Python agents

A contract-first Python framework for modernizing APIs for AI through exact application behavior and explicitly bounded agent-owned decisions.

ИИ-помощник на собеседовании: локально распознаёт вопросы и показывает ответы в реальном времени. AI assistant for interviews: on-device speech recognition with real-time answers.

A curated library of 100+ GPT Image 2.5 prompts with outputs, parameters, provenance, and Flare vs Sunburst comparisons.

Lovomo——本地运行的 AI 角色聊天助手：本地大语言模型 + GPT-SoVITS 语音合成，通过 NapCat 接入 QQ。多角色人设与情绪化语音、流式回复、表情包、RAG 知识库、工具调用、定时问候与待办提醒，全部在 WebUI 里配置，另带插件市场与 GitHub 分支发布。数据不出本机。

A System One model (jev) plays Craftax; an LLM sets the goals

A progressive source-study tutorial of DeepSeek Harness (dsh): 17 chapters from a minimal agent-loop to multi-agent delegation, compaction, permissions and cross-process RPC, with runnable teaching code. Zh/En.

面向教学知识库的可扩展本地 MCP 基底。内置 BeMarkdown，将 Word/PDF 转换为包含正文、公式、表格和示意图引用的中间 Markdown，支持来源追溯、任务日志与 agent 复核，并提供模型自动下载和部署脚本。

Reactive, artifact-driven agent runtime: agents transform versioned, typed, provenance-aware artifacts inside an evolving context — no graphs to draw.

Backend for Brave's AI Services

多 Agent 协作开发框架：项目负责人 + 6 单责角色 + 阶段门禁 + 实时看板 · 单写手 + 只读参谋 · 四实现（ZCode/OpenCode/WorkBuddy/Universal） ｜ Multi-agent delivery framework: project owner + 6 single-accountability roles + stage gates + live board · single-writer · read-only advisors · 4 implementations (ZCode/OpenCode/WorkBuddy/Universal)

The comprehensive list of AI agent frameworks and orchestration tools: 175 SDKs, workflows, multi-agent systems, MCP tools, memory, deployment, and evaluation.

Collections of recursive self-improvement (RSI): papers where the loop that improves a system also changes the thing doing the improving.

Local runtime security and policy enforcement for AI agents and LLM tool calls, with permissions, guardrails, rate limits, approvals, auditing, and an emergency kill switch.

A story companion for Honkai: Star Rail — live subtitle OCR, character chat, and alternate story branches.

Agentes de IA en produccion: conector MCP con siete herramientas, function calling, orquestacion multi-modelo (Opus/Sonnet/Haiku/Fable), diseno de prompts y gobernanza. Un problema real resuelto en dia y medio, con transcripts, errores y costos a la vista. Python.

A Claude Code engineering template for reliable data warehouse AI development./面向数仓 AI 开发的 Claude Code 工程化模板：hooks、skills、subagents 与八步标准流程。

Universal Author Voice Engine — upload any author's texts, extract their voice, generate content in that style. PDF/HTML/TXT in & out. OpenAI, Claude, Ollama, Codex.

Claude Code plugin that cuts context tokens and model cost — output-truncation hooks, an Opus-plans/Sonnet-Haiku-implements workflow, and workflow-hygiene guards.

SearXNG search MCP for Claude Code & Grok — privacy metasearch + page extract for agents.

A trustworthy document-grounded RAG chatbot for solar and energy technical support, with manual upload, provenance, citations, fault-code lookup, and hallucination-aware answers.

DQL knowledge base + RAG pipeline + GitHub Copilot instructions for accurate Dynatrace Query Language generation + MCP server + Copilot instructions for accurate Dynatrace Query Language generation

Iris - your personal AI super-assistant. Fast, lightweight, fully yours. Protocol-first (any OpenAI-compatible endpoint), 292+ plugins, knowledge-base RAG, local-first & private. Official site: x33834.github.io/iris

MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.

safetensors gtm-gpt-chat text-generation conversational gpt nanogpt

AIGEN — An Economy By Agents, For Agents. The first token created by AI for AI. Earn $AIGEN by contributing to the ecosystem.

transformers safetensors qwen3_5_text text-generation veriloop veriloop-coder

transformers safetensors qwen3 text-generation agent tool-use

mlx safetensors llama omlx apple-silicon oq

gguf mistral quantized 2-bit 3-bit 4-bit

transformers safetensors qwen2 text-generation conversational convAI

transformers gguf llama code math text-generation

Mochi —— 会成长的桌面 AI 伙伴。VRM 3D 角色与 VRMA 动作导入，支持流式对话、语音、记忆与多模型接入。Tauri + React + Three.js × LangGraph。

Standalone Hermes plugin for Linear Agent Sessions and attributed Linear tools

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.

An always-on fleet of Claude-powered AI agents that help keep your life manageable — assistant, butler, concierge, plus specialists and plugins you add. Reachable on Telegram and by voice. Ships as a Home Assistant app (add-on).

A multi-agent knowledge base system built with LangGraph, Hybrid RAG, MCP, HITL and Docker Compose.

A daily job search that runs itself: scrape the boards, grade every posting against your own rubric with Claude Code, get one email. Korean boards + global ATS.

用 AI agent 一键生成你的豆瓣读书可视化报告 + 个性化品味洞察。适配 Claude Code、Cursor、Openclaw、hermes等本地 AI agent。

一条命令为 Codex 与 Claude Code 安装三段式会话标题插件

China macro context for trading agents on Base — x402 micropayments for ADR volatility signals (GDP, CPI, policy, industry data). Four layers: DO·KNOW·NOW·ARK.

BeeCode — free AI coding agent for the terminal. g4f models, no API key, real tools, skills/plugins/MCP, EN+RU UI.

🤖 基于 DeepSeek Harness 的微信 AI 自动化机器人：AI对话/记忆/日程提醒/天气/联网搜索，多面具人格切换，双通道LLM，Web控制台

易语言调试中转 MCP：本地 E5.95 IDE 的读取、可靠修改、编译与运行观测，通过 MCP 交给 AI 调用

Universal persona distillation skill for OpenPersona — distill any person or character into a runnable skill pack

A self-improving personal state system: an AI agent reads your journal through PAD emotion, security/hope (G) and growth (XP) lenses, asks for your feedback, and turns it into rules. Python stdlib only.

McDonald's perks hub built on the official McDonald's MCP. Introduces a Coupon Availability Window model that tells you when a coupon is actually usable today and how long is left, ranking everything P0-P3.

Autonomous Web QA & Self-Healing Testing Agent powered by Google Gemini SDK, Playwright, and Pytest. Features dynamic DOM scanning, zero-scripting test generation, live execution, and AST self-healing.

AI farm manager for Farming Simulator 25 — Claude Code skill + in-game mod

元气方程-Energsolve — Agent竞品分析系统

Neovim config + MCP Python bridge — a code editor built for AI agents

MNC-style pharmaceutical pipeline asset assessment Agent Skill

Claude skill for the Bambu Lab 3D printing loop: scaling that preserves hardware fits and magnet holes, print prep and slicing, parametric design, and a queryable print log.

夸克/百度网盘资源整理 Agent Skill + 本地文案助手 | Agent skill to save & organize your own Quark/Baidu Pan shares, with offline copywriting

麦麦点餐最优解｜WorkBuddy Skill + 麦当劳 MCP + 本地 Python 组合求解。按预算、热量和蛋白质筛选搭配，附无需 MCP Token 的离线演示。

麦门军师 —— 基于麦当劳 MCP 的点餐决策 Skill：自动领券、智能比价、营养把关、一句话点餐（麦当劳程序员创意开发大赛参赛作品）

Let Codex supervise Google Antigravity agents through MCP with scoped tasks, plan-driven workflows, and parallel Git worktrees.

MCP-style TCP bridge for Autodesk MotionBuilder, enabling AI agents to inspect scenes, rigs, poses, animation curves, takes, and FPS animation workflows.

AI product design workflow for Claude - UX research, MVP scoping, UX/UI design, prototyping, validation, design systems and developer handoff.

A collection of skills for the CapSolver, unleashing your RPA potential.

AI Agent that auto-generates professional Notion templates(workspaces) from natural language.

AI-powered local control plane for Docker, processes, ports, projects, and developer environments.

AI agent that actually operates your Windows apps — real clicks & keystrokes, persistent memory, 12+ IM channels. An AI Agent that truly operates your desktop

transformers safetensors mistral text-generation license:apache-2.0 text-generation-inference

Local AI cycling coach built on Claude: reads Intervals.icu, WHOOP and weather, keeps a training plan, gives a morning briefing and weekly review.

Private, local-first AI agent: planning, sandboxed tools, four-tier memory, streaming UI and OpenTelemetry — runs entirely on your machine with Ollama.

Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM. Source-available, free for personal use and for evaluation of up to 31 days.

Is your backtest real? Deflated Sharpe Ratio, backtest-overfitting (PBO) and lookahead checks with measured false-positive rates. Works with vectorbt, backtesting.py and TradingView.

A curated list of public places where AI agents talk to each other. Synced with swarmmemo.com/guides/agent-board-map.

Agentic vulnerability discovery with proof: autonomous agents hunt bugs, but no claim counts until it is replayed in a fresh container, judged against known bugs, and re-attacked after patching. ZCode (Z.ai/GLM) and Moonshot Kimi Code port of rust-in-peace. PoC or it didn't happen.

A tool-calling agent harness that keeps working when tools fail. Retries, timeouts, loop detection, and honest error reporting, benchmarked against injected failures.

AnswerBook transforms exam papers into step-by-step solution books with structured explanations, mark-wise breakdowns, common mistakes, and confidence indicators, helping students understand concepts and prepare smarter for exams.

compact 150M typed-decision engine: calibrated probabilities, abstain flag, Jev-compatible /v1/systemone API, local ONNX on CPU. 0.3.0 (68M) beat Jev on typed-decisions.

Tool-using agents judge a failing source useless, yet keep querying it. Code and data for the paper.

Ditto Bench and an agentic framework for LLM robot control

Agent skills for academic research: literature review, citation audit, paper writing, peer review, reproducibility, MCP tooling, and CS research.

Make your AI agent write in ASD-STE100 Simplified Technical English. Short sentences, no AI slop, plus a linter. Works with Claude Code, Codex, Cursor, and any SKILL.md agent.

A highly scalable and pluggable evaluations repository that works with all environments to provide an unified experience for all your evaluation tasks

Executed-evidence verification gate for AI coding agents

Physical Agentic AI framework for safe, skill-grounded multi-robot orchestration with LLMs, deterministic runtime validation, and embodied robot teams.

PANINI-DR: controlled deep research through Generative Semantic Workspaces - Official Codebase

Daily AI news, fact-checked and traced back to its roots. A source-checked history of AI since 1943, a glossary with lineage, and the labs and people behind it. Open data, built nightly on free Gemini and Groq tiers.

Two-sided agent workspace that turns a homeowner's references and a designer's constraints into one living-room brief both approve, with adaptive questions, visible conflicts and dual approval.

Use AI coding agents with LTspice via sim-cli: run circuits, inspect waveforms/logs, and produce replayable simulation artifacts.

Agentic Soft-Token Compression (ASTC): training-free in-model context compression for long-horizon LLM agents.

Vectorize integrations with the Python ecosystem

Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.

An personalized agentic system empowered by langchain

AI-powered call center quality assurance with multi-agent LangGraph pipeline - transcription, summarization, QA scoring, compliance detection

Check what the user may do before your AI agent does it. Live permission checks against Jira, GitHub, Kubernetes, AWS and 17 more systems.

drive-discovery-assistant

从 0 到迷你 Claude Code 的 LangChain Agent 学习仓库：LCEL · 记忆 · RAG · LangGraph · 自制 Agent Harness，全部可独立运行、默认走 OpenAI 兼容协议。

WebGuard AI: An AI-powered web vulnerability scanner. It uses OWASP ZAP for discovery, while LLMs (LangChain/OpenAI) analyze outputs, filter false positives, propose remediation codes, and generate professional reports. Microservices stack: FastAPI, Next.js, MongoDB, and Docker.

Autonomous LLM-powered trading agent built with LangChain and Alpaca Markets, capable of analyzing markets, reasoning on opportunities, executing simulated trades, and explaining investment decisions.

Jiro Search: Open-source, self-hosted search API with 9 engines, 12 social scrapers, MCP server, hybrid search & AI synthesis. Free SerpAPI alternative. MIT licensed. pip install jirosearch

SQLite of agent memory — single-file, embeddable, zero-config. Episodic + semantic memory, hybrid BM25+vector recall, bitemporal facts, spreading-activation, working memory, async API, LLM compression, Ebbinghaus decay, GDPR forget, multi-agent, MCP-native.

基于 LangGraph 的多智能体协同金融研报智能分析系统 | Supervisor 分层调度 + 4 专业 Agent | DeepSeek + AKShare + PyMuPDF | 全流程自动化

Find which tools your LLM agent confuses and fix their descriptions with proof

BARC PROJECT

👔 FitCheck.AI is your personal AI stylist. Upload outfits for savage critiques, auto-tag your wardrobe, and get smart recommendations - powered by Streamlit, LangChain, MongoDB, and VLMs like CLIP and Qwen.

智慧农业害虫防治演示系统 - YOLO检测 + AI决策(RAG增强) + 无人机执行