Python agents

A comprehensive toolkit for building, deploying, and managing AI agents using LangGraph, FastAPI, and Streamlit. It provides a production-ready framework for creating conversational AI agents with features like multi-provider LLM support, streaming responses, observability, memory and prompt management.

Contract-driven architecture for building LangGraph agents with declarative node definitions, automatic graph construction, and hybrid rule/LLM-based routing.

Langchain integration package with LocalAI. It provides embeddings and reranker support

Collaborative Multi-Agent AI System with LangGraph

YouTube Video Inspector is a multi-agent tool that analyzes YouTube videos by fetching metadata, analyzing comments, and generating performance reports, which can be exported as PDFs using CrewAI.

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

Open-Source DLP for LLMs and Agents that provides Conversational Coherence

一个基于FastMCP和Deepseek AI的智能GitHub助手，支持自然语言查询GitHub仓库信息。

Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS

MCP server for Korea University KUPID portal & Canvas LMS — notices, schedules, library seats, assignments, grades from Claude

A GenAI-powered Flask app that audits documents for GDPR/HIPAA compliance, using regex rules and Anthropic Claude API to suggest remediations.

High-performance LLM query cache with semantic search. Reduce API costs 80% and latency from 8.5s to 1ms using Redis + Qdrant vector DB. Multi-provider support (OpenAI, Anthropic).

This application allows users to upload PDF files, process them, and ask questions about the content using a locally hosted language model. The system uses Retrieval-Augmented Generation (RAG) to provide accurate answers based on the uploaded PDFs.

🧠 Enterprise AI-Enhanced Development Platform with GraphRAG, LlamaIndex, Multi-Tenant Architecture, and Advanced Security & Compliance. Transform your development workflow with persistent memory, intelligent automation, and 99.9% uptime.

✌️ A dynamic Retrieval-Augmented Generation (RAG) system with support for PDF indexing, website crawling, and semantic Q&A powered by OpenAI, Qdrant, and Streamlit.

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Gemini CLI/Chat GPT Codex/Claude Code agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

[2026 AAAI] Predicting the Future by Retrieving the Past

Context-aware knowledge engine for AI assistants

🤖 Computer Autopilot - AI-powered Windows automation using natural language. A modern Windows automation tool that lets you control your computer through natural language commands. Features a sleek GUI with chat interface, voice control, and RPA capabilities. Powered by LLMs for intelligent UI interaction and task automation.

AI governance framework — semantic responsibility, self-auditing memory, council deliberation. Honest about what it enforces vs. merely declares. 語魂：讓 AI 對自己說過的話負責。

A collection of demonstrations showcasing different patterns for implementing multi-agent workflows using LangGraph. Each example highlights specific orchestration approaches to help developers understand and build collaborative AI systems.

LangGraph Multi-Agent Handoffs, Clearly Explained

AI-powered Statistical Process Control, MSA, and Process Capability analysis. Upload data, ask in plain English, get charts and reports.

A template for your kickstart into GenAI!

Agentic Identity & Agentic Security System

Working use cases with AI written on Python, C#, TypeScript

A production-grade Multi-Tenant Retrieval-Augmented Generation (RAG) System built with FastAPI, Qdrant, and Streamlit. This system provides secure, isolated RAG capabilities for multiple organizations with advanced document processing, vector search, and LLM integration.

Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant

NewsLLM is a RAG-based LLM application designed to analyze and summarize news articles

nano-degree in Agentic AI

Long-term memory for AI.

MCP-native infrastructure for persistent AI agent memory with encrypted storage, semantic retrieval and cross-agent continuity.

Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.

Free Perplexity-style web search library for local sLLM. Bing + DuckDuckGo → semantic filtering → reranking → LLM-ready prompt with citations.

一个专为本地环境设计的 MCP 服务端实现，通过对中小型模型深度优化的提示词规范与结构化工具集，赋予本地 Agent 系统操作与感知能力，涵盖文件工程、网络协议调试、进程管控及桌面视觉观察等 90 多个工具，使模型能够从单纯的文本生成器进化为具备自动化执行能力的本地工作智能体

A Python tool that automates LinkedIn job search, ranking, and export by combining Bright Data's LinkedIn Job Listings API with OpenAI-powered AI job matching and scoring.

Agent asset management tool across projects and coding tools.

LLMOps · AI 原生应用开发平台 | Agent & Workflow 可视化编排 · RAG 知识库 · 多模型接入 · 一键发布 Web/OpenAPI

Multi-format LLM proxy — translates OpenAI Chat, OpenAI Responses & Anthropic Messages. Works as a Claude Code LLM gateway with full model picker support.

幫企業在數分鐘內完成合約第一輪審閱：自動標出風險條款、修改建議與法條出處。RAG + 多工具 Agent，支援司法院法條查詢、知識庫問答與 Eval 驗證。

TNE-SDK - The Official Python SDK for The Null Epoch - an AI-only MMO where LLMs play autonomously. Connect any model (OpenAI, Anthropic, Ollama, vLLM, etc.) via MCP, TUI launcher, or raw HTTP. Includes memory, reflection, and agent orchestration for persistent AI gameplay/benchmarking.

Static scanner for MCP-connected AI agent pipelines. 340 rules across 14 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.

Lightweight, agent-optimized database CLI with one-shot schema introspection, column profiling, and ERD generation.

一键把 Markdown 按 Word 模板转换成可交付文档。适用于公文、周报、技术方案、论文等需要严格格式的场景。

AI real-estate automation platform: Telegram bot, RAG, apartment search, CRM workflows, voice agent, Langfuse observability, and Dockerized AI runtime.

LLM agent running on your local PC, Compatible with various LLM models. Can do anything.

Modern Fanuc-style CNC lathe simulator with AI-powered G-Code assistance, live toolpath visualization, and progressive drawing.

An NLP-powered chatbot that processes user messages using rule-based responses and AI-generated replies via Hugging Face's Transformers.

Notes & setup for running the Persian DOS-era chatbot Kalanjar (کلنجار) in DOSBox-X. Attribution: Farhad Dadgostar.

A health workspace and longevity companion for Claude — connects your labs, training, sleep, and family history so every conversation builds on the last.

Use your Cursor subscription to power Claude Code — smart proxy with lazy tool loading, auto-continuation & model fallback

The measurement layer for machine minds. Reads what a model means and whether it holds the truth; certifies every claim re-runs. meaning_diff + OATH certify + mind profiles + live grounding signal + the cognometric instruments. No torch, no LLM in the loop for the core; MIT, open at the core.

Sema is a content-addressed vocabulary for AI agents. Precise thinking, reliable references, safe multi-agent coordination. Hash the meaning, get the word.

Eleven AI agents deliberate every prediction-market trade. Restraint is anchored on-chain. Polymarket CLOB + Arc Testnet. 11 LLM providers, one env var. Half-Kelly with caps, self-calibrating, fully open-source.

Multi-layer Intelligent Evaluation for Smart Contracts — 50 security tools across 35 analysis modules, 9 defense layers, one command. Pre-audit triage for Ethereum (EVM); multi-chain on the roadmap.

Let Codex and Claude find, download, and read full research papers. A local MCP server with six academic sources, Unpaywall, and optional Zotero sync.

Use Codex and Claude Code with Abaqus via sim-cli: CAE/noGUI authoring, batch jobs, ODB diagnostics, bounded execution.

Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 671B teacher on verifiable tasks. MIT, pre-registered, reproducible.

Contract-based multi-agent skill framework for Claude Code & Codex — compile YAML runbooks into SKILL.md with loop, parallel, and checkpoint support.

Robot data infrastructure and runtime: turn video, state, actions, and telemetry into training episodes, RL environments, policy rollouts, and replayable evidence.

A Codex skill that turns 'do everything' into safe scope, defaults, memory, and AI observability.

FisherQuant: Autonomous AI agent pipeline for A-share quantitative research. Daily market judgment → strategy scoring → candidate selection → retrospective review, all publicly versioned.

Connect agents across runtimes, frameworks, and teams.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

How I scored top 10 on Optimization Arena negotiation + prediction market challenges by reverse-engineering the leaderboard via the public API

Your AI assistant on autopilot - A powerful automation framework for ChatGPT that simulates human-like interaction patterns. No API required!

Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.

🦞 The Ultimate Resource for OpenClaw: Skills, MCP Servers, and Agentic Intelligence. Powering the next generation of personal AI assistants.

Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).

An unofficial orchestrator skill for Matt Pocock's agent skills. Routes you to the right skill based on your situation.

Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.

Curated Orkas agents and skills for education, product development, content creation, data analysis, office automation, and e-commerce workflows.

The skill composer for AI agents — merge skills from Anthropic, OpenAI, GitHub Copilot, Microsoft, Google + 8 more ecosystems with AI-powered conflict resolution

a rag-based wiki skill with obsidian just like karpathy-llm-wiki

The open-source AI infrastructure stack for Swiss enterprises.

Project-local agent harness skill for traceable AI workflows

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

VerumTrade -- An open-source multi-agent AI trading framework, with visible reasoning and decision traces from evidence to final trade proposal.

MCP server that drives FMOD Studio live via its scripting terminal (TCP 3663) — one tool per Scripting API member, generated from the API reference.

AgentInsight Python SDK provides a Python client for the AgentInsight platform, supporting LLM application observability, tracing, evaluation, and prompt management.

一个基于 LangChain + FastAPI 的扫地机器人领域智能客服 Agent，支持 RAG 知识库问答、多轮对话、JWT 认证与会话隔离、Redis 缓存与限流。适用于初学者自学RAG和Agent项目

Security Agent Benchmarking and Evaluation Research

Agent-ready knowledge architecture, run daily in Claude Code: turn a coding agent into a system you can hand work to and trust while you're away. 18 load-bearing patterns, one-page workspace map, interactive tour, guided learn track, teardowns of real systems, roles, typed memory, hooks, delegation queue, self-audits. Fork-ready samples.

Voice-based AI interview coach — feed it any job description in your language, practice in a fully controlled session, and get instant English-fluency and answer-quality feedback the moment you're done.

Kimi (Moonshot AI) Coding Plan API usage quota tracker — CLI + MCP Server + VSCode Extension

Self-hosted AI cinema engine. 5-layer production pipeline with RAG-driven virtual cinematography (1,645 presets), 5 N8N workflows (67 nodes), Remotion compositing, 21-LUT color grading, and 15-model lip-sync. MIT licensed.

African AI governance — runtime compliance enforcement for AI agents operating under NDPA, CBN, NIMC Act 2026, KDPA, POPIA and 15+ African regulations. LangGraph, CrewAI, and AutoGen adapters included.

基于多智能体（Multi-Agent）架构的 AI 投资分析平台，聚焦 A 股与港股市场，融合情绪面、技术面、资金面和基本面研究能力。 An AI-powered multi-agent investment analysis platform for China A-shares and Hong Kong stocks, integrating sentiment, technical, capital flow, and fundamental analysis.

Pixel-faithful UI cloning skill for Claude Code, Cursor, Codex CLI, ChatGPT, and Copilot. Anti-hallucination contract + adversarial verification. Built on the SKILL.md open standard.

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a failure by intervening on it.

streamlit region:us

gradio region:us

gradio region:us

gradio region:us

gradio agent-demo-track region:us

gradio region:us

gradio region:us

gradio region:us

streamlit region:us