Python agents

Token-efficient CLI for AI agents to read, write, and collaborate on Google Docs & Drive.

A collection of intelligent AI agents built using Ollama, LangChain, and local LLMs — including chatbots, voice assistants, web scrapers, document readers, and custom tools. No APIs required. Fully offline.

A multi-agent system for product marketing

VettIQ is an AI-powered startup idea validation tool that leverages LangGraph workflows, FastAPI, and Streamlit to deliver actionable insights for entrepreneurs

智能体工作流（Agentic Workflow）应用案例的项目集合。

MCP server for Google Ad Manager. Manage ad campaigns, orders, line items, and creatives through AI assistants like Claude, ChatGPT, Gemini, Cursor, and VS Code. Automate your ad operations with natural language instead of clicking through the GAM UI. Built by Matious.

A fully local document intelligence system that allows users to build a persistent private knowledge base from documents and query it using retrieval augmented generation. The system runs entirely offline with local embeddings, vector search, and LLM based answer generation.

Scanner for adversarial hubs in RAG and vector databases

Zero-dependency Python SDK for WeChat Bot (iLink protocol) — text, image, video messaging & MCP server | 零依赖微信机器人 Python SDK，支持多媒体消息和 MCP 服务器

Reusable Codex/Claude skills, including md-to-xhs-cards for Markdown to Xiaohongshu (RedNote) image cards and direct XHS publishing

Steerable Harnesses for DeepAgents — Orchestra🪶

Este repositório foi cuidadosamente criado para fornecer uma coleção de agentes de inteligência artificial especializados, projetados para otimizar e automatizar processos em diversos departamentos de uma empresa, incluindo Marketing, Logística, Comercial, Financeiro, Recursos Humanos, Operação, Jurídico, Suporte e muito mais.

End-to-end agent to transform unstructured clinical notes into structured FHIR data (EACL 2026)

Production-ready LangGraph multi-agent system for travel planning. Async parallel orchestration across Amadeus, Hotelbeds, Twilio, HubSpot.

Open Agent Spec is a declarative YAML standard and CLI for defining and generating AI agents. One spec, any LLM engine (OpenAI, Anthropic, Grok, Cortex, local, custom).

Trae AI Agent 增强框架 — 34 个技能 + 8 条规则 + 双轨记忆。稳定、专业、中文优先。

EDINET XBRL parsing library and MCP server for Japanese financial data

Personal AI Chief of Staff -- built on cognitive architecture principles

Decision Infrastructure for the AI Era. 🧠✨️🤺

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

TinyFish Web Agent integrations with workflow automation tools and AI agent frameworks

Zettelkasten knowledge management MCP server for Claude Desktop with knowledge graphs, imoort/export tools, and Claude Skills integration"

Agentic code-review CLI that records each review/fix/test run trajectory, building a corpus for fine-tuning open-weight models.

ontorag cli and core library

Skills for AI coding agents

Self-hosted pipeline for a sane job search. Pulls listings from LinkedIn, Indeed, Greenhouse, and Gmail; LLM filters out the noise; auto-generates a tailored resume, cover letter, and company briefing for each application worth sending. Web UI for triage, Docker Compose to deploy.

Ollama Agent is a powerful command-line tool (CLI and REPL) that allows you to interact with local AI models.

Local-first Codex quota tracker and multi-account switcher for macOS and Windows

Open-source, fully automated multi-agent content pipeline: Web content → AI Script → Voiceover → Video → Telegram Approval → Social Media Upload

Routed Media OS for Claude Code — 96 skills + 13 modes + 7 specialist agents covering FFmpeg, OBS, NDI, DeckLink, Dolby Vision, HDR10+, and 2026 open-source AI media. Install via Claude marketplace.

Clouisle is an enterprise-grade knowledge base and intelligent AI Agent platform built on a distributed architecture. It transforms disparate data systems into actionable insights, while empowering intelligent agents to drive business decision-making and automation.

One step to enable best-practices for AI agents — drop into any project and enjoy the magic.

Chrome DevTools for AI Agents - Real-time debugging, pause, inspect, and step through your AI agent execution. Auto-instruments OpenAI, Anthropic, LangChain.

AProver: Agentic Prover for AI-Generated Code — LLM agents + BMC for automated verification of systems software

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

Deterministic multi-provider AI-agent orchestrator — ODA loops, GPT/Claude/Gemini/Kimi adapters, safety controls, event log

Read-only AI trading companion harness for decision logging, D1/D3 review, and rule evolution.

100% local research agent for your papers - ask PDFs on your machine, page-accurate verified citations, cross-paper synthesis, Ollama-ready

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model judgment, not holistic LLM-judge guesswork), with confidence intervals.

A lightweight proxy that converts Anuneko services into a standard OpenAI API format. 将 Anuneko 服务转换为标准 OpenAI API 格式的代理服务。

A Python trading bot connecting directly to Interactive Brokers (IBKR) via ib_insync for live market data and automated order execution, with optional OpenAI integration for advanced signals.

OpenAI Security Console - Python3 AI-powered Cybersecurity Framework

Engineering governance for AI coding agents: keep AI-generated code aligned with your architecture, standards, and prior decisions.

Authorization infrastructure for AI agents - policy enforcement, signed WASM bundles, per-request user scope, and audit trail for OpenAI Agents, LangChain, Google ADK, and Pydantic AI.

A human-like memory for AI Agent

LLM-powered data engineering agent: converts requirement docs and natural language into production-ready SQL, automating data pipeline workflows for ETL and analytics tasks. Open-source, MIT licensed.可嵌入的 LLM 驱动数据开发 Agent：将需求文档和自然语言转换为生产级 SQL，自动化 ETL 和分析任务的数据流水线工作流。开源项目，采用 MIT 协议。

A lightweight Python tracing toolkit for recording execution graphs from existing systems.

AI-powered MP3 metadata updater to automatically update song details (title, artist, album, year) using OpenAI API or local LLMs via Ollama.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

OASiS — an open-source agentic framework for verified multi-physics, multi-code simulation. MCP server letting any AI model drive eight FEM/multiphysics codes (FEniCSx, deal.II, 4C, NGSolve, scikit-fem, Kratos, DUNE-fem, FEBio) plus the SPARTA DSMC particle code, with curated knowledge, verified execution, and cross-code coupling.

Full-pipeline AI agent for Nature-series journal writing. Supports OpenClaw, Claude Code, and Codex. Covers journal selection, drafting, figure generation, citation verification, and reviewer response.

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cpp). Features KV cache-aware compression, session dedup, error cards, and Pichay-proven context paging.

Give AI coding agents a voice. Cross-agent skill that wraps OpenAI gpt-realtime-2 for Claude Code, Hermes, and OpenClaw.

Get insights into token usage for Claude code and Codex sessions with a dashboard and menu bar widget for mac

Multi-agent demo for Statewave conflict resolution. Concurrent agents write to a shared subject; the compiler detects contradicting facts via Jaccard similarity and supersedes the stale one with provenance. FastAPI + SSE, Apache-2.0.

MCP-сервер для кабинетов Wildberries и Ozon: продажи, остатки, цены, финансы, отзывы через Seller API напрямую, без браузера. 793 метода schema-driven, safety-гейт на запись. Подключает ИИ (Claude Code, Cursor, Codex, ChatGPT) к API WB и Ozon. Open-source MIT.

MCP server for parametric 3D modeling in Autodesk Inventor - drive Inventor with AI in natural language. Includes Agent Skills and undocumented Inventor 2026 COM API knowledge.

static region:us

gradio region:us

gradio agent-demo-track multi-agent research perplexity claude openai region:us

streamlit region:us

gradio region:us

gradio region:us

gradio region:us

gguf facebook meta pytorch llama llama-3

transformers gguf gpt llm large language model h2o-llmstudio

transformers joblib safetensors ChatNT feature-extraction text-generation

transformers gguf llama biology medical text-generation

transformers pytorch safetensors llama text-generation en

transformers safetensors qwen2 text-generation code codeqwen

gguf code-generation quantization qwen3 qwen-coder cerebras

transformers safetensors gemma4_assistant text-generation image-text-to-text conversational

gguf atomic-chat gemma gemma4 google llama.cpp

transformers safetensors qwen2 text-generation chat abliterated

gguf ravenx openfable soul-infusion qwen3_6 coding

transformers gguf llama text-generation unsloth base_model:ByteDance-Seed/Seed-Coder-8B-Reasoning

docker region:us

llama.cpp gguf quantized llama-cpp qwen3.5-moe mixture-of-experts

transformers gguf agentic code tool-use agent

Model Optimizer safetensors qwen3_moe nvidia ModelOpt Qwen3

transformers safetensors qwen2 text-generation code codeqwen

Local SQLite memory for LangGraph agents, with provenance, TTL, export, and MCP.

MCP (Model Context Protocol) server for DuckDB — auth and friendly SQL support out of the box

List of all the awesome projects into ADK-Hackathon

A 100% local, privacy-first alternative to Windows Recall — captures your screen, OCRs it, and lets you semantically search and chat with your history using a local LLM. Zero cloud, zero data leakage.

A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, reproducible experiments, and deterministic RAG.

Translate academic papers & monographs (PDF) into a single self-contained bilingual HTML — Chinese/original/side-by-side. Vendor-neutral, works with any file-capable AI agent. 把論文/專著 PDF 翻成單一自包含的中英對照 HTML（純中／對照／純原文三態切換）。廠商中立，任何能操作檔案的 AI agent 都能跑。

An end-to-end framework for running, sandboxing, and scoring agentic LLMs on complex data-science and econometric replication tasks.

Alpha-stage PRD generation with FastAPI, Streamlit, provider adapters, streamed state, and explicit scope boundaries.

AI eyes that roll through video footage — watch, understand, act

Modular AI-powered testing & monitoring platform — Performance / Test Agent / Test Case Gen / API & UI Automation / Knowledge Base

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data

Local-first AI project OS that turns coding models into reliable software agents with memory, sandboxed execution, verification, recovery, GitOps, and deployment.

AI agent skills for Nutrient APIs and SDKs — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents

43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.

Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.

多 Agent 协作平台 — supervisor 调度、@ 直连成员、Agentic RAG、Skill 沙箱产出物

An operational field guide and reference architecture for treating tokens as a first-class infrastructure resource. Built for AI Engineer World's Fair 2026.

A 125-task benchmark for knowledge-mediated implicit associations and retrieval blind spots in long-term agent memory.