Python agents

Full Form : Expert Network for Intelligent Guidance and Multi-task Assistance. Using multiple LLMs, for Conversational as well as Functional Request.

Agentic workflow sandbox tailored for research tasks

CLI for Goodeye: turn business outcomes into verified AI workflows that agents run reliably.

Workshop designed for students of BMS College of Engineering on building AI Agents

F5 for your filesystem: checkpoint before every agent command, restore even after rm -rf

redteam is a multi-model harness that forces an independent reviewer to challenge AI-generated code before it ships. Apache-2.0.

GridVibe is a browser-first workspace for launching and managing multiple SSH terminals, local shell panes, agent panes, and SSH/SFTP or local repository file explorer panes from one control surface.

Local RAG assistant with FastAPI, Ollama, document indexing, sources, timings, and request IDs.

Public mirror of the bitHuman SDK — pip install bithuman. Generated/published from the private bithuman-sdk-internal monorepo. [public]

smart terminal buddy: hey to ask, hey wtf to fix

Customizable AI Telegram bot starter kit powered by Google Gemini — multimodal, self-hosted, Telegram Stars payments, Adsgram integration.

💫 Visual data pipelines with AI-reviewed transformations and live spreadsheet output, built offline-first with Polars and PySide6.

Fix the JetBrains AI Assistant + Google Gemini "Something went wrong" error. A zero-buffer FastAPI + httpx proxy for the OpenAI-compatible (BYOK) provider: strips IntelliJ's model-id prefixes, returns a clean /models list, filters unsupported params, and disables Gemini 2.5 thinking to beat the commit-message streaming timeout.

your everything-app, self-hosted — AI (aide), mail, docs, files, calendar, tasks, gallery & more on your own machine

An AI-assisted security testing workspace for authorized engagements.

Revolutionising traditional survey methods by integrating conversational AI capabilities into a web-based survey interface. This interface will not only collect responses but also interact dynamically with respondents, providing a more engaging and personalised experience.

The Student Tracking System is an AI-powered platform designed for educational institutions, providing features such as personalized dashboards, attendance tracking, class management, and real-time updates. It enhances both student and teacher experiences with smart recommendations and an AI chatbot assistant.

AI-powered real estate chatbot (OpenAI Assistant API + Streamlit): natural-language property search with AI-generated SQL. Live demo, 94% query accuracy.

This production-ready AI system automates customer support with multi-step workflows, tool integration, stateful conversations, and real-time performance monitoring.

Flavor Bot is a recipe recommendation chatbot that suggests recipes based on ingredients or dish preferences.

A personal Google Chat AI Assistant powered by Generative AI to automate and intelligently enhance daily conversations.

This an ai-based python chatbot. This an example of an basic ai program.

Metis is a conversational agent aiming to provide students support in many aspects of their studies. It is designed to be modular and support many different types of bots with different underlying architectures. Metis aims to assist the user based on the learner's personal preferences.

SoulLink - AI Soul Companion | Personalized AI chat with personality-driven interactions, multi-model support (GPT-4o & Gemini), tarot personality system

Seq2Seq Chatbot Using Tensorflow.

NOAH: Neural Oriented Artificial Human

Seq2Seq implemented by MXNET

Automated chatbot evaluation for generated natural language responses. Published in NAACL 2019 and powers chateval.org.

Source code for the AI Campus Chatbot

Телеграм-Бот проект для Яндекс Лицея 2022/2023

Maxbot transport bot example

Answer medical queries through a simple LLM chatbot rather than searching the web and piecing it together on your own

Local Chat App using Ollama, FastHTML, Redis & OAuth

Django+agent+chatbot+search

Daily Telegram channel digest with OpenAI summarisation and pluggable Markdown output adapters (Notion, Obsidian, Logseq, Hugo, files, stdout, custom).

An open-source tool to extract subtitles (.srt/.vtt) from Douyin video links via OpenAI-compatible ASR APIs. Supports batch processing and 1-click Docker deployment.

Image and video understanding + generation for AI agents -- across Gemini, OpenAI, and Grok.

Deploy an API built with Streamlit on Heroku, in order to classify images.

poc gpt-4 vision bot

Read chat log from a Twitch channel and get a natural response from OpenAI. Then use TTS to say that response for yourself and your chat's amusement.

A cutting-edge project leveraging DALL-E 3 and gpt-4o for AI-driven video generation, with FFmpeg for multimedia manipulation.

This Streamlit app allows users to upload, visualize, and modify CSV or Excel data using natural language commands, translated into python code by a custom agent powered by ChatGPT-4o. It showcases the potential of LLMs to transform data interaction into an intuitive and accessible process.

AI-powered social media content manager using OpenAI for intelligent content generation. Creates platform-optimized posts for X (Twitter), LinkedIn, and Facebook in multiple languages. Features automated content extraction, keyword analysis, and follows Python best practices with type hints and dataclasses.

I built AgentWatch to solve a problem I had: AI agents burning tokens and money behind my back. Now I can monitor everything in real-time. Feedback welcome! 🤖💸

Local monitoring center for Codex CLI sessions: rolling 5-hour quota, token usage, estimated cost, and a NOC-style dashboard.

Security-first MCP server for Odoo 17/18/19 — YAML-driven security, zero Odoo-side code, 27 tools + 5 resources + 7 prompts

Save the last 30 seconds of audio to text using ai. Send that text to a notion page, readwise, obsidian, or just save it locally in a text file.

Sanitized Codex skill for direct WeChat public-account drafting in 135 Editor.

TaskFlow AI is an intelligent daily planner that transforms natural language descriptions into structured, prioritized daily plans. Built with Flask and OpenAI GPT, it automatically categorizes tasks, estimates time, and generates optimal schedules. Features include voice input, dark mode, and responsive design.

🛡️ Autonomous DevOps AI Co-Pilot. We predict failures before they happen and fix them when they do. Powered by ML & Generative AI. 🚀🛡️

Advices from multiple agents

Production grade AI contact center starter kit with FastAPI, OpenAI tool calling, RAG, observability, Docker, Terraform, and AWS deployment

🔍 BOT that summarizes sentences in URLs sent to Discord using ChatGPT API

Raspberry Pi projects scripts .

Create articles effortlessly with Smart Words, an advanced AI-powered tool for generating high-quality content. Say goodbye to writer's block and streamline your content creation process.

A simple chat written in Python that is using OpenAI's API

Local-first analytics dashboard for Claude Code: cost, tokens, models, tools, heatmap, leaderboards & Claude Wrapped — one HTML file, zero deps, no telemetry.

An MCP server that gives Claude conversations a persistent, interactive plan/to-do panel.

Watchlist-driven intelligence pipeline crawling LinkedIn, X, RSS, and email into one neutral signals brief.

MCP server for Chinese A-share financial statements. 把 A 股财报变成 LLM 可调的工具。

Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.

Free, local-first AI gateway — unified API access to Claude, ChatGPT, Gemini & 150+ Arena models. Zero API keys. Drop-in OpenAI/Anthropic compatibility.

Drop-in LLM cost-optimization proxy. Auto-route + cache + compress + batch. Flat monthly pricing by token volume, keep 100% of savings. Free 60M tokens/mo.

Reliable, schema-validated structured extraction from documents (PDF, DOCX, CSV, email) using LLMs — built for automation pipelines.

Audit your Claude Code instruction stack — find the rules Claude silently ignores (dead, contradictory, vague, duplicate, bloated). Zero-dep CLI + GitHub Action.

Discord x Claude Code bridge via MCP (Model Context Protocol). Human-in-the-loop AI assistant integration with forum threads, real-time communication, and AI-powered title generation.

Turn complex AI workflows into reusable Claude skills. Capture the lessons to a tagged journal that survives context resets, then crystallize it into a validated skill.

A curated collection of Claude Code plugins for enhanced productivity and development workflows

My custom claude code (hopefully agentsmd soon) plugins for when I've scoured the interwebs and all the existing CC marketplaces but couldn't find anything good enough.

Imagine — bring Google Gemini into Claude Code & Codex: delegate reasoning, code review, research & automatic prompt-engineering. Runs on your Google AI Pro subscription, not your agent's tokens. MIT.

Free local Google Search MCP server — Playwright-driven, persistent Chrome profile, headless-by-default with CAPTCHA reveal

Evidence-based document extraction API for form filling. Local-first (Ollama), also supports OpenAI-compatible endpoints and Claude.

See where LLM money goes, why, and how to cut waste. Local-first FinOps + spend intelligence for Claude Code & the Anthropic API. Pure stdlib, zero deps.

Auto-recover Claude Code sessions stuck on transient API errors. Outer-loop watchdog for unattended tmux Claude Code with usage-limit discrimination, exponential backoff, and 10-retry cap. Single file, no third-party deps.

Open source PII masking middleware for OpenAI and Anthropic SDKs

Migrate LLM apps between models safely — then benchmark old vs. new to prove the upgrade. Agent skill for behavior-preserving migrations + a runnable eval harness (three-arm leaderboard, prompt sweeps). Works in Claude Code, Codex & Cursor.

My Claude Code skills. wong turns your work day into a study guide you can actually read. dormammu breaks your code until it works. agamotto summons a ruthless AI critic to tear your plans apart.

Stock analysis skill for Claude - analyst consensus, price targets, and Buy/Hold/Sell signals rendered as an interactive dashboard.

Local-first AI agent for a PM job hunt: scores roles against your CV and drafts tailored applications you review and submit yourself.

7 Claude Code slash commands + automation for Google NotebookLM. Built on notebooklm-mcp-cli. Tested on 41K-message Telegram forums, YouTube research, auto-doc notebooks for 30+ frameworks.

App-first AI framework with a built-in, governed memory engine (memory, agents, RAG, MCP)

Visual RAG pipeline searching 8.28M Wikipedia articles as screenshot tiles, matching visual layouts, and querying local Ollama LLM.

NeurIPS 2025 D&B | RAG-IGBench: benchmark for RAG-based interleaved image-text generation.

Lightweight in-process Hybrid RAG memory for local AI agents. FAISS + BM25 + time-decay, zero cloud dependency.

AI agent OS with multiple tools.

This repository is dedicated to implementing algorithms "From Scratch". It goes beyond simple API calls, diving deep into the underlying logic of everything from basic training to cutting-edge techniques like DeepSeek-R1.

12-week lab-driven curriculum: cloud/infra engineer → AI Agent/LLM engineer. Local-first MLX stack, measured engineering, every claim grounded in a runnable RESULTS.md.

multimodal retrieval engine

Universal AI Memory Layer - Cross-client, cross-repo context management with RAG. Works with Claude Code, Claude Desktop, Gemini CLI, and any MCP client.

FastAPI backend for MemexLLM with hybrid retrieval, Qdrant vector search, LlamaIndex orchestration, PostgreSQL persistence, and citations.

MCP-Server for hierarchical classification systems in official statics like COICOP, SEA or NACE

BrainTrace: GraphRAG-based on-device knowledge management system for secure and efficient document analysis

OpenAI-compatible local embedding server for MLX models on Apple Silicon.

MNEME is a temporal knowledge-graph RAG system for personal knowledge management, answering complex questions over your notes with time-aware citations. This repo contains the reference implementation from the MNEME paper and can be used with your own documents.

OpenPlex — open-source Perplexity Pro alternative for your terminal. Web search + RAG pipeline + cited answers. Supports NVIDIA NIM, Google AI Studio & OpenRouter. Runs on Termux and Linux.

Private AI for your Synology NAS — local LLM chat with optional cloud fallback. Multi-user, full Arabic + English UI, OpenAI-compatible API. Supports DVA 3221 (CUDA GPU) and DS1821+ (CPU AVX2).

Advanced RAG Assistant featuring Query Rewriting, Smart Routing, and Hybrid Parsing (OCR) using Azure OpenAI.

LlamaIndex tool integration for SearchApi.io — multi-engine web search (Google, News, Shopping, YouTube, Bing, Baidu)