Python agents

A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using faster_whisper module which is a reimplementation of OpenAI Whisper module) and TRANSLATED SUBTITLE FILE (using unofficial online Google Translate API) for any video or audio file

Starter template for Claude Code memory system: modular rules with glob patterns, persistent memory, session continuity with auto-handover hook, and .claudeignore setup.

It shows how to realize agentic RAG.

The multi-backend, multi-modal micro-framework for AI agent development, orchestration, and deployment

NextAI is an AI-powered app for Frappe and ERPNext, delivering seamless content generation, automation, and productivity enhancements.

[ASE 2025 NIER] An LLM-based system that fully automates Chaos Engineering

ATAT is an email client for AI Agents. Deploy dozens of AI agents through a single email address (IMAP/SMTP) using the OpenAI API. Just add credentials, create one email and the aliases you need, and you have agents over email. Just add credentials and it works.

Autonomous driving agent in Carla simulator leveraging IL and RL techniques.

Y-Agent Studio 是一个面向 企业级应用 的Agent开发套，Y-Agent是其中的核心模块。 包含了：支持智能体编排、RAG、流程日志、单元测试、流程测试、语料生产等垂直领域非常需要的功能。 智能体编排可以在同一个流程中，同时支持多智能体协作和流程混合编排。

Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMs

An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human intervention.

AMP: The Agent Memory Protocol — Open source, MCP-native memory server for AI agents. Give your LLMs a hippocampus.

Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM needed). MCP server for AI agents with 500x fewer tokens. Extract, observe, script runner. 50KB, pure CDP.

JusChat é um assistente jurídico inteligente baseado em tecnologia GraphRAG (Graph Retrieval Augmented Generation) que utiliza processamento de linguagem natural e grafos de conhecimento para consulta e análise de documentos jurídicos brasileiros.

Ontology, and Knowledge graph based RAG that uses local LLM.

An agentic coding and automation assistant, supporting both local and cloud LLMs.

[IEEE S&P'26] WebCloak: Characterizing and Mitigating the Threats of LLM-Driven Web Agents as Intelligent Scrapers

Une suite complète de skills, agents et scripts marketing entièrement en français, conçue pour Claude Code.

A vibe coded final fantasy tactics inspired game using Codex, Claude Code and Agent Skills

Cursor AI Agent Team Framework: A three-agent collaboration system for AI-assisted work

一个基于多智能体的股票行情调研系统

Neurosymbolic AI agent framework - LLM + Prolog reasoning for small models. Single binary, runs offline or cloud-ready. Python & Rust.

Cut AI agent token usage by up to 90%: record a browser session once with freu-cli and it compiles into a reusable skill command. Constellation-based DOM targeting survives class renames and page reshuffles, so skills keep working. Drops into Claude Code, Codex CLI, Cursor, OpenClaw, and Hermes skills directories.

Self-hosted, BYOK outreach intelligence. Scan forums free; draft replies in your voice only on demand.

AI 全链路小说创作工具

AI Agentic Trader

Real-time guardrails for AI coding agents. 77 rules across 8 packs covering code quality, security, and infrastructure safety. Inline ignore directives, path exemptions, hook timing, and session summaries.

AgentLeak: Open benchmark for privacy leakage in LLM agents — 7 channels, multi-agent, multi-framework.

Memory for Claude Code that survives the session boundary — install the plugin into any repo: a hot cache injected every session under three hook-enforced caps, per-session handoffs, audit-driven promotion into knowledge and rules, plus agent orchestration and QA layers. Zero deps.

AI agent security harness, adversarial testing: 640 executable tests in the v4.24.0 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Four target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 19/20 (2026-Q1/Q2 set), NIST AI 800-2.

Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.

An agnostic AI-driven exploratory test framework that intelligently explores, tests, and validates any application

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

自进化量化选股系统 — Kronos K线预测模型 + Hermes Agent 自进化闭环 + A股三池漏斗选股

AgentWatch — Real-time reasoning auditor and observability platform for AI agents. Catches silent failures in your agent's reasoning chain before they execute — not after they break production.

Build Your Own Herness with SoloEngine. Achieve Loop Engineering — by simply dragging and dropping.

面向企业内部授权场景的 AI 代码安全审计框架。支持 redteam/full 两种模式，支持靶场集成验证，全程自动编排。适配 Cursor、Claude Code 及其他支持 Agent 调度的 AI IDE。

A Databricks framework for quick Agent solutions

Unified search, crawling, and archiving toolbox for AI agents and automation scripts.

A CLI tool that provides a collection of reusable, framework-native AI agent components

COS-PLAY: Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Game Play

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.

FAIR cyber risk quantification toolkits, agent-based control simulation (FAIR-CAM), threat event frequency estimator (PyPI), LLM classification validator (PyPI), Monte Carlo risk engine with IRIS benchmarks.

Building Agents with OpenAI SDK, Published by Packt

WebLLM Gateway：让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链，支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

AI Voice Agent System for Real Estate — Retell AI + Modal + Twilio + Notion + Claude

Filesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups.

[ICML 2026] E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent Memory

Port of pi-mono to Python; AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pod.

Claude agent skill: Score any video ad with an AI expert panel. 8-dimension rubric + 3 specialist personas.

SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

A curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.txt, MCP configs, rules, and examples.

Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting

Evidence-driven stock market analysis CLI for A/HK/US/JP/KR stocks, funds, and portfolios.

Search knowledge by what documents mean and how they look — not one or the other.

gradio region:us

gradio region:us

gradio region:us

gradio region:us

transformers safetensors phi3 text-generation conversational custom_code

transformers safetensors cohere2_moe text-generation conversational chat

static region:us

gradio region:us

transformers safetensors qwen3 text-generation information-extraction named-entity-recognition

A machine-native, empirically-ranked resolution graph for autonomous agents.

AI Code Stitcher - Paste AI Generated Code - It Just Works! Copy output from Claude, Cursor, ChatGPT, Aider or any other LLM and AI Code Stitcher intelligently applies it to the correct locations in your existing codebase.

Finch: self-improvement orchestrator — mines session history to detect corrections, breakthroughs, and behavioral patterns.

Claude Code plugin & Agent Skills for AI-native development: codebase readiness scoring (/assess), Six Thinking Hats deliberation (/huddle), AI-slop removal (/deslop), skill hardening (/skill-forge), and more.

The black box for AI agents — record every session, referee every task claim. Live mirroring + atomic coordination in a bucket YOU own. No server.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

Claude Code skill plugin implementing Betty Flowers' Madman-Architect-Carpenter-Judge writing framework with collaborative AI-human oscillation, SEO optimization, and multi-article content strategy.

AKM — universal Agent Knowledge Management. A tool-agnostic Markdown knowledge OS for AI agents: memory / brain / vault over seven layers, with a Learn Back loop. Works with Claude Code, Codex, OpenClaw, and any agent.

Run Qwen Code as a coding agent through an OpenAI-compatible API.

a control tower for your Claude agents

Claude Code skill that prepares Indian Income Tax Returns (ITR-1/2/3/4): parses Form 16/AIS/26AS/broker statements, reconciles every rupee, compares regimes, computes tax + interest, and emits a portal-ready data-pack JSON for a browser agent to file.

Native Excel (.xlsx) generator tool for Open WebUI — multi-sheet, Tables, live formulas, charts. MIT.

Dynamic emotion system framework for Hermes Agent - real-time emotion detection,Long-term memory, context management, and recall systems, state management, and persona expression

A personal AI operating system for knowledge workers. Carries your context, reaches your real tools, runs your SOPs, and learns from every correction.

A scheduled, agent-driven software factory. Keep a plain JSON backlog; Forgeo runs your coding agent (Claude Code, Codex, opencode) on each task and commits to main. Refactors when idle. No branches, no PRs.

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

Production-oriented AIOps Agent with durable LangGraph workflows, PostgreSQL checkpoints, RAG, MCP, and recovery tests.

DeepSeek Harness 的 SDR 数字员工插件：九阶段外贸获客 SOP、结构性人工审批、客户去重、持久化知识检索与审计日志，默认 dry-run 安全演示。

The first Agent Skill a beginner installs. Bootstraps Claude Code, Cursor, and other agents, then routes every task to the current best skill for that job.

Hermes Agent plugin: rewrites your prompts before they hit the LLM — across CLI, TUI, Discord, Telegram. Quality scoring + analytics + arrow-key interactive overlays.

transformers pytorch safetensors llama text-generation llama-2

Live Knowledge Base of LLM Agents for Science

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Learn to design an LLM wiki from first principles. Used as agent memory. Workshop with 3 exercises, open-source code, video, and slides. No coding skills required.

Save your GPT-6 Astra tokens. Let Luna do the dirty work.

Deterministic repo-wiki build system, driven by any coding agent. Zero LLM, zero network.

Sea safety intelligence dashboard — AI-powered dive condition forecasting for Dauin & Apo Island, Philippines. PyTorch LSTM forecaster with XGBoost baseline and LLM agent, pluggable weather/marine/air-quality providers (Open-Meteo, Storm Glass, AQICN). React 18 + Vite frontend, Python backend, Docker.

Self-hosted RAG knowledge base for docs and code, searchable by Claude Code and other agents over MCP

Your iPhone, driven from Windows: LLM agents tap, type, and read the screen over USB

Enterprise multi-agent self-evolving workflow orchestration platform MVP

AI restaurant marketing & operations engine for Claude Code. Multi-platform review analysis, menu engineering, local SEO, social content calendars, ad copy & PDF reports. 14 skills, 5 parallel agents. Restaurant marketing agencies charge $3-$10K/mo for what this does in minutes.

Multi-agent AI news pipeline powered by GLM-5.3-Flash and Jev

Reference implementation of FINESSE: self-reflective multi-agent financial reasoning with dynamic expert routing and ethical verification.