Python agents

A workbench for running large Mixture-of-Experts LLMs locally on consumer hardware with a tight VRAM budget.

A funky CLI that talks to Qwen 3.6 via Ollama with animations and attitude.

Stops Claude Code from starting a task your usage quota can't finish. Local, zero-dependency CLI that warns or blocks prompts before you hit your 5-hour or weekly rate limit.

Model Context Protocol (MCP) server for the CallRail REST API v3 — query calls, form submissions, transcripts, and more from Claude Code, Claude Desktop, Cursor, or any MCP client.

MCP client built from scratch in Python — STDIO transport, tool invocation, resource templates & prompt rendering via interactive CLI

Agent-readable semantic browser layer for AI agents — token-efficient web understanding, semantic snapshots, persistent sessions, and MCP/CLI/Python APIs.

Connect AI agents to HP ALM via the Model Context Protocol (MCP)

Local MCP code-intelligence for AI coding tools: surgical search/read/edit, agent-config version history, path-level access + masking guards, and a multi-project hub.

Connect your personal Telegram account to Claude Code using the MTProto protocol instead of the Bot API.

Remote cockpit for CLI coding agents — drive Claude Code / Codex / Reasonix from your browser or phone. CLI Agent 网页远程座舱：浏览器/手机远程驾驶多个 CLI 编程智能体。

Research trending topics and generate ready-to-post social content for X, LinkedIn, and Instagram with AI-driven topic analysis

mlx safetensors gemma4 4-bit quantized apple-silicon

transformers safetensors gguf qwen2 text-generation ai-model-builder

peft safetensors base_model:adapter:openbmb/MiniCPM5-1B lora transformers unsloth

safetensors qwen2 abliterated uncensored code qwen2.5

Security-first, brain-agnostic self-hosted agent runtime

gradio region:us

transformers safetensors qwen3_5 image-text-to-text agentic tool-calling

transformers safetensors granite text-generation unsloth lora

mlx safetensors qwen3_5_moe mlx-vlm moe coding

Multi-stage LLM equity research agent that anchors deterministic bytes32 commitments of its trading decisions on Mantle for post-hoc verification, executes paper trades on Alpaca, and enforces a fractional-Kelly risk kernel. Built for the DoraHacks Turing Test Hackathon 2026.

Serve any ACP coding agent — Claude Code, Gemini CLI, Codex — over the A2A protocol, with tool progress, file diffs, and permission prompts preserved.

AI "company brain" for a pasta maker (Al Dente S.r.l.): a FastAPI bounded tool-calling agent over live CRM/ERP/call APIs + a compiled RAG wiki, with a Next.js/React UI featuring a 3D knowledge graph. Frozen POST /ask contract, honest abstention over hallucination.

An Agentic ERP Operating System orchestrated with .NET Aspire. Decouples business logic into Neo4j graph workflows and Qdrant vector compliance policies, executing through a secure FastAPI SQL sandbox with an append-only cryptographic audit ledger and dynamic React JSX dashboard generation.

Decision layer samples for diagnostic reasoning and RoboCasa scenes for LLM agent evaluation

Source-of-truth marketplace + project scaffolder for custom Claude/agent skills, personas, and instructions. Organized as {stack|common}/{feature}; welcome-ai-badger scaffolds a repo, feed-badger contributes back.

Universal engineering kernel and reusable skill for agent-led repositories

A LangGraph superset: a 3D capability-manifold agent framework that routes over a semantic space instead of wired edges.

Evaluation of the agents, not just the model, in real-case scenarios

A locally running RAG chatbot with safety guardrails and RAGAS evaluation, reproduced from three upstream repositories on a single workstation with **rootless podman** and **Ollama on the host** — no OpenShift, no Kubeflow, no cluster.

🧠 Don't Miss A Face — Automatically backup WhatsApp photos of your loved ones to Google Photos using AI face recognition

Stops your coding agent from pushing unverified work. Your agent does the reviewing; a state machine records the result per-commit and gates the push.

An automated, agentic exploratory testing tool that performs comprehensive QA testing on web applications, simulating human user interactions through various input methods (mouse, keyboard, TAB navigation, arrow keys, etc.).

Milestone-driven development workflow for Claude Code and Google Antigravity.

TOKN — download & try. A trust-first agentic coding/reasoning harness with 20+ regulated-domain plugs, offline licensing, and in-place self-update. Public binaries only (source is private). Start a 14-day trial: tokn license trial

A unified local AI workspace — chat with GGUF models (Qwen, Llama, Phi), generate images, and share your AI remotely. Features agentic web search.

EmotiWeave: correctable multimodal emotion recognition with continuous affect tracking and conflict detection.

Systema Auxilium is an operating-system AI assistant that can handle a wide variety of tasks for you.

A method and toolchain for biblical study with an AI assistant — without ending up trusting it. Atomic cited findings, firmness marking, and a validator that keeps the corpus honest.

OpenClaw AI Assistant 的核心文档与配置仓库

An Event-Driven Agentic-RAG system for real estate documentation, featuring smart routing between vector search (Pinecone) and structured JSON data.

政企会议纪要skill

Claire - An agentic AI with persistent semantic memory, built for conversations and tasks.

JARVIS, but real. A local-first AI assistant for Windows that sees your screen, controls your apps via UI automation, speaks back with neural TTS, and runs on Ollama — with hot-swappable cloud fallback to OpenAI/Anthropic/Gemini. Includes a React dashboard with real-time SSE streaming.

docker region:us

transformers safetensors llama text-generation minicpm minicpm5

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.

AstrBot 插件：SSH 远程接管 Linux（多服务器）；ssh_exec / send_file / save_file；仅 QQ；白名单 + 致命命令闸门

CMM: Correcteur Mathématique Markdown

Claude Code and Codex skill for AI-tell audits, artifact cleanup, fidelity checks, and restrained prose edits. Local, no API calls.

MCP gateway federating 21 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.

Multi-mailbox IMAP/SMTP control plane. One YAML, N accounts, one bearer-auth gate. Unified inbox across Gmail/Outlook/iCloud/mailo/inbox.lv/whatever — search, read, mark, send. Reader mode strips HTML chrome for LLMs. Streamable-HTTP MCP server + REST API on one port. Ships as a Docker image.

gradio clip faiss rag computer-vision video-search surveillance multimodal

safetensors gguf qwen2 code coding-assistant lora

transformers safetensors gguf llama medical text-generation

gguf text-generation-inference code unsloth uncensored finetune

safetensors gpt_oss mixture-of-experts mxfp4 text-generation chat

gguf text-generation en endpoints_compatible region:us conversational

Autonomous Bybit spot trading agent: an LLM proposes orders, a deterministic risk guard validates every one before it reaches the exchange. Safe by default (testnet + dry-run). No proven edge — read the measured results.

A multi-agent Python system for comprehensive stock analysis and equity research reporting

🛡️ Modular Python framework for Cybersecurity LLM agents, purple team automation, log triage, and detection engineering in lab environments.

Open-source multi-agent simulation engine to predict society-level response to launches, crises, campaigns, and narratives.

Reference implementation of Double Ratchet: co-evolving an inspectable evaluation metric with a lifecycle-managed skill library for self-improving LLM agents (arXiv:2607.12790)

Open-source LangGraph job-search & application system — ~20-node evaluation graph, ATS/WebSearch discovery, and a human-in-the-loop Playwright apply assistant. 460+ pytest tests.

Open-source infrastructure and an emerging specification for traceable, revocable, rebuildable, and verifiable persistent learning in AI agents.

A cognitive operating system for AI agents — browser & computer intelligence, persistent missions, memory, recovery, evidence, and governed real-world action.

FUTS program evolution: evolve a program toward the best score on your metric — 以coding agent为变异算子的程序进化框架

Local LLM agent that operates a VyOS network lab over SSH. Tool-calling, evals, and fine-tuning on a 3B model running fully local.

Nine-agent AI framework automating quant research from hypothesis generation through leakage-aware backtesting

Defense-in-depth against prompt injection in tool-using LLM agents. Semantic drift detection catches synonym-evading attacks that bypass regex. Self-play red-team, calibrated scoring, ablation study.

An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.

Reference implementation of Ratchet: a minimal hygiene recipe for self-evolving LLM agents (arXiv:2605.22148)

CharmOS / C(H+A)RM — open-source framework to manage humans AND AI agents as first-class relationships, on a personal second brain, driven by the RDR loop (Recall to Deep Research). Manifest-first, Apache-2.0.

An AI agent given a real mandate, an audit obligation and a point-in-time data wall produces a tactical asset allocation study for a fictional university endowment

Autonomous chemical engineering agent: LLM tool-use over RDKit, Antoine thermo, Python+scipy, arxiv literature. 23-problem benchmark across 10 ChemE subdomains.

Local Hybrid RAG system — FastAPI backend, hybrid retrieval (FAISS + BM25 + RRF), BGE-M3 embeddings, and Ollama LLM, with real-time alerts and streaming chat.

CrewAI Agents build for Ceds Home Lab

WSQ TGS-2025059028 — Build and Deploy Agentic AI Apps with CrewAI, Autogen, ADK and Streamlit. 20 self-contained hands-on labs covering multi-agent workflows, RAG, Streamlit Cloud deployment and production guardrails.

多智能体协作系统：Crew/Agent/Task 抽象、3种协作模式、18种内置工具、LLM驱动决策

A RAG Application: Ask questions about DHL's public operational documents, or check a (simulated) shipment's tracking status.

Automate reconnaissance and vulnerability scanning for security audits using an integrated pipeline that organizes results and generates reports.

Swarmattacker Web application scoped Black box penetration testing agent

transformers gguf minicpm minicpm5 minicpm5-1b tool-calling

transformers onnx safetensors llama text-generation conversational

transformers safetensors hrm_text text-generation function-calling tool-use

Weaver is a synthetic lifelong reader. Hail Weaver

Ontology-aware RAG framework — RDF/OWL as the source of truth for LLM agents via MCP

🧰 claude-skills-toolkit · ⚡ 15 skills agentic para Claude Code · 🔒 security-audit (12 capas: OSV/KEV/EPSS/SAST/…) · ₿ bitcoin-custody-audit (custodia Bitcoin, 14 etapas) · 🐍 python-lint-guard · 📌 python-deps-pinning · 🏷️ version-bump · 📄 md-to-doc · 📋 yaml-control · 📝 md-lint-fix · 🐳 docker-cleanup · Zero-deps · Cross-platform 🐧🍎🪟

Home Assistant integration for the open-source Home Mind server — a conversation agent with persistent memory. Install via HACS. (Using the Nives add-on? It bundles its own.)

Local-first, voice-controlled AI assistant for the home. Pluggable STT/TTS/LLM and MCP servers; runs on your own hardware.

🤖 A personal AI assistant for Windows — listens, answers aloud, and safely controls apps. 100% offline speech, allowlist-gated actions, 132 tests passing.

Self-hosted knowledge base with semantic search, queryable by AI assistants over MCP.

Local-first file, document, and software-package organizer

this is an ai based assistant named jarvis, it acts like iron man jarvis providing real time comunication and performs actions.

Local-first desktop AI assistant for voice tasks, calendar and daily automation

🎨 Flutter AI UI Skill — Master-level Flutter UI/UX design intelligence for AI coding assistants. 30+ palettes, 15 font pairs, 120+ guidelines, project analyser & M3 starter template.

Local-first PCB automation for KiCad with safe MCP tools and deterministic autorouting research.

Nexus-LLM is LLM ai model which can run locally on your device.

AI agent skills collection & Vibe Coding methodology — ready-to-use skills for project launch, architecture visualization, content writing, and a complete framework for AI-driven development.