Python agents

An AI functional testing project

AI Assistant for Color Harmony / Gradients / UI Design. - LLM Chat / Color Agent / OKLCH / OKLAB

BeeGen is an intelligent command-line tool designed to assist developers with everyday tasks, leveraging the power of generative AI.

Mobile-first frontend for TaskWizard — a smart AI-powered task breakdown planner. Built with Expo + React Native, connecting to a FastAPI + Ollama backend to generate actionable step-by-step roadmaps from any goal.

This Python-powered virtual assistant offers seamless desktop control through both speech and text commands, simplifying everyday computer tasks. It acts as your intuitive digital helper, allowing you to manage activities effortlessly without lifting a finger.

Iron Man-inspired AI desktop assistant | Claude API · Voice I/O · Live System Monitor · Animated HUD | Python

Visiona AI is a real-time assistive system for visually impaired users that detects objects, estimates distance, tracks motion, and predicts collisions using multiple cameras. It provides voice alerts, answers queries, remembers objects (15 min), and supports goal-based assistance.

Fraud Transaction Detector is a machine learning system that identifies and flags potentially fraudulent transactions, provides risk scoring, analytics summaries via Agentic AI, and actionable insights to help businesses monitor and prevent fraud effectively.

⚡ Enterprise B2B Transactional API. Built with FastAPI & PostgreSQL, featuring AI-powered intent extraction, robust concurrency control (pessimistic locks), and automated CI/CD to AWS.

Combining different open source AI models to form a powerful AI assistant that can perform many different tasks and runs locally.

This project is a Conversational AI application designed to interact with users using natural language. It can be used for chatbots, virtual assistants, or customer support automation.

AI-powered personal OS with autonomous agents, progressive security, custom agent creator, and multi-channel messaging

Browser-based VS Code development platform for 8 developers with AWS Bedrock Claude AI. Infrastructure as Code using AWS CDK (Python). Bangkok deployment with Singapore Bedrock integration.

Talk to AI — it talks back. Built with Whisper + Groq + FastAPI

AI-powered Microsoft 365 assistant with natural language processing capabilities for email, calendar, tasks, and document management

Self-hosted AI chat interface with RAG, long-term memory, and admin controls. Works with TabbyAPI, Ollama, vLLM, and any OpenAI-compatible API.

Client d'assistant IA pour l'API Albert de la DiNum

PyiMAi is a lightweight AI-powered CLI tool that allows you to interact with an AI model directly from your terminal, with optional image support.

AI Operating System inspired by Jarvis — modular assistant architecture with voice, automation, memory, and agent orchestration.

🧠 A fully self-hosted, universal AI chat interface powered by local LLMs. Designed for both desktop and laptop use — supports CPU and GPU (CUDA) execution. Features real-time streaming responses, clean minimalist UI, and no external server dependencies. Ideal for building your own private, offline AI assistant.

Yüksek performanslı, multimodal RAG tabanlı bir bilişsel öğrenme ekosistemi. Gemini 1.5 Pro, LangChain ve Streamlit altyapısıyla geliştirilen sistem; endüstriyel düzeyde PDF raporlama, görsel mantık analizi (Vision RAG) ve modüler çalışma alanı yönetimi sunar.

A Python library for measurement, observation, and calibrated judgment from camera images — the perception layer for human-helper AI applications.

🧠 Enhance your AI coding assistant with a universal knowledge base and rules system, compatible with any project and editor.

An MCP server that automatically fixes broken Selenium test locators when UI changes occur, reducing test maintenance overhead.

Govern and orchestrate AI coding agents — Claude Code & Codex automation with skills, approvals, notifications

abaritbot: AI assistant using RAG and openAI API.

Debian packaging and build scripts for Notolog Editor (.deb builder repo)

A smart browser-based chatbot built using Chainlit and the OpenAI Agents SDK. It handles user queries with intelligent responses and automatically stores the conversation in a JSON file. The project uses uv, a fast Python package manager, for dependency management and setup.

专为企业出差打造的智能小助手，帮你快速摸清差旅规则，轻松选合规酒店，省心安排全程行程。

Alexa ChatGPT Skill (Amazon Alexa Custom Skill with OpenAI GPT)

🚀 跨平台 Markdown 转 Word/WPS 增强工具。支持 Office/WPS 双环境、LaTeX 公式、Mermaid 渲染与复杂表格映射。高效打通 AI 生成内容与专业公文写作。 / A productivity toolkit bridging Markdown/AI content to Word/WPS with Pandoc-driven automation.

Jarvis: An offline-first, privacy-centric AI assistant for the Linux desktop. A modular, event-driven assistant featuring local wake-word detection, STT/TTS, and a hybrid LLM-powered intent engine. Designed for Fedora/GNOME.

A geometric memory database with importance-stratified shells, HNSW acceleration, and mass-weighted decay scoring. Zero to hero: SQLite → 10M+ records.

Modular Python framework for building workflow automation systems that combine tools, AI assistants, and persistent memory. Define sequential workflows to automate tasks step by step, with optional human checkpoints.

Deliver production-ready Flutter UI components designed for AI coding assistants to create polished, user-friendly apps efficiently.

A general-purpose SQL tool for Strands Agents — supports PostgreSQL, MySQL, and SQLite via SQLAlchemy

A modern desktop application for managing and organizing AI prompts with dynamic variable substitution. Built with Python and Flet.

Deterministic stateful governance for AI agents and agentic systems

Static analysis engine that maps any codebase into ranked, token-budgeted context — offline, zero LLM cost

Convert any code repository into a single markdown file for NotebookLM and other LLM tools.

Vision AI "Cortex" for Agents. A Playwright-based MCP Server & API that captures screenshots with ground-truth DOM extraction and full auth state injection. Containerized.

SmartEdu AI V2 is a lightweight system that turns your study materials (PDF/DOCX/PPTX) into simple, meaningful multiple‑choice questions (MCQs). It uses a Retrieval‑Augmented Generation (RAG) pipeline built around Google Gemini for both embeddings and text generation, with a minimal in‑memory vector store for fast, local retrieval.

Production-ready MCP server template with async PostgreSQL, OpenTelemetry observability, tool-level security, Docker and Kubernetes Helm chart. Zero to deployed in 10 minutes.

Win系统剪贴板AI增强：面向 Windows 的剪贴板增强工具，支持历史、托盘、热键、Prompt 优化与图片基础操作。

Thordata Firecrawl – Firecrawl-compatible web crawling & scraping API built on Thordata, turning any website into AI-ready Markdown/JSON/HTML/screenshots.

Claude Code skill for Solidity smart contract security audits - OWASP SCSVS/SCSTG coverage, Slither integration, 11 security domains. By Demeter Financial.

Production-grade Claude Code plugin: control your personal Telegram via MTProto (Telethon). 120 typed MCP-tools, 9 resources, 7 prompts, 6 skills, 4-layer PreToolUse safety net, channel-push & permission relay

A Claude skill that rewrites LinkedIn profiles against a target JD with rubric-based refinement. Grounded in real competitor profiles, scored across five dimensions, voice-preserving.

SQL-like DSL for Chroma DB

use local LLMs to do Retrial-Augmented Generation with local Chroma, function calls and tool usage

Self-learning memory for AI coding agents — MCP server

Deterministic /compact alternative for Claude Code. Compresses JSONL sessions 4-10% without LLM summarization. Zero hallucinations, full error preservation.

Braindler: Internet-Enabled AI for Real-World Tasks, Goal Achievement, and Human Communication

Open-source middleware that aims to let any AI agent (OpenClaw, LangChain, AutoGPT) securely connect to any API, database, or enterprise system via YAML config. Features 22+ adapters, zero-trust security, EU CRA compliance engine, MCP gateway, React dashboard, and OpenClaw plugin support.

Simple Document Reader, give it a link and it will automatically fetch all the data and give you answer to questions from the docs

BabyAGI + LangChain w/ Tools

Autonomous coding agent — a sentence in, a validated app out. Resilience stack with operational gates, completeness CRITIC, runtime flow verification, surgical-mode stuck-loop recovery, and progressive tiers. Compatible with any OpenAI-compatible LLM.

Tamper-evident audit logging for OpenClaw and other local AI agents: hash-chained, locally verifiable, zero cloud dependency.

Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.

ASTRA — Autonomous Spaceflight Trial & Research Agent: one line of natural language → a flown Kerbal Space Program 1 mission (design, fly, diagnose, retry). Flew a full Artemis Moon campaign live.

AI-Powered Meme Token Scanner with LLM Agent, Base Chain Wallet Integration & Token Usage Analytics

AstrBot 宿主上的多 Agent 编排内核：TaskAnalyzer → AgentCoordinator → SubAgent 三级调度 + MCP Bridge + Shipyard 沙盒；435 单元测试 / 99% 覆盖 / ruff+mypy+bandit 全绿

The open-source Fable alternative — a zero-dependency harness that makes ANY LLM verify instead of assume, persist instead of quit, and reuse before reinventing, with a local failover floor you own.

LLM projects can be directly used or added to organization

🐙 Meet Octopus AI: Because Two Hands Just Aren't Enough Let’s be honest: being a human is exhausting. You only have two arms, one brain, and a desperate, daily need for caffeine.

Local-first LLM agent with native/prompt tool calling, memory, streaming and OS automation.

🤖 Explore AI agent architectures with agentic-ai, featuring ReAct agents, reflection-based designs, and modular LLM integrations using LangChain and LangGraph.

Production AI agent quality gate and risk control framework for LLMOps, agent evaluation, regression detection, gray release, audit, and observability

Palimpsest is an LLM-assisted semantic code enhancement framework that bridges Ghidra decompilation and CodeQL database construction. It is optimized for IoT device firmware analysis and for generating CodeQL-buildable source code.

Embed and edit videos directly within ComfyUI workflows using the OpenReel extension with timeline, effects, and server-side rendering.

A ReAct-based AB test analysis agent with memory, docs retrieval, routing, fallback, and evaluation.

AI-assisted music production pipeline: LLM agent + Python DSP tools for recording prep, mixing, mastering, and analysis

Autonomous local AI recruiting agent that scrapes jobs, scores compatibility, drafts personalized application pitches, and tracks your pipeline via Telegram. 100% free, private, and offline.

Lightweight open-source toolkit for evaluating tool-calling AI agents on safety, correctness, and reliability

🤖 Build intelligent, offline LLM agents with LangGraph and llama-cpp-python using this starter template for local, private tool-calling applications.

RAG-based internal knowledge copilot for fintech support, providing grounded answers with source citations and safe refusals.

Drive Claude Code on your Mac from your phone: list and resume every session, start new tasks, stream results live.

Feed LLMs financial data and interactive charts in one call — an MCP server for A-share quotes, financials, and macro indicators, 42 tools with results-as-UI.

面向 Crypto 市场研究的 Agent Skill：现货、合约、链上与协议证据解析

If you can read ~100 lines of python, you understand agents

Multi-agent orchestrator that runs a hierarchical engineering team (Product → EM → Tech Lead → specialists) on top of locally-installed Claude or Codex CLIs.

Open-source, self-hosted evaluation and governance platform for multi-agent systems

Recoverable long-horizon AI agents — a framework-agnostic reference harness + recovery-faithful live benchmark. Thesis: "Checkpoints Are Compactions" via Re-grounding Recovery. 0.x: v1.0 held until a powered live-LLM study confirms the claims.

POLO: Preference-Guided Multi-Turn Reinforcement Learning for Sample-Efficient Lead Optimization (KDD 2026 Oral)

Voice-based coding assistant speak commands, get AI work + narrated feedback in real-time

UAHP v0.5.4: Solving the "Silent Agent" Problem with Death Certificates and Liveness Proofs

The ultimate open-source, local-first AI agent for job search. Find, score, tailor, and track career opportunities using a multi-agent self-correcting QualityCritic loop.

llmpress reduces the token cost of sending source code to an LLM by detecting repeated patterns, replacing them with short aliases, and transparently restoring the originals in the model's response.

Auto-course is multi-agent system for generating academic content - inspired from auto-slides (https://auto-slides.github.io/)

Computer Use for Windows - without the screenshots. Element-based MCP server: UIA + Win32 + CDP, 3-tier fallback ladder, ~ms per command.

An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.

H-SPAE AlphaAgent: session-persistent harness for LLM-driven alpha factor mining with memory, resume, context compression, and reproducible artifacts.

Multi-tool AI orchestration that researches its own success criteria before acting, validates them after, and earns autonomy from track record. Orthogonal to single-agent frameworks.

Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).

B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs

LLM travel-deal agent with structured output, evidence grounding, and agentic planning - each shipped with benchmarked before/after reliability gains.