Python agents

The missing governance layer for AI agents. Declare what your agent can do, what requires human approval, and what it can never do - before it runs. Runtime enforced via scyvera, not just documented.

Python SDK for Fly.io Sprites: computers for agents. Sprite management, remote command execution, filesystems, checkpoints, services, and network policy from Python.

Local-first runtime for observable, debuggable AI-agent workflows with slidable autonomy and multi-agent/tool orchestration.

The Zero-Trust Runtime Security & Governance Layer for Autonomous AI Agents.

The Graph Search Engine for Your Knowledge Base

Answers you can judge and act on without reading code — Claude Code plugins that keep implementation detail below a marked line. Off by default, armed one session at a time.

PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game? (EMNLP 2026 Findings)

Agent Skill that turns your coding agent into a keyboard firmware expert. Audits ZMK/QMK keymaps, tunes home row mods, makes trackballs layer-aware, generates keymap diagrams with CI, adds alt layouts (Graphite, Colemak-DH), and debugs the failures the docs don't cover. Works with Claude Code, Codex, Cursor, Gemini CLI and more.

A curated collection of skills for AI agents to properly work with datavault4dbt.

Convert your ChatGPT export into readable, searchable files. Built for everyone who deserved better.

Decide-then-code. A Claude Code plugin that teaches every load-bearing decision, records your choice, and blocks code from moving past a decision you have not made yet.

Source-grounded public context for 课代表立正: Knowledge Bank, YouTube, Public Axioms V1, and 《真本事》 frameworks.

Python + Terraform. Cloud-ready GraphRAG solution that uncovers distant connections across data and grows incrementally as new documents arrive.

Extends Gephi with AI capabilities. Includes a Gephi plugin for graph analytics, an MCP server bridging AI assistants and Gephi, an agentic AI plugin with slash commands and workflow skills, and a specialized agent for network analysis research. Built for researchers working across network science and AI.

⚖️ VerdictAI — Multi-agent courtroom debate & verdict system. 7 AI experts cross-examine real case PDFs, cite real statutes & precedents, and deliver structured verdicts with executable next steps. FastAPI + LangGraph + WebSocket.

亚马逊评论分析 Agent Skill：卖家精灵 Review 表 → 一/二/三级分类树（格子里是买家原话）→ HTML 看板 + 交付 Excel

Real-time, async multi-agent orchestration system built on the Actor Model for IoT use cases with MQTT pub/sub.

A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choice, local or not.

MCP server for Apple Mail: sub-ms search over 300k+ messages via Mail's own SQLite index, verified sends, Exchange body backfill, triage plan/review/apply. 849 tests, MIT.

Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patterns. Production-tested from 1,200+ hours of ops. Updated daily.

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates professional PWNDoc reports with integrated YARA and Sigma rule.

OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.

Open-source full-stack AI agent with an embeddable React UI and FastAPI runtime. Self-host with streaming, pause/resume, durable state, and parallel multi-agent subtasks.

Recoverable and auditable deep-research agent built with LangGraph. It plans research, searches the web, manages evidence and context, resumes interrupted runs, and generates cited reports—also designed as a learning reference for AI Agent enthusiasts.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.

Multi-account and usage manager for Claude Code and OpenAI Codex - switch logins, track quota, auto-rotate before rate limits

Deterministic CI scanner and surface-risk scoring for MCP (Model Context Protocol) servers.

Jeevan Setu is a sophisticated multi-agent AI system built on the crewAI framework, designed to predict patient surges and optimize hospital preparedness.

Private ChatGPT Desktop Webview app made with QtWebView.

ContextQA - The open-source tool for data-driven conversations

Vector databases for generative AI

Minimalist Context Management for message-based GPTs

This project demonstrates how to parse emails, process them using OpenAI's GPT-3.5, and load the data into a Weaviate vector database for enhanced search capabilities. Utilizing few-shot prompts and parallel processing, it showcases the power of combining NLP techniques with vector search.

A FastAPI application that relays client WebSocket connections to OpenAI's Realtime API, enabling seamless integration for real-time speech-to-speech interactions

Send prompts to OpenAI GPT models from your favourite launcher

DiskRAG is a high-performance vector search system built on top of DiskANN.

🤖 World's first AST-powered AI development agent | Autonomous Django/Flask builder | Zero-token intelligence | Military-grade sandbox | Made in India 🇮🇳

A visual, editable context layer for Codex. AI edit AI's context with surgical precision, giving you more control and freedom over what Codex sees.

Shared memory bus for MCP-compatible agents with permissions, subscriptions, and optional payments.

AI Agent Tools library for Graphlit Platform

AI agents that work while you sleep - schedule workflows, automate tasks 24/7, integrate with Automagik Suite and LangFlow

Using langchain framework created some useful Ai applications.

Lightweight, decoupled RAG evaluation scaffold (dataset → vector store → RAG workflow → evaluation) with a Qwen-based demo.

LLM as Agent

AI-powered chatbot that provides guidance using YouTube video content as a knowledge base. Built with RAG architecture using LangChain, Qdrant, and Google Gemini AI, ElevenLabs and Streamlit.

This script is a chat application that allows users to ask questions about multiple PDF documents implemented with meta's LLAMA2

AIPE (AI Pipeline Engine) is a flexible and powerful tool for creating and executing complex AI workflows

Python SDK for vishwa.ai

🔍 GemInsights: Unleash Gemini AI on your data! 🚀 Analyze dataframes for valuable insights, replacing traditional data analysis. 📊 A cutting-edge tool revolutionizes the way you analyze dataframes, offering a paradigm shift from conventional data analysis methods.

Testbed for multimodal retrieval augmented generation techniques with FiftyOne, LlamaIndex, and Milvus

A Flask Server Demo Application showing off some llama-index LLM prompt magic, including file upload and parsing :)

[ACL 2026] CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy

CogNetX is an advanced, multimodal neural network architecture inspired by human cognition. It integrates speech, vision, and video processing into one unified framework.

Control local Codex and Claude coding agents from your phone via Telegram — review plans, approve bounded work, inspect diffs/tests, and keep receipts.

Prompt Assembly Language - A framework for developing LLM prompts as versioned, composable software artifacts

ZyronixBot [WA Multi Device] is a WhatsApp based third party application that provide many services with a real-time automated conversational experience.

🤖️🐱 一个基于 Rasa 的中文聊天机器人——「锅贴」

A user-trainable Knowledge Base / FAQ Slack Bot on AWS SAM based on ChatGPT and Embeddings.

An interview digital assistant built with OpenAI GPT3

Powered up by Lex, Polly, Lambda, S3 and some sentiment analysis, the Shakira chatbot will make you move your hips.

Chat-bot for vk.com

NaverTalk Python Library(네이버 톡톡 파이썬 모듈)

Open-source Search GPT engine

Geppetto: Advanced Slack bot using multiple AI models for interactive conversations and creative image generation. Enhances Slack with automated responses and intelligent dialogues, supporting flexible model management and Docker deployment.

微信自动回复机器人

Automates chat replies for Messenger and WhatsApp using PyAutoGUI for UI actions, Pyperclip for clipboard capture, and Groq for AI responses. Cycles configured chat positions, skips replying to your own messages, supports dry-run and logging, and includes cursor tools and easy config for fast testing and demos. Ideal for portfolio demos & research.

An AI chatbot for the Matrix chat protocol which can assume any personality imaginable

Python library to open/close applications in windows.

PyTorch version for Sequential Matching Network

Script that automates Cracking Sora invitation codes by Brute force

A Deep Learning Approach leveraging Transformer style Architectures for signal classification

A connector between OpenAI's GPT-3 and Facebook Messenger.

Deeplot 聊天即绘图

Summarize text content into a Tweet-sized statement using OpenAI's GPT-3 based Davinci model

Translate English to SQL and Python Pandas with OpenAI's GPT-3 Codex model

Pythoness: use natural language to define Python functions.

A Youtube video summarizer using ChatGPT and Youtube APIs. Generate a short mp3 file of the summarized video in ANY languages with only a Youtube link.

Embedded AI search engine for code

Lunary AI Python Client (Analytics, monitoring and evaluations for GenAI apps)

Automatically convert functions to schemas for LLM function calling.

NLP command-line assistant powered by OpenAI

An AI-powered git commit message generator written in python.

Source-linked project history for AI work across nine tools. Local PostgreSQL, one-click processing, and per-purpose local, API or CLI models. English/German UI.

End-to-end natural language to SQL system: schema-aware model fine-tuning, retrieval-augmented prompting, and easy-to-use CLI, powered by a custom fine-tuned Phi-4 Mini.

AI agent for enhancing datasets with information from the internet

API-first variant triage pipeline combining genomic filtering, annotation, and LLM-driven interpretation for clinical genomics workflows

Universal Agent Messaging — encrypted agent-to-agent communication protocol

Stateful AI Agent for Knowledge Extraction

AI orchestration framework for structured multi-step workflows with validation - build reliable smart contract security analysis and beyond

About Modular AI assistant — 60 built-in tools, multi-provider LLM support (Ollama, OpenAI, Anthropic, Gemini), hybrid memory, WhatsApp/Telegram daemon mode

⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex.

IAttorney is an intelligent legal assistant built using Flask, LangChain, FAISS, OpenAI, and a RAG (Retrieval-Augmented Generation) pipeline.

Using AI agents to research customers and write them personalized sales emails

Stop runaway LLM agent costs

A file-based Command Protocol enabling Claude Code to trigger Unity Editor operations. Built for multi-agent and highly parallelized workflows.

Home Assistant custom component that gives OpenClaw access to your smart home

Amazon Bedrock Q&A multi-modal chatbot with advanced RAG

It is an artificially intelligent chatbot which can interact with customers with voice.