Python agents

The workspace layer for Claude Code — browse every session, persistent project memory, MCP awareness, and per-project launch control. Terminal UI and desktop GUI. Zero runtime dependencies.

AI SRE agent diagnosing Kubernetes incidents over Google Chat — security-first sandbox: NixOS VM, default-deny egress, hard tool denylist against prompt injection

MatchaFlow is a large language model (LLM) based multi-agent system that simulates a complete software project management workflow.

AI-powered cross-channel ad campaign coordinator designed to generate ad copy variations, allocate budgets, and output production-ready ad manager payloads.

Conversational cart recovery retention agent designed to analyze abandoned shopping sessions and negotiate discounts dynamically.

GenPark Commerce Production API gateway hosting billing, fraud checks and search integrations.

GenPark AI Skill - Generate structured product launch plans with phased timelines, task checklists and budget allocation

GenPark reviews sentiment analysis and pros/cons summarizer agent skill.

GenPark image tagging and metadata generation agent skill.

GenPark AI Skill - Compile supply delay metrics to forecast vendor reliability levels

Vercel Edge Geo headers routing redirector

Rerun-like AI agent workflow composer with step execution and retry

Vercel Blob file upload simulation helper

Parse unstructured product specifications utilizing phia APIs

Detect conflicting product attributes using phia spec validations

GenPark AI Skill - Competitor ad copywriting hook parsing counter strategy planner

Price decrease alerts dispatcher

Cold outreach sales email hyper-personalization engine

Static AST code analysis, taint propagation & zero-day vulnerability detector

Self-adaptive delay and weight manager for rate limits

Agent-to-Agent (A2A) brand commerce representative for LLM search recommendation

gpt-image-2 images on your ChatGPT/Codex subscription — no API key, reference images supported. Claude Code skill.

Autonomous YouTube Shorts generator — AI picks topics, writes scripts, creates voiceovers, assembles videos, and uploads to YouTube on autopilot. Python + OpenAI + Coqui TTS.

Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

API Scraper — Hunt down leaked API keys in GitHub commits, validate them against live endpoints, and check remaining balances. Multi-service support for OpenAI, Anthropic, DeepSeek, Google Gemini, Mistral, AWS, and more. Features a dark-themed PyQt5 GUI with concurrent scraping, auto-export, and import of previous results.

Codex agent orchestration skill with adaptive thread thinking, callbacks, QA/review gates, fenced automations, project autopilot, and optional agy/Gemini review.

transformers safetensors llama text-generation conversational arxiv:2403.04652

Fusion_GPT is an Autodesk Fusion 360 extension that integrates OpenAI's GPT models, allowing users to chat with AI directly within Fusion 360. The AI can provide design insights, answer questions, and interact with the Fusion 360 environment.

FFmpeg toolkit with CLI, MCP server, and AI tool schemas

Real-time duplex voice call sentiment interceptor & script adapter (Dograh style)

Social media video/image ad copy & creative asset generator (AdAnt style)

Agentic dev environment orchestrator & PR review agent (Xirp style)

Open-source voice agent pipeline builder with streaming ASR & TTS (Dograh style)

A team's knowledge, captured where the work happens, filed by an agent, and answered with citations you can check.

A local MCP bridge that lets Claude, Codex, Antigravity, and Cursor read and edit the project open in DaVinci Resolve — free version included. Nothing to edit, nothing to repaste.

Native non-MCP Crawl4AI and Trafilatura plugin for Claude Code

Open-source privacy testing for AI agents. Python SDK, CLI and MCP tools to detect data leaks across tool calls, memory, inter-agent messages and logs, with redacted reports and CI gates.

AI-powered Product Management second brain. Capture chaos. Surface patterns. Never let critical items slip.

CogniEDA is a validity-preserving research-state system for AI-assisted exploratory data analysis. It turns objectives, data profiles, assumptions, tasks, hypotheses, evidence, and discoveries into governed objects so conclusions stay traceable across long-horizon analytical sessions.

The most comprehensive MCP server for Blender — 218 tools for 3D modeling, AI generation, MSFS content creation, and more

SoulHub is an open-source Agent persona template community — share, discover, and deploy well-tuned AI Agents with one click.

Full-duplex streaming voice agent pipeline (Dograh style)

🪐 Growmos: A new approach to agentic AI—a living system expanding its knowledge like the universe, compounding its capabilities, and getting more work done with fewer tokens.

transformers safetensors qwen3 text-generation unsloth trl

Self-contained demos for the Nutrient Data Extraction API — grounded extraction with per-field citations, bounding boxes, and confidence scores.

SciSage: multi-agent scientific survey generation with hierarchical reflection; includes the SurveyScope benchmark.

Local coding agent with native Zhipu GLM / StepFun Step Coding-Plan support. Four hard gates — the agent can't claim done without running the tests. 本地 coding agent，原生支持智谱/阶跃 Coding Plan，四道门硬约束。

Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.

SNAFU. Agentic LLM flow to help you with "naming things" in source code.

AI Agent / LLM application engineer Chinese interview question bank: 2,038 questions with reference answers

Talk to Claude Code instead of typing: a voice daemon + dashboard that records you, transcribes, routes to your agent sessions, and speaks the replies back - with per-voice avatars, push-to-talk hotkeys, and a live conversation HUD

A modular framework for agentic Bayesian optimization

把中文视频逐字稿转换为可执行 HyperFrames 分镜规格的 AI Agent Skill

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

transformers gguf text-generation-inference unsloth llama trl

Local-first control plane for coding agents, Git worktrees, and tmux sessions

Make AI agents finish authorized, non-trivial work and prove the requested outcome with direct, scope-matched evidence.

A curated list of plugins, tools, skins, and extensions for DeepSeek Harness (DSH).

《企业级 Agent 从入门到专家（2026版）》——从单 Agent 核心机制到多 Agent 与企业落地的工程化实战教程，配套可运行贯穿项目与 CI 验证门禁。

AegisAl：基于 Tauri 2、FastAPI 与 LangGraph 的跨平台桌面安全智能体

本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an exact passage/figure, one-click DOI to source.

Multi-account and usage manager for Claude Code and OpenAI Codex — switch logins, track quota, auto-rotate before rate limits

Open reproduction of NVIDIA's AVO paper (arXiv:2603.24517): evolutionary search where an autonomous coding agent IS the variation operator — Vary(P)=Agent(P,K,f). Runs on the Claude Code or Codex session you already have.

Production-grade RAG pipeline built from scratch (no LangChain) — hybrid FAISS + BM25 retrieval, cross-encoder reranking, evaluation harness, and AWS Lambda deployment.

Citation-grounded Turkish Legal RAG system for legal question answering, combining BM25 + dense retrieval, fine-tuned E5 embeddings, BGE reranking, and Trendyol LLM SFT.

gradio region:us

safetensors jais Arabic English LLM Decoder

Portable AI coding-agent skills for source-attributed, human-approved context packages.

[SEC 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems

Store data · Write plugins · Analyze your showfile.

Telegram bot for Obsidian — self-hosted AI agent / life OS: PKM notes RAG, kanban tasks, personal finance. Python, DeepSeek, fail-closed modules.

Azimuth — multi-venue concentrated-liquidity LP bot. Automated pool screening, entry and exit for Meteora DLMM on Solana and Uniswap v3/v4 on Robinhood Chain.

CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.

AI-agent courtroom for hackathon judging: LLM jurors cross-examine teams over Discord, scores stay sealed, and every session is voiced and livestreamed.

A local-first Streamlit HR assistant for parsing PDF résumés, answering candidate-related questions, and ranking applicants against job descriptions using explainable skill matching.

A Model Context Protocol (MCP) server exposing ERP-style data (sales orders, inventory, purchase requisitions) to AI agents — with a real human-in-the-loop approval gate on write actions. FastAPI + FastMCP + PostgreSQL, Streamable HTTP transport, Dockerized, tested.

Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 categories x 5 roles), 29 reproducible environments with 6 rebuilt from real Marconi100 ExaData, scored on 7 weighted dimensions.

transformers safetensors Dream feature-extraction text-generation conversational

Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable sources, and human-reviewed proposals.

Autonomous AI agent skill to position for the $FLOP airdrop. Install in your agent and prompt 'Help me with the $FLOP airdrop'

Self-hosted AI agent for terminal and Telegram, with Claude/Codex workers, live activity and a deterministic permission kernel.

Open Model Hardware Standard - AI agent hardware control

First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.

dMoERA Creator Studio MCP Server: build, backtest, and deploy crypto trading strategies via AI agents

AI Agent 开源书单/教程合集 | Awesome list of LLM Agent books & courses

CREATIVE · VIDEO — One raw facecam take → a finished short-form motion-graphics ad. Claude Code skill + playbook, rendered with HyperFrames.

For folks who don't have time to read 220,000+ words of research 📚

The shortest complete answer: an agent skill

Hermes Herald — dispatch tasks across Hermes profiles with fail-closed model routing, SSE auto-delivery, approval relay, and per-call subagent model selection.

gguf GLM 4.7 Flash thinking reasoning NEO Imatrix MAX Quants

Role-playing autonomous agent orchestrator managing crews (CrewAI style)

Real-time neural 3D asset generator and PBR texture synthesizer (Luma Genie style)

Pan-African and global cross-border payment gateway with mobile money rails (Flutterwave style)

Resilient agentic document parser & schema drift workflow automaton (Gumloop style)

Institutional DCF/LBO financial model and 10-K audit builder (Rogo style)

Photorealistic aesthetic diffusion prompt and lighting synthesizer (Midjourney style)

Stateful OS-tier memory virtualization agent with auto-paging (Letta / MemGPT style)

Conversational language tutor and pronunciation fluency coach (Speak style)

Full-track generative music and vocal multi-instrument synthesizer (Suno style)