Python agents

SYNAPSE: AI-Powered Intelligence Aggregation & Automation Platform

Autonomous AI agent that acts as your digital representative, privacy-first, risk-aware, human-in-the-loop

Extract text, answer questions, and pull structured data from PDFs and scans with local RAG and OCR for German and English documents

Reliable RAG with built-in RAGAS evaluation. A tutorial-style LangGraph pipeline: Grade/Verify/Trace gates, hybrid retrieval (dense+BM25), per-gate cost tracking, and LangSmith tracing.

Give your Python objects the ability to think and act — no glue code, no prompt engineering.

🔍 Market-Rover – AI Stock Intelligence for Indian Markets – reduces cognitive load for drive-by visitors

An open-source, self-hostable, multi-user, multi-persona, security-hardened agentic OS.

Code for paper "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views"

Geometric framework for extracting structure, transitions, and stability from dynamical systems.

Local multi-agent workspace with Hermes orchestration, role-based AI agents, memory, scheduling, Skills, MCP, terminal, files, and HTML preview.

Polymorphic Agent Swarm Architecture: model-agnostic, self-organizing multi-agent system with 6 topologies, 1,095+ tests (adversarial, chaos, e2e, integration, performance, MCP, Ray), 18 completed phases.

AgentRearrange is a Swarms orchestration primitive that turns a tiny string DSL (-> for sequential, , for concurrent) into arbitrary mixed-topology multi-agent workflows.

An open-source AI agent platform that does the work for you.

A high-performance, multi-agent observability engine designed for the Model Context Protocol (MCP). It provides a non-blocking, transparent proxy layer that implements deterministic token attribution, real-time context-window alerting, and heuristic-driven static analysis to optimize LLM metadata overhead at scale.

Resume Tailorator is a sophisticated multi-agent AI system designed to analyze job postings and tailor your resume to match specific job requirements. It ensures authenticity, avoids AI clichés, and optimizes for Applicant Tracking Systems (ATS).

BuddyDesk — Windows 桌面 AI 伴侣：灵动岛 + 像素橘猫 + 命令执行。纯 Python/PySide6。

A RAG-based conversational AI for knowledge seekers and autodidactic learners.

Génération automatique de débats politiques par IA. Audio + vidéo.

Telegram AI userbot. Answers in groups and PMs from personal account

Free offline AI chat for Windows. Llama 3.2 3B model. No API keys, no censorship, no internet required. 100% private.

LEO BOT: the AI for Chatbot, Marketing Automation and Personalization Engine

Thin Integration Harness Engine for SMEs — decouple Shell, Brain, and plugins via OpenHarness. Headless, contract-first orchestration. Not an Agent framework.

🤖 Power your chats with BarkSuckerbird, a versatile Telegram bot that uses AI models and live web search for instant insights and support.

A command-line base Gemini client

🌐 Self-hosted, offline-capable personal intelligence platform. 3D globe with live aircraft/vessel/satellite tracking, OSINT feeds, memory-linked AI chat powered by your own ChatGPT conversation history exports (ChromaDB + Ollama), and autonomous investigation — all running locally with zero API keys required.

This is a Generative AI powered Question and Answering app that responds to questions about your uploaded file. Here we utilize HuggingFaceEmbeddings and OpenAI gpt-3.5-turbo

Model Context Protocol (MCP) server for LightRAG - 30+ tools for RAG and Knowledge Graph operations. Easy installation via npx or uvx.

Tool to export any project folder or repository into a single, neatly formatted file — ideal for quick AI-assisted code review, debugging and refactoring. Collects source files recursively, wraps them in fenced code blocks with relative paths, filters noise (e.g. node_modules, .git), shows basic stats and supports optional clipboard copying.

A self-hosted LLM proxy service built around LiteLLM, with support for additional proxy tools and provider integrations such as CLIProxyAPI. Includes monitoring capabilities and is deployed on Docker Swarm, managed via Portainer.

Reusable AI agent skills for Django, OpenAI, web UI, Python packaging, and structured LLM workflows.

ClatSearch is a Python tool that fetches real-time product data from Amazon and eBay via the Perplexity API. Enter a query to get details like price, ratings, descriptions, and more.

A video similarity pipeline extracting frame embeddings using OpenAI’s CLIP model and aggregating them into video-level representations. The system indexes embeddings with FAISS to enable efficient, real-time similarity search across varied video collections.

AI生图提示词模板库，按角色与模板分类整理，包含写实cos、漫展场景、镜头、灯光、材质和负面词模板

AI recipe generator from fridge ingredients — Google Gemini Vision + OpenAI + Streamlit | Generative AI | LLMOps | Python

一款针对 LLM 输入侧审查的精确逆向分析工具。自动定位 NewAPI、OneAPI 及任何实施基于字典规则进行 Prompt 过滤的 API 网关中的敏感关键词 | A precision reverse-engineering tool for LLM input censorship. Automatically pinpoints blocked keywords in NewAPI, OneAPI, and any API gateways enforcing dictionary-based prompt filtering.

Unofficial Home Assistant custom integration using ChatGPT/Codex OAuth for conversation and image analysis.

The action layer for AI agents. Proof of what your agent actually did, not what it claimed.

WhisperForge is a Python tool that leverages OpenAI's Whisper model to transcribe large audio files. It automatically splits files into manageable chunks, processes them, and combines the transcriptions into a single document. Ideal for handling lengthy recordings and generating clear, organized transcriptions.

Visual AI Workflow Constructor & IDE Assistant. Build autonomous agents, automate browser/desktop tasks, and patch code via drag-and-drop pipelines.

Local-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.

Free OpenAI-compatible API that forwards requests to GPT via browser extension - for testing

A Habbo client AI agent for interacting with other users naturally

See what your AI coding cost and produced, from the logs already on your disk. Offline, no account.

Pack your codebase into a single file for AI analysis

AI-Powered Burp Suite extension for elite bug bounty hunting. Detects HIGH/CRITICAL vulnerabilities using LLMs.

🎤 Control your world with Jarvis, a voice-activated AI assistant that simplifies tasks and enhances productivity.

GitHub Action + CLI that auto-writes PR descriptions, adds labels, and reviews code using OpenAI

OpenAI API powered Twitch chat bot that allows users to ask questions and receive answers via TTS.

Async web crawler powered by Playwright headless Chromium — JavaScript rendering, AI-powered extraction (OpenAI / Anthropic / Google), CSS rule engine with visual preview, and a full PySide6 desktop GUI. SQLite WAL crash recovery, proxy circuit breaker, RFC 9309 robots.txt, ReDoS-immune regex, 3,822 tests. pip install astrocrawl[full,gui,fast].

🤖 CLI to fine-tune GPT-3.5 Turbo models rapidly. 💬

Claude Code usage dashboard in your macOS menu bar — costs, tokens, plan limits, trends, multi-machine sync

Claude Code skill for real estate & PE asset management — LP reporting, rent rolls, T-12 analysis, valuations, debt monitoring, hold/sell/refi

Long-term spoken-English coaching tracker for Claude Code: practice by voice in the Claude app, get scored reports, a mistake bank, trend charts, and an adaptive next-session focus.

bem (Ben-Mutt) — a Mutt-inspired terminal email client for Gmail & Google Workspace, wired end-to-end with Claude: AI triage, reply drafting, an agentic inbox-zero mode, and a live copilot.

Session memory & orchestration for Claude Code: one index of all your sessions, three modes — finish / handoff / spawn

Claude Code의 영구 기억 시스템 — 4-layer 파이프라인 (세션 검색 + 메모리 회수 + Memory Compiler). Karpathy LLM-as-Compiler 패턴 실증판.

A terminal-native, zero-infrastructure local RAG pipeline and developer intelligence hub powered by OpenAI Codex, ChromaDB, and Groq/Gemini.

MCP RAG server — local embeddings, your docs never leave your machine. Private knowledge base + web search for Claude, Cursor, and Ollama. Drop your docs, connect your AI client, done.

🧠 Open-source context engine that feeds AI agents with policy-compliant enterprise knowledge. MCP-native, GDPR & EU AI Act ready, self-hosted.

Dual-track AI reference architecture: RAG system design & AI Security Engineering (EN/ZH) | 双轨 AI 参考架构：RAG 系统设计与 AI 安全工程

Parse any file to Markdown and JSON, anyparse, document-parsing, document-understanding, ocr, vlm, multimodal, image, pdf, markdown, docx, pptx, xlsx, tsv, csv, txt, md, rst, htm, html, xhtml, shtml, png, jpeg, jpg, webp, epub, ipynb, eml, etc.

Multi-user Streamlit RAG app with SQLite auth, Qdrant vector search, document upload, per-user collections, chat with citations, and configurable OpenAI or Ollama models via Docker/local development.

🤖 Discover the latest research papers on ArXiv tailored to your interests using AI-powered analysis and smart search features.

Training code and models for spam message detection in Russian

This project uses a local LLM with Ollama for embeddings and ChromaDB for document retrieval. It features a Gradio interface for users to ask questions and adjust response creativity. Documents are pulled from URLs, embedded, stored in ChromaDB, and retrieved to provide concise, sourced answers.

Test harness for RAG pipelines: scores retrieval, groundedness, citation accuracy and prompt-injection resistance, and fails CI on regression.

An AI-powered MTG card lookup and deck manager.

벼리 — headless hybrid (lexical + semantic) search for a Markdown vault. No app, no GPU, no cloud. Korean/cross-lingual. Apache-2.0.

Bring Google NotebookLM into any MCP client (Claude, Cursor, Codex, Antigravity…) — grounded Q&A with citations, source management, and Studio content generation. Install via uvx or a one-click Claude Desktop extension.

(ACL 2026 Main) Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents

Dual-system layered memory SDK for LLM agents — structured write path, hybrid retrieval, evolution chains.

MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.

Local AgentOps for cross-vendor CLI coding agents: route work, recover state, and accept only with evidence.

Wrap any Click or Typer CLI as an MCP server for AI agent integration

QA Maestro is an intelligent QA automation system that uses multiple AI agents orchestrated through MAF to perform end-to-end testing workflows.

AI-powered CLI research agent that searches the web, collects sources, and generates concise summaries with references using LangGraph, Tavily, and an OpenAI-compatible LLM.

Build and deploy large language models with Open Qwen, a PyTorch-based framework for efficient, flexible AI development and research.

Self-hosted, GDPR-native AI agent for sovereign organisations. Multi-LLM, multi-channel (web, voice, mobile, Telegram, Slack), HITL on every irreversible action, native PII anonymisation pipeline. Free for personal use, commercial licence for business deployment.

Offline AI voice assistant with semantic memory, wake-word detection, local LLM inference, streaming TTS, and modular tool-agent architecture.

AI-native control plane for Mimestream on macOS.

Hermes AI agent market-analysis skills (crypto / saham IDN / forex+commodity). Pluggable per-asset analyzers used by the Hermes agent.

Agentic coding CLI for a-Shell

Autonomous B2B lead generation & qualification agent with AI scoring, NLP, multi-source web scraping, email automation & compliance

📚 Search and download academic papers via Scopus metadata with Unpaywall and optional Sci-Hub fallback for full-text access.

Autonomous A-share quantitative trading strategy optimization powered by AI agents

Control Claude Code / Codex on your home PC from your phone via QQ — text a task, the agent codes in your real project, results return to chat. Windows · pure Python stdlib · zero pip deps · self-healing watchdog.

基于生命周期钩子的轻量级 AI Agent 框架 — 插件即文件，全异步，零 SDK 依赖

Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.

AgentSkills-standard interview preparation skill — research, mock interview, and performance evaluation

Agent automates interactions with Amazon's Rufus AI assistant to ask questions and capture responses.

Production-backed 6-layer memory architecture for AI coding agents. Model-agnostic — works with Claude Code, Cursor, Aider, Copilot, or any custom agent. Includes templates, scripts, interactive wiki graph builder, and one-line installer.

🍊 XiaoJu — An Open AI Companion with Continuous Emotion Dynamics

M.A.R.I.A. — local autonomous cognitive architecture, offline-first, modular, safety-aware.

Exabase memory plugin for Hermes Agent.

RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation (ICML 2026)

SafeGEO: a benchmark for Generative Engine Optimization (GEO) attacks on LLM recommendation agents — paper, dataset, and agent-side mitigation study.

Korea-market multi-agent equity research framework (KOSPI/KOSDAQ) — CLI-first LLM execution over KIS/DART/ECOS/Naver News with a self-improving analyze→verify→reflect loop. Research/education only.

RAG-based Healthcare Clinic Assistant using LangGraph, LangChain, Groq (Llama-3.3) & Pinecone — with hybrid retrieval, safety guardrails, and multi-turn memory.

This implements a real-world AI agent system that handles end-to-end business workflows.

AI system discovery and risk mapping for agentic architectures. Generates CycloneDX AIBOMs with topology and risk classification.