Python agents

Self-hosted, AI-agent-native governed data platform with ontology, policy controls, lineage, and auditable writebacks.

Palamedes is a powerful, next-generation open-source AGI engine built to tackle one of AI's most fundamental limitations: discovering what to pursue before being told what goal to pursue.

An intelligent, AI-powered code review assistant that leverages Retrieval-Augmented Generation (RAG) to provide context-aware, consistent code reviews based on historical review patterns and customizable style guides.

A control loop that turns Codex subagents into a continuously refilled engineering team—with isolated workers, independent model review, headless scale, and a live dashboard.

Blind, LMSYS-style arena for comparing AI coding agent harnesses (Claude Code, Codex CLI, OpenClaw, Hermes, OnDemand) instead of models. Same task, same model, isolated runs , humans judge blind, results roll up into an Elo leaderboard. FastAPI + MongoDB backend.

DevIntel AI is an AI-powered developer productivity platform that enables developers to connect GitHub repositories, index code bases, and chat with an AI assistant using Retrieval Augmented Generation (RAG). Get instant code insights, refactoring suggestions, and intelligent explanations.

transformers gguf text-generation license:gemma endpoints_compatible region:us

Safe, local-first internet access for AI agents — zero login, zero cookies, no third-party data services. Install once to read public web pages, YouTube, GitHub, Bilibili, V2EX and RSS.

Agent-ready creator strategy kit that turns brand truth and breakout content patterns into creator archetypes, hooks, concept slates, and test plans before sourcing or production.

Monolingual Italian late-interaction (ColBERT) retriever for search and RAG

Turn any URL into structured intelligence — SEO, tech stack, contacts, products, social profiles, security headers & AI-ready Markdown via one fast REST API.

Self-hosted AI companion with a simulated daily life, long-term memory, and consistent-identity selfies. Your keys, your data, your machine.

gguf mtp speculative-decoding rocmfp4 vulkan strix-halo

Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.

MCP server for live Google Trends data. Query search volume, breakout keywords, and 5-year history from Claude, Cursor, VS Code and more.

safetensors jais Arabic English LLM Decoder

Orchestrator for automated GitHub issue monitoring and agentic development across multiple repositories.

AI image generation studio for Hermes Agent. 11 presets across 9 models (FLUX, GPT Image, Nano Banana). Negative prompts, social sizes, prompt library, gallery, cost tracking, inpainting, image-to-video, editing, upscaling.

Taste-first club-music production that automates everything but the judgment. You direct in plain language; the agent writes each track's source, drives the synths, renders, and inspects. You never operate a DAW or plug-in; you make every musical call. Open-source, keyboard-first.

Structure-aware Markdown chunking for RAG over visually rich documents: keeps tables, headers, fences and figure captions intact, with a reproducible structural-fidelity benchmark.

Personal cognitive-retrospection Agent for tracing viewpoint changes across long-term Obsidian notes with source-grounded evidence.

Multivariate ad creative fatigue auditor & refresh triggers (AdEspresso style)

LLM specialist in AWS, GCP and Azure acting as a senior cloud engineer — RAG + read-only tools + domain specialists

Production-grade Blender extension and cross-platform asset pipeline for validating, optimizing and exporting mobile-ready 3D assets to Godot, Unity, Unreal Engine, Flutter and Android.

Maker-checker Codex skills for disciplined code changes, independent verification, and safe adaptive parallelism.

Context Engineering完整中文教程：RAG系统、记忆架构、多智能体、认知工具、神经场论 | 750K+字 | 即用模板

Beginner-friendly Sol-led orchestration for Codex with pinned Luna and Terra workers and verified review.

Your coding agent says it works. Gopnik tries to prove it doesn't — against the code, the delivered revision, and the checks themselves.

LLM 驱动的求职 AI Agent：8 平台搜岗 + 精排匹配 + 简历定制 + 材料审核 + 投递追踪 + 模拟面试 + Offer 评估 + 薪资谈判，本地部署

AI-first parametric CAD and 3D-print preparation from chat, voice, parameters and images.

awesome-agent-engineering(本地目录 ~/AAE)

static region:us

基于 DeepSeek Agent 的自主交易平台:AI 全程盯盘、分析、决策、下单执行合一,7×24 无人值守。三市场模拟竞技(美股/港股/A股)+ A股实盘(通达信桥)双轨运行;DeepSeek/GLM/Claude/GPT 多模型公平对决;L2 微观因子·分账制·风控网关·交易记忆·Arena 可视化。Docker 一键部署,免费接口初始化数据,个人投资者零门槛开跑;加模型、加市场、改交易思路均无需改代码

Evidence-first legal workflow for Russian civil practice, with intake, drafting, review gates, document assembly, and privacy controls.

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

Document-scoped enterprise RAG API with FastAPI, SQLite, Qdrant, citations, refusal, and evaluation.

Personalized video sales outreach script & storyboard planner (Tavus style)

Non-LLM AI substrate that remembers who it is across sleep gaps. Pure numpy, Hebbian + sleep replay + persistent slow weights. Ten identity tests, two audit rounds, contributions welcome.

Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).

Скажи словами, что построить — получи работающую версию, проверенную до того, как её назовут готовой. Плагин для Claude Code: сам собирает требования, план, код и приёмку; «готово» закрывает код возврата, а не фраза в чате. Откат одной фразой, стоп одним словом, без терминала.

An instruction library for agentic workflows

Kaval.AI is an opinionated Python library for building well-defined, testable and robust agentic workflows, chatbots and tools.

Five layers of an agent harness, each with the failure it prevents. Runnable with no API key.

Enterprise-grade AI Decision Intelligence platform. Features an automated AutoML engine (XGBoost, LightGBM, CatBoost, LSTM), SHAP explainability, Gemini-powered AI Copilot, FastAPI microservices, and React/TypeScript frontend with end-to-end CI/CD and Docker orchestration.

Audit every skill installed on your agent. Finds the ones that can never fire, measures what they cost you on every message, and flags any shipping runnable code.

Most AI will tell you your startup idea is brilliant. This one researches it properly and scores it out of 100. The two ideas I have put through it came back 43 and 28

Give Claude Code, Cursor, and other AI coding agents the ability to run sudo with case-by-case GUI approval. Passwords encrypted with your SSH key; no passwordless sudo required.

Agent skills for Machine Learning for Algorithmic Trading: leakage-safe quant ML, backtesting, validation, and autonomous research workflows.

Open-source AI short-form video generator — turn a topic into a captioned YouTube Shorts / TikTok / Reels video with AI visuals (fal) or free stock footage, AI voiceover, and auto captions. Python.

Realtime hallucination fact checker & primary citation verifier (AI Fact Checker)

Thai-first local AI guide: Hermes orchestration, Open Source RAG/data masking, and selective GPT-6 Astra API escalation

MCP server giving AI coding agents accurate Siemens NXOpen .NET API knowledge via hybrid retrieval (BGE-M3 + sqlite-vec), built from your own licensed NX installation

Find text that hides from humans but speaks to machines. Defensive scanner for indirect prompt injection in untrusted content.

Smart CLI Tool which makes life easier - AI and Debugging!

A cute little AI desktop assistant with a beautiful fullscreen interface, natural voice chat, live system info, smart automation, and GPT powered conversations all in one place ♡

Thompson-mode systems discipline for AI agents. Think first, build bottom-up, brute force until measured, rewrite over patch.

Award 1 winner in Agents for Good — safety-first multi-agent dementia care support prototype built with Google ADK, MCP, Cloud Run, and human approval.

Lightweight Wayland scaffold for AI agents to operate one GUI app without stealing the human's host focus, cursor, workspace, or clipboard.

Open evaluation harness for AI agent memory systems. Runs LoCoMo and LongMemEval against Synap, Mem0, Zep and Supermemory with pluggable provider adapters.

Self-hosted AI agent for terminal and Telegram with a deterministic permission kernel, human-scoped approvals, Claude/Codex workers, and an append-only audit trail.

Let AI agents watch videos — cloud-hosted MCP server with transcript + frame extraction for TikTok, YouTube, and 1000+ platforms

Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured on Sonnet and Opus, every run published — including the ones that failed. Demote, don't delete.

Build your team of AI agents without the pain of prompt chaos, wide-open keys, MCP overload, and a free-for-all on your machine. Declare each persona (bro) once, with its prompt, tools, secrets, procedures, and whom it may summon, and it comes to life in its own sandbox holding exactly that, on any harness, any model

docker region:us

Introducing Bimo 5 (Autonomous Multi-Modal AI Agent with real-time voice, vision processing, document analysis, image generation, and web search/fetch).

A production-ready conversational AI app powered by Chainlit and Ollama, with multi-modal document processing, MCP tool integration, and persistent chat sessions. Handles voice input, file analysis (PDF, DOCX, images), and dynamic LLM switching via customizable chat profiles. Easily deployable on Railway for fast, scalable cloud hosting

🐙 Multi-armed mocks for LLM apps - Drop-in replacement for OpenAI/Anthropic APIs for deterministic testing

AI 长篇小说创作工坊 v3.0.0 —— 15 种题材、5 Agent 协作、15 面板化工作台、世界线分支与世代传承、多 AI 服务适配与用量成本统计 | AI long-form novel studio: multi-agent, panel-based workbench, alternate world-lines, multi-provider support

Local-first course material hub with source-grounded AI study tools.

Local-first hybrid LLM router for policy-aware local/cloud inference

A framework-neutral RAG evaluation skill with golden sets, regression gates, and script-domain checks.

从零开始学 AI Agent：17 章渐进教程 + 每章可运行代码 + 算法面试轨（100 题详解）+ 65 道模拟面试题 + 项目实战案例（真实 Go Agent 项目源码级复盘，76 道练习题）+ 本地多语言在线判题（Python/C++）。网页版双击即开，无需 API Key 也能跑完。

transformers pytorch llama text-generation openthaigpt th

Memoria del proyecto para agentes de IA, cambiá de agente sin perder la historia.

A curated list of projects, integrations, and resources for Jev, TypeSafe AI's System One model.

250+ academic Agent skills + orchestration engine: math modeling · paper writing · LaTeX · scientific figures · literature review · IP drafting. Host-agnostic (any Agent), quality gates + audit evidence chain. CC-BY-NC-4.0.

A curated collection of reusable agent skills for design, research, browser automation, and developer tooling.

Perfect memory. Exact reasoning. Complete history for AI agents.

Agent-agnostic token reduction with exact recovery and fail-open guarantees. First-party Hermes Agent adapter; RTK terminal rewriting optional.

A durable workflow harness for Codex.

天机，可以泄露 —— 外贸人的 AI 工作流 skill 合集 | Battle-tested Claude Code skills from a real foreign-trade factory

Scores whether an autonomous AI agent actually did the work or just hallucinated its report, by checking every claim against recorded API calls. The core engine behind NoHalu.

Evidence-gated Obsidian brain for bounded multi-agent improvement loops.

Route every coding task to the best AI agent on your machine — Claude Code, Codex, Cursor, Gemini CLI, Aider, OpenCode. Installs as a Claude Code plugin, Gemini extension, or Agent Skill.

An executable, no-code SDLC graph that carries a feature from spec to PR — with explicit nodes, guards, bounded retry loops, and durable state. No framework. No SDK. No runtime to install. Your coding agent is the runtime.

🤖 The most comprehensive AI Agent for Airtable operations - Natural language interface with 33 MCP tools, complete API knowledge, and production-ready deployment

🧠 Knowledge-Driven Development (KDD): ready-to-use template combining OKF (knowledge as linked markdown nodes) + CCDD (deterministic contracts for ephemeral AI agents). Clone it, write a contract, and the built-in validator + CI are already working for you.

A bounded Codex Skill for authority-aware, privacy-conscious repository documentation curation and public projection.

A living local memory layer for your AI tools.

Infinite whiteboard spatial clustering engine & theme aggregator (Miro Assist)

Engineering rules for software built with AI coding agents, and the checks that enforce them

Forge is a Multi-Agent AI Coding Orchestrator that unifies multiple AI coding assistants (Claude, Gemini, Antigravity, GitHub Copilot) into a single autonomous build system. It enables users to dispatch tasks to multiple AI agents simultaneously, orchestrate their collaboration through various patterns, and run full autonomous builds...

Plugin marketplace for AI-assisted reverse engineering across Codex and Claude Code.

GB/T mechanical CAD skills for Codex, Claude Code and AI agents: AutoCAD/MCP, 2D/3D, strict DRC, assemblies and product safety gates.

BiNeuron is a local AI assistant that detects programming languages from requests/files, selects specialized models based on hardware, and generates code/docs/analysis via configurable prompts. It extracts text from PDFs, Word, images (OCR), and other formats, translates, filters profanity, and uses proxies if needed. Runs offline.

Curated, validated harness primitives for GitHub Copilot and Claude Code: agents, skills, prompts, hooks, plugins, MCP integrations, catalogs, and tooling.

Give your AI an eye — local screen → vision-model captions → memory store your AI reads on wake-up.

AI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading — files out, cross-verified, zero deps | 文献调研/实验方案/作图/精读，交付文件+交叉验证，零依赖，MIT

Static cost analyzer for multi-agent context graphs: explain what agents load and estimate tokens per fire and per day.

Reliable Codex workflows for research, design, and software development.