Python agents

A versatile personal finance management tool, ai-finance-pencil combines Django Rest Framework and Next.js to provide an intuitive UI for tracking income and expenses. Enhanced with OpenAI's GPT-3 for interactive insights, budgeting tips, and chat support.

SQL functions for calling OpenAI APIs

The Pudim Hunter 🍮 is a Proof of Concept (PoC) tool to scrape job listings from SimplyHired, analyze them against your resume, and assign a relevance score. Get insights into how well each job matches your skills. Automate your job search smarter! 🚀

Leveraging OpenAI's Whisper ASR and GPT-4 models to automate the process of generating meeting minutes from audio recordings, as well as text summary and key point extraction.

Trainer and Evaluation scripts for fine-tuning Whisper models for the Ukrainian language

Contextual RAG over webinar videos using Pinecone, Claude and AWS.

Model Context Protocol (MCP) server exposes tools to read multiple document types including DOCX, PDF, Excel, and TXT. This has been tested on Trae Desktop.

🧙🏻 Code and benchmark for our Findings of ACL 2024 paper - "TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models"

Claude Plus is an advanced AI-powered development assistant that combines the capabilities of Anthropic's Claude AI with a suite of development tools.

A powerful CLI tool to manage, test, and optimize RAG pipelines. Streamline your Retrieval-Augmented Generation workflows from terminal.

A customizable Python CLI tool for interacting with local Language Models, ensuring data privacy while providing conversation memory and extensibility through plugins and efficient Retrieval-Augmented Generation capabilities with ChromaDB integration. Also compatible with OpenAI API.

An advanced tool designed for creating automated news bulletins. It generates dynamic news scripts using OpenAI, and provides voice narration using either OpenAI or ElevenLabs text-to-speech services. The system supports seamless integration with AzuraCast and S3 for content storage and distribution, making it a versatile solution for broadcasters.

Save 50% off GenAI costs in two lines of code

Australian Tax Office (ATO) chatbot using LlamaIndex RAG and OpenAI. Features automated documentation processing with ZenML pipelines, Qdrant vector storage, and Streamlit interface. Built for accurate tax information retrieval and natural language query processing.

The Explicit GraphQL Framework for the LLM Era Simple patterns. High performance. PostgreSQL at the center.

Your AI-powered SWE teammate, built into your git workflow

[COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"

The BioContextAI Registry for biomedical MCP servers

This is a Telegram bot that can download audio from YouTube videos and summarize the content using OpenAI's GPT-3 engine. It's a handy tool for quickly extracting insights from YouTube content.

ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)

🚀 A powerful tool to automatically generate descriptive tags for image datasets using both WD Tagger and VLM, with a user-friendly web UI. Perfect for preparing training data for Stable Diffusion and LoRA.

Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS.

🕷️ Adaptive web scraping skill for OpenClaw agents — bypasses anti-bot, survives site redesigns. Powered by MyClaw.ai

Production multi-agent trading platform with rigorous walk-forward validation. TSMOM momentum (1.097 Sharpe) + GEX regime filtering. Interactive CLI, autonomous trade lifecycle, daily scheduler. Alpaca integration. Built on Microsoft AutoGen. Research-driven approach with statistical validation. Educational - not financial advice.

Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)

analystOS - AI research platform for stocks and crypto with Web UI + Notion automation. Upload docs, scrape URLs, chat with research via RAG. Powered by OpenRouter (50+ models).

Ag3ntum is a self-hosted Ops Engineer (AI-Powered Agent) for Linux servers and websites. It performs server configuration, security hardening, log analysis, website troubleshooting, and routine maintenance — methodically, traceably, and inside a 6-layer security sandbox.

AI-powered Streamlit app for analyzing, summarizing, and chatting with documents (PDF, DOCX, CSV, images, etc.) using LLMs and Together AI.

AI-Tourism Agent 是智能旅游规划系统中的 AI 规划引擎，基于 LangGraph、FastAPI、OpenAI 等技术栈构建。 本服务接收后端转发的用户对话请求，通过 LangGraph 工作流完成意图识别、对话引导、并行获取天气与景点数据，并生成个性化旅游路线与结构化攻略。不直接面向用户，仅与 ai-tourism-backend 通过 HTTP/SSE 通信；会话与历史由后端管理，本服务负责 Checkpoint 状态持久化以支持多轮规划。

dog-raf es un chat y un sistema de consulta por generación aumentada para explorar las ediciones del Diario Oficial de la Federación de México.

A modular PyTorch library designed for learning, training, and deploying world models across various environments.

Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. Apache-2.0.

Bittensor Subnet 11: verified agent work on open-weight models. Season 2: fusion policies over the Engy catalog; next: an open protocol for verifiable environments.

💰 AIFi (AI Finance) is an agent-first workspace for compounding investment research and insight.

Real virtual desktops for AI agents. MCP-native, self-hosted, fully isolated.

Open-source EU AI Act compliance scanner. 51 checks across Articles 9-12, 14-15. Drop-in trust layers for LangChain, CrewAI, AutoGen, OpenAI. Local-first, no data leaves your machine.

Project To Markdown: Project files into structured markdown, optimizing documentation for AI analysis. Enhances AI assistants' performance in understanding project context, featuring both GUI and CLI interfaces. Ideal for improving AI-powered code comprehension and problem-solving.

🌊 The simple wrapper of leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

does code matter?

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).

PPO-based RL system for XAUUSD trading. Trained on 2004-2025 gold price data (15-min intervals).

12 AI rocket scientists in your terminal. Full satellite mission design from zero to orbit. Production-grade skills with built-in physics, formulas, and validation. No API dependencies.

Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

AI-powered algorithmic trading agent for the Charles Schwab API. Python, options strategies (wheel/theta, covered calls, iron condors, verticals), quantitative backtesting, LLM signal review, and Telegram control.

Multi-agent swing trading system — automated screening, research, and execution with backtesting and live trading

The Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.

No Mac Mini? No problem. HermesFace is the best free way to deploy Hermes Agent on HuggingFace Spaces — 2 vCPU, 16GB RAM, 50GB storage, always online, zero cost.

Fiction-book-writing preset for AI GitHub Spec Kit. Stackable, priority-ordered collections of template and command overrides for Spec Kit writing complex fiction novel books (single POV and multi POV)

Decision provenance for AI-coded codebases: the why, and what was already tried and rejected.

The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed workflows.

AstraDesk Enterprise AI agents Framework + Demo Apps

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

mori MCP server — a governed memory layer for AI coding agents.

Fastn MCP server — give AI agents governed, audited access to integrations and tools across your customers' systems of record.

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

Obsidian-powered daily logs, session logs, /prepforreset handoffs, and wiki janitor skills for AI agents.

Run DeepSeek-powered Codex sidecars as cost-effective worker agents under a GPT main brain.

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

Local-first LLM wiki — ingests your documents into a curated, citation-backed knowledge base you can read and chat with. Marimo + SQLite/FTS5, any OpenAI-compatible model, no cloud required.

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning

多智能体应用与任务执行平台

Multi-model orchestration skill for Hermes Agent - parallel subagents, citation enforcement, source verification

Use Google Antigravity (agy) as an agent backend from Claude Code / OpenAI Codex / Cursor / any MCP client. MCP server with 10 typed tools + Skill bundles, hybrid backend, capability detection, long-task supervisor, worktree-isolated execute.

Self-hosted AI API gateway 鈥?proxy OpenAI / Claude / DeepSeek behind one endpoint; works with Codex CLI / OpenCode / Cherry Studio.

璇玑 XUANJI · AI 自主进化 A 股量化模拟盘系统 — 覆盖数据采集→因子计算→策略回测→模拟执行→风控监控→AI自主调度/复盘完整闭环。五层AI Agent架构，硬风控+白名单执行，可审计可回滚。

Self-contained Codex skill for ad-hoc development sessions on session branches.

Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.

gradio region:us

streamlit region:us

gradio region:us

gradio region:us

transformers safetensors qwen2 text-generation retrieval-augmented-generation text-generation-inference

transformers safetensors llama text-generation license:cc-by-4.0 text-generation-inference

gguf glm chatglm thudm quantized GGUF

transformers safetensors gguf llama text-generation mergekit

transformers gguf llama text-generation en es

transformers safetensors qwen2 text-generation chat conversational

transformers gguf code qwen-coder finetune text-generation

transformers pytorch llama text-generation code math

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

transformers safetensors qwen3_5_moe image-text-to-text quantized moe

transformers gguf code qwen qwen-coder codeqwen

gguf code codeqwen chat qwen qwen-coder

Structured market intelligence for Indian financial events, macro context, and sector impact.

Open-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

面向外贸出口场景的 Hermes / Open claw Agent Skills 包，支持海外客户发现、批量名单处理、公司背调、客户评分、决策层线索、开发信、跟进计划和报价单导出。

Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.

AI-native workflow runtime for scientists working with multimodal scientific data.

Dialogue memory for AI agents (hermes plugin): auto-recall of facts across sessions, LLM fact extraction with a cheap gate, SUPERSEDE versioning. Local SQLite + hybrid search. One-command install.

A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.

Let AI agents manage your Zotero library: headless CLI + Python API to search, import, enrich, export BibTeX, and attach PDFs (Web API + WebDAV) — no desktop app required. Ships with an agent skill & AGENTS.md.

Agent skills that turn Claude Code (or any agent) into an award-winning multi-modal creative pipeline — art, music, video, story. Panel-of-Experts debate, a deterministic state graph, and an immutable continuity block that makes creative drift structurally impossible. Prose contracts, not framework code.

Manages parallel Claude Code sessions, so you don't have to.

Referee report on your economics paper before a real referee sees it — verified comments and a revision plan your agents implement. Agent Skill for Claude Code & Codex.

A memory and continuous learning system designed exclusively for AI — your AI grows smarter the more you use it.

Универсальные безопасные Agent Skills для любых конфигураций 1С / Universal safe Agent Skills for any 1C:Enterprise configuration

Skill-Atlas

Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.