIT Licensed)

[ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

ArgusBot: A 24/7 supervisor Agent for Codex CLI and Claude Code CLI that keeps agents running, reviewing, and planning until the job is actually done.

🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat, Dream consolidation and calendar-level summaries · AI 伴侣记忆网关：向量搜索、记忆热度、Dream 睡眠整合、日历层级摘要，任何客户端都能接

This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT (speech-to-text) to enable voice and vision-driven conversations, with additional web search capabilities via OpenAI and Langchain agents.

Standardized environment infrastructure for Agentic AI development.

A multi-agent AI trading system using LLMs to optimize strategies and adapt to market conditions in real-time.

A collection of enhancements, plugins, and prompts for Open WebUI, developed and curated for personal use to extend functionality and improve experience.

Vigil: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.

Run MemGPT-AutoGEN-Local LLM Together

中文智能客服机器人demo，包含闲聊和专业问答2个部分，支持自定义组件（Chinese intelligent customer chatbot Demo, including the gossip and the professional Q&A(FAQ) , support for custom components！）

ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://arxiv.org/abs/2311.09835)

Train embodied agents that can answer questions in environments

[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents

A powerful dataset generator for Rasa NLU, inspired by Chatito

Smart Python Agent Development Environment

Blockify: Agentic data optimization for enterprise RAG and agentic search. Blockify replaces naive chunking with deduplicated IdeaBlocks — ≈78X accuracy aggregate improvement, 2.29X vector search accuracy, 40X compression, 3.09X token efficiency. Integrates with LlamaIndex, LangChain, Obsidian, Milvus, Elastic, Supabase, Cloudflare.

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

A GPT-4 powered AI agent that can create full projects with iterative prompting

PC Agent: While You Sleep, AI Works - A Cognitive Journey into Digital World

[EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

Human-taught Computer-use Agent Designed for Real Windows and MacOS Desktops.

Memory Palace is a long-term memory operating system purpose-built for AI Agents.

Claude Code 免杀 SubAgents

Python functions powered by AI agents - with runtime post-conditions for reliable agentic workflows.

Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model Context Protocol (MCP) to expose ERPNext functionality to any compatible Language Model

Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo character; built to be operated end-to-end by an AI agent.

A complete voice AI building block with telephony integration, featuring real-time speech-to-text, text-to-speech, and LLM-powered conversational agents.

A completely private, locally-operated Ai Assistant/Chatbot/Sub-Agent Framework with realistic Long Term Memory and thought formation using Open Source LLMs. Qdrant is used for the Vector DB.

Conversation models in TensorFlow. (website removed)

Tools to build web AI agents that can authenticate, interact with and extract data from any website.

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

Illuminate your data. Agent framework turning natural language into SQL, charts, dashboards and reports.

Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit

One-click Railway template for Hermes Agent. A web admin dashboard for provider/channel setup, gateway supervision, user pairing, and backup/restore, with the native Hermes UI proxied behind one login.

A simple Python sandbox for helpful LLM data agents

Marco Search Agent for Realistic and Challenging Agentic Search

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration...

Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts

wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk

[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.

SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving

🧠 Second Brain AI agent

Scale your compute with Claude Code as a programmable agentic coding tool

Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.

这是我开发的一个基于大模型的小红书内容运营智能 Agent 系统。 该系统可以实现从数据采集到内容生成，再到自动发布的完整流程，主要功能包括： 使用 Playwright 爬取小红书热门内容 分析爆款规律（关键词、标签、标题结构） 基于分析结果自动生成选题 使用大模型生成完整文案（标题、正文、标签、互动语） 调用图像模型生成配图 支持通过 API 或 MCP 一键发布内容 技术栈包括： FastAPI、LangChain、OpenAI（GPT + 图像模型）、Playwright、Pydantic 等。 该项目的核心思路是将数据分析与大模型生成结合，实现内容生产的自动化与智能化。 适用于： 内容运营、自媒体自动化、AI Agent 应用开发等场景。

Open-source AI real estate search with RAG, vector search, multi-provider LLMs, FastAPI, Next.js, ChromaDB, and a live demo.

不教 PUA，只教真心。Win your crush before it's too late. Inspired by colleague-skill（同事skill）

Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...)

Multi-agent AI prediction engine - digital sandbox for scenario simulation (fork of 666ghj/MiroFish)

A python-based chatbot for Mattermost (http://www.mattermost.org).

Record and Replay AI Agent Trajectories.

A benchmark for evaluating AI agents on realistic business workflows

SRE reliability instrumentation for agentic AI — DQR, TIE, HER, AQD

Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x

Agent trace and tool-use safety evaluation lab.

MCP Server for Tree-sitter

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts. Cloud LLMs or fully local via Ollama.

200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.

transformers safetensors llama text-generation facebook meta

A self-evolving multi-agent system for autonomous research, operating 24/7 to explore, learn, and improve.

Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms

An intelligent Wiki overlay tool designed specifically for gamers, featuring GEMINI-powered RAG (Retrieval-Augmented Generation) capabilities for smart Q&A services.

A Text-Based Environment for Interactive Debugging

GroupMe Discord and Slack Chatbot for ESPN Fantasy Football

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

shareAI Lab's skills for agent to build agent & other custom software system

Multi-agent team orchestration skill for Claude Code. Set up parallel AI agent teams with file-based planning and role-based collaboration.

🔁 Improve your agent harness autonomously overnight

Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation

Multi-agent AI prediction engine - digital sandbox for scenario simulation (fork of 666ghj/MiroFish)

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Local-first AI Skill and Agent for creating original Douyin and TikTok story scripts with a searchable SQLite reference database.

Curated Blender + Seedance workflows for AI filmmaking: previs, camera control, Blender MCP, reference video, and agent-guided use cases.

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. Includes a live web dashboard for managing memories, logs, and sessions. MCP connects over HTTP & STDIO and works with major LLMs like Claude, Codex, Grok, Gemini, and other models.

Claude-Code-Multi-Agent驱动的新一代AI编程助手生态系统，基于Claude Code构建的智能代理协调工作空间，实现从需求到交付的全流程自动化开发

Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.

Give your AI agents the skill of visualizing data the way Edward Tufte intended.

An Excel AI agent that uses MCP tools to let LLMs read, edit, and automate Excel spreadsheets.

Context is yours. Agents are replaceable. Orbital — a project agent that turns your context into assets.

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

Extract Bilibili videos into learning-oriented Markdown notes with full subtitle and comment archives

transformers safetensors minicpm feature-extraction agent text-generation-inference

transformers pytorch safetensors llama text-generation llama-2

专为数学建模竞赛设计的数模 Agent Skills：MCM/ICM 美赛、CUMCM 国赛、华数杯、M3、HiMCM 等，面向 Claude Code 与 Codex 的获奖级建模工作流。Math modeling contest skills for Claude Code & Codex.

A multi-agent AUTO Research loop for idea discovery, experiment execution, evidence-grounded paper writing, quality audit, and live Web observation from AI group, CNIC, CAS.

Your AI is trapped in apps. We set it free — Self-hostable AI stack for multi-user, multi-agent workflows on Matrix.

Text2Text Language Modeling Toolkit

Community developed integrations and plugins for the Datadog Agent.

"Is karma really that important to you? Damn bro, you need a life" - YouTube Comment

Automate the tedious development tasks with AI

Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.

Deep research tool for local knowledge base.

面向 AI Agent 的可溯源 A 股板块研究 Skill，贯通政策、权威媒体、市场资金、公司与 ETF，支持实时查询、研究编排和二次应用开发。

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.