Language
Python agents
62,809 Python AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
62,809 agents · ranked by popularity · refine in the directory →
Python agents — page 334 of 629
Governance layer for multiple AI coding agents on a production codebase: constitution, decision log, evidence grammar, CI gates.
A package of documentation and tools for Coding Agents to generate DCS combat scenarios.
gradio region:us
transformers safetensors llama text-generation minicpm minicpm5
mlx safetensors qwen3_moe text-generation conversational base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct
gguf text-generation ggml quantized q2_k q3_k_m
Let your agent drive your Android phone — from Windows, over ADB, with nothing installed on the phone. Works with Claude Code, Codex and Hermes.
Document-grounded adaptive tutoring with bounded tool-use agents
A reusable skill & plugin kit for long-running AI coding agents: file-backed delivery contracts, discriminative validation gates, and restart-safe evidence. Deploy paths for Claude Code, Codex, TraeCode, and DSH.
Evidence-gated vulnerability research for AI security agents.
AI agent炒股荐股盯盘+open claw微信实时推送播报工作流
A self-hosted job-hunting agent driven from Discord: finds postings, scores them, drafts cover letters, tailors your CV, and can watch your inbox -- runs on a local LLM.
empirical research framework designed to analyze multi-agent Large Language Model (LLM) conversations as observable, continuous-state dynamical systems.
Local Pokemon Red LLM-agent harness with live gameplay UI, structured traces, save states, replay, and turn-by-turn agent observability.
Resource management planner
A production-ready local AI assistant powered by LangGraph, FastAPI and Ollama.
Digital Engine for the development of Social media and digital marketing strategies, social media plans,, their implementation, and the monitoring and evaluation of the same
Spec-Driven Development (SDD) for Claude Code
Evidence-gated Recursive Self-Improvement (RSI) runtime for self-improving LLM agents, self-evolving agents, agentic AI, AI safety, evaluation, lineage, and rollback.
A security layer for AI agents. Stops prompt injection, tool tampering, and runaway behavior before they happen. Open-source guardrails for AI agents — auditable, self-hosted, and works with any framework. Deterministic security sidecar for LLM agent frameworks. Drop-in protection against prompt injection, tool poisoning, and capability abuse.
Autonomous AI code review & PR automation — a self-hosted, multi-agent software factory that reviews, fixes, and merges its own pull requests through a verifying LLM pipeline.
Static security scanner and analyser for AI agents, MCP tools, and LLM applications - OWASP LLM Top 10, and infrastructure checks. Zero runtime dependencies.
Self-evolving personal AI agent. Telegram-first. Multi-provider BYO key. Persistent memory, daily journal, skill graph, dream cycle. Free forever. Apache 2.0.
A co-pilot for your first real circuit board. Reads your KiCad project, explains what the checks are telling you, and sizes a case that fits. Works alongside KiCad and FreeCAD.
gradio region:us
gguf text-generation vi base_model:vinai/PhoGPT-4B-Chat base_model:quantized:vinai/PhoGPT-4B-Chat license:other
gguf llama.cpp reap expert-pruning moe qwen3.5
Turn Instagram reels into local transcripts, keyframes, and LLM-ready Markdown bundles.
법조문·대법원 판례·생활법령을 근거로 답하는 법률 Q&A 챗봇 | LangGraph 에이전트 + Chroma RAG + FastAPI(SSE), Docker→GHCR→EC2 배포 | answer_quality 0.912
Multi-agent AI customer support system built with LangGraph, LangChain, OpenAI, and RAG, showcasing a modular architecture for intelligent task routing, retrieval, tool use and human-in-the-loop workflows.
Runnable, offline reproductions of one defect class in three agent frameworks: a value that is neither an explicit yes nor an explicit no reaches the execute path of a human-approval gate.
A lightweight agent framework for production runtime. Cycle-based execution with pluggable LLM backends, tool dispatch, memory compression, and distributed scheduling.
基于 Claude Code 架构精简的 AI Agent 框架 | 7层架构 Agentic Loop + 6个内置工具 + 三级权限控制 + 动态System Prompt | 可以更加详细的学习工程级架构,也可以自定义内置工具使用
Ticket-Driven Development for AI agents — the agile, lightweight memory + backlog framework that lets Claude always know what to work on next.
Your personal assistant agent for macOS. Your own JARVIS for planning, research, memory, and getting work done.
Lightweight AI coding assistant inspired by Claude Code, Codex & OpenCode — 100% Python, LangGraph state machine, Textual TUI, WebSocket server. Self-hosted & extensible.
📄 Summarize research papers, extract citations, and answer queries with this AI-powered assistant built using LangChain and OpenAI's GPT model.
gguf gemma4 coding agentic terminal tool-use
transformers safetensors llama text-generation wicara pytorch
gguf quantized gemma gemma4 agentic abliterated
transformers gguf qwen3_next heretic uncensored decensored
gguf text-generation base_model:Nexusflow/Athene-V2-Agent base_model:quantized:Nexusflow/Athene-V2-Agent endpoints_compatible region:us
transformers safetensors gemma4_unified image-text-to-text gemma4 sft
transformers gguf llama text-generation llama-2 code
Vendor-neutral MIT skills for Claude Code and Codex: cold email, sequences, LinkedIn DMs, humanization, reply-intent, ICP. Approve-before-publish. By Veneris.
A cross-host web-design skill for Claude Code and Codex. Project-derived art direction, a decision router instead of a style pack, and a rendered verification harness that measures the page instead of trusting the code.
Local first AI assistant for your workspace & messaging. Zero data leakage, local storage, and fast CLI controls.
Prevent AI coding agents from acting on stale code context with source-aware freshness checks and hard stale gates.
Long-session handoff for Hermes Agent: measure how close a chat is to the token limit that ends it, export the whole session, and continue in a fresh chat that reads the parent transcript in full. Recovers context that compaction already removed.
Opinionated Claude Code engineering config: 11 always-on rules, 63 on-demand standards, 30 slash-command skills, 33 runtime hooks, 9 custom agents, 36 MCP servers, and a 774-item review checklist across 69 categories
static rl-environment region:us
safetensors qwen3_5 qwen qwen3.8 abliterated uncensored
transformers gguf merlina grimoire text-generation orpo
Agent 自动测试系统：LangGraph + LLM 编排的 API/Web UI 自动化测试，从 OpenAPI 契约生成用例、执行测试、自动重试与缺陷归因，产出可视化报告
DSV4 behavior-discrimination benchmark: 81 lightweight zero-dependency pytest grading tests (d10/d11/d12/t2/t3/t4/v4) for datapipe — discriminates harness/agent/persona effects that public tests saturate on
Close Code: A terminal-native AI coding agent powered by LLMesh, with multi-model routing, tool execution, context management, and agentic workflows.
Natural-language tool calling for LLM agents — Python implementation of the NLT paper (arXiv:2510.14453). Boosts tool-calling accuracy on weak/free-tier models by up to 14%.
Governed cognition substrate for AI engineering agents: mission envelopes, evidence-bound belief/plan graphs, quarantined memory, model-role review, sentinel checks, and BlackFox handoffs under human authority.
No Promises Without Proof. A dependency-free discipline that forces agents to pair every success claim with evidence and a proof state (OBSERVED/INFERRED/UNVERIFIED/BLOCKED), then derives the completion verdict deterministically.
Stateful conversational AI agent built with LangGraph, SQLite, and Streamlit. Features dynamic ReAct tool-calling loops, multi-thread session persistence via SqliteSaver, and 4-bit NF4 quantized local inference (Qwen 2.5) optimized for low-VRAM deployment.
Runtime security layer for AI agents — inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.
Provide adaptive math tutoring for grades 1–6 using AI agents that generate problems, analyze errors, and guide student practice.
Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.
Autonomous coding pipeline for Claude, Gemini, ChatGPT, GLM CLI agents. Helps to automate all your coding tasks, can run autonomous overnight or any time. Designed for MacOs and Linux servers - MacMini or MiniPC.
Xenopus 1.0.0 — a self-improving autonomous AI agent runtime. Local-first, verifiable, model-agnostic.
Self-evolving AI Agent that adapts to user preferences over time. Works with ChatGPT, Claude, and 40+ platforms via Agent Skills open standard.
面向生产环境的 AI Agent 动态技能网关与自进化底座：三层级联意图路由(R@1=98%)、8维沙箱评估、8重防御防线、LangGraph状态图旁路与SQLite原子发布状态机。
The best $0 research agent that runs on a laptop. Local Gemma 3 4B + SearXNG + trafilatura. CLI · TUI · Web GUI · MCP server · submittable Claude plugin. 264 tests, all mocked.
gradio region:us
docker region:us
docker region:us
gradio home-assistant smart-home automation local-first voice yaml small-model
docker streamlit plotly llmops observability telemetry evaluation model-monitoring
static region:us
gradio mcp-server region:us
transformers safetensors qwen3_5_text text-generation merged multi-agent
gguf text-generation base_model:driaforall/Dria-Agent-a-3B base_model:quantized:driaforall/Dria-Agent-a-3B endpoints_compatible region:us
gguf qwen3.5 function-calling tool-use qlora finetune
gguf text-generation tr license:llama3 endpoints_compatible region:us
transformers gguf trendyol llama-2 turkish text-generation
transformers gguf conversational text-generation ar dataset:MBZUAI-Paris/Darija-SFT-Mixture
gguf LLMs mistral Intel text-generation en
gguf code expert-pruning imatrix llama.cpp moe
transformers gguf code codeqwen chat qwen
transformers gguf code qwen qwen-coder codeqwen
gguf llama.cpp imatrix qwen coding reasoning
transformers gguf causal-lm code text-generation en
safetensors mnemosyne cognitive-ai sclm audio text-generation
A team makes a hard technical decision with AI, and keeps the receipts.
transformers safetensors gguf phi3 text-generation ai-model-builder
hermes gguf duo-neural llama.cpp agentic coding
一个将现实议题、规则机制与角色关系转化为可交互多智能体仿真/演绎世界的生成与运行框架。
Self-hosted autonomous-development BMAD framework platform — Telegram + console drive Claude Code through a typed, event-sourced spine. Python 3.12 · FastAPI · aiogram v3 · MCP stdio.
Agentic RAG system using FastAPI, Streamlit, LangGraph, Chroma, Serper, and arXiv search with built-in evaluation and observability.
Developed an AI-powered online exam portal with secure test conduction, automated result generation, anti-cheating monitoring, and performance analytics using React, and Tailwind CSS.
Build Windows apps in 13 seconds from your PHONE. Self-learning local AI agent. Runs on a 4 GB GPU or just CPU + RAM. No API keys, no cloud.
The official Pinecone Plugin for Cursor
Agent-deployed, hands-off literature monitor: bioRxiv + journals -> 3-stage LLM filter -> Discord/Telegram digest, with chat-based deep-read & figure follow-ups.
A Claude Code plugin that generates divergent solutions, attacks them, and merges only what passes the tests.
Welcome to cerbere-agent guard, originally just agent guard, then rebranded after the mythical hound of the underworld. Our mission? Guarding your AI agents, keeping them in line, and blocking unauthorized actions. Think of it as the ultimate guard dog for AI security and guardrails. 🐕🛡️