Python agents

codex and claude skills repo

Reinforcement learning and AI algorithms evaluated on OpenAI gym environments

NutriScan is a Discord bot that provides nutritional estimates for meals based on images you provide. It utilizes OpenAI's GPT-4 Vision model to analyze images of food and return a concise breakdown of their nutritional content.

MCP server exposing Amazon Selling Partner API to Claude Desktop and other MCP clients. 55+ tools across 19 SP-API scopes, multi-marketplace, safe writes.

Memory Graph Core Primitives — persistent, graph-based memory for LLM interactions via MCP

Ask your database questions in English. The model emits a typed query plan, never SQL text - validated against the real schema and the caller's role before any SQL is generated.

Turn CSVs into a context graph your AI agent can build, query in plain English, and verify — SPARQL-backed, Apache-2.0

Silent regression detector for RAG pipelines

Self-evolving, evidence-based memory layer for coding agents and development teams.

BAZINGA - Distributed AI that belongs to everyone

transformers safetensors qwen2 text-generation retrieval-augmented-generation text-generation-inference

transformers safetensors llama text-generation text-generation-inference unsloth

Extract subtitles and transcribe audio from Bilibili videos

🔍 Zero-API-key web search for AI agents via self-hosted SearXNG. Works natively with Claude Code, OpenClaude, Gemini CLI, Codex CLI, Hermes & more. One SKILL.md, eight tools.

Qdrant-backed semantic memory provider for Hermes Agent

Polymarket sandbox for OpenClaw agents. Full trading engine, real market data, simulated USDC. One argument from live trading. No real money at risk.

Data tracker for signals called from MarketAnalysis — records TP/SL results into complete per-asset monthly data. Clean table format for AI chat agents. Integrated with MarketAnalysis for accurate trading data logging.

Local-first, auditable knowledge compiler for technical docs and source code

yeaboi — AI Scrum Master in your terminal: sprint planning, daily standups, team retros, 1:1s & delivery reports, synced with Jira, Azure DevOps, GitHub, Confluence and Notion

🚀 InvestPilot : 基于 Claude Agent SDK 与 MCP 的全自动智能投研助手。通过多 Agent 协同，实现从金融数据获取、深度分析到专业报告生成的全流程自动化。

🎬 MCP Server + Agent Skill + CLI — Transcribe any video URL to text. Plug into Claude Desktop / Cursor / Windsurf / Codex. Supports Bilibili, YouTube, TikTok, 1000+ sites × 5 ASR providers.

基于 LangGraph 构建的自主医疗 AI 智能体平台，集成 869 个医学/生信技能，具备语义检索、多层错误容错与安全代码执行能力

LLM Tool for effective test evaluation of ML projects with curated Checklists and LLM prompts

Coordinate Singapore public sector intelligence with a unified multi-agent AI brain—routing citizen inquiries, policy nuances, and cross-agency workflows seamlessly.

The Everything Prediction Engine — five AI analyst personas debate, 10,000 Monte Carlo worldlines unfold, and superforecasting calibration converges any question into one actionable probability.

Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.

Prudence, a custom harness powered by Microsoft Agent Framework. Includes a "counsel and craft" mode which delegates executive function to Microsoft Foundry and task completion to local models.

Graduate Agent is an open-source AI assistant that helps students discover research opportunities, personalize application materials, and manage the entire graduate admissions pipeline from search to submission

A small, self-hosted MCP server that gives Claude read/write access to your Google Sheets, optimised for analytics on tabs of 50k+ rows

llama.cpp gguf gemma local-ai agentic-ai coding-assistant

minorAgent —— 轻量、清晰的 Agent 框架。内置丰富工具与多 Agent 协作，强可扩展性，适合 Agent 入门学习与二次开发。期待与社区共建。

Claude Code plugin marketplace. audit: a manifest-driven audit/fix pipeline with enforced plan-first and TDD gates — deterministic hooks, not prompt suggestions — token spend attributed to phases and tasks, and a shareable HTML report. Zero dependencies.

Trusted AI mathematics workbench: ProblemContract to Attempt to verified proof/counterexample bundles with SymPy and Lean evidence gates.

gguf chat text-generation en license:apache-2.0 endpoints_compatible

gguf safetensors phi3 ai-model-builder fine-tuned llama.cpp

mlx safetensors qwen3_5 text-generation mlx-mtp qwen

Universal zero-token AI gateway: LLM plan-cache + real device control (Android via rish/Shizuku or ADB, desktop shell)

Context Excavator solves a real problem: when you paste large codebases into ChatGPT, the AI gets lost in noise. You're feeding it 500 lines of code when only 20 lines actually matter. The LLM can't tell the difference, so it gives irrelevant answers. This project extracts only the code that matters, automatically..

Rules your coding agent physically cannot ignore. Claude Code hooks that DENY the tool call and BLOCK the reply - stopping reactive patches, guessed citations, and premature 'done' claims. Also works as an LLM-agnostic rule pack.

Run Claude Code on your Windows PC from Discord -- multi-session channels, local voice in/out (drive mode), git worktrees, and confirm-gated dangerous actions.

DialogBERT implemented by TensorFlow

Multimodal Telegram AI bot: image understanding, voice STT (Whisper) and TTS voice replies, smart group-chat moderation, persistent Gist memory. Gemini or any OpenAI-compatible LLM (Groq, LiteLLM, OneAPI). Single Flask file, 3 dependencies.

rasa custom components to support multiple languages and multiple text scripts

Starter kit for educators to test, adopt and iterate on genAI tools in the classroom

Bobby is the coolest mf

A powerful voice-activated chatbot using Google Generative AI and Google Search API. It leverages large language models (LLMs) to listen, respond, and search the web for you.

🥇 2nd Place | Solution for Hackathon Kiln 2025 | AI-powered assistant that both educates on blockchain concepts and can help advanced users quickly retrieve precise, real-time data using Kiln's API

Upload a CAD PDF to extract text and automatically generate a concise engineering summary using a local LLM.

LLM leveraging OpenAI API to be used in Glific via webhooks

A starter kit for building realtime speech-to-speech applications using the OpenAI Agents SDK and the GPT Realtime API on Azure AI Foundry.

Advanced AI-OCR with FastAPI and OpenAI Integration

Benchmark LLM jailbreak resilience across providers with standardized tests, adversarial mode, rich analytics, and a clean Web UI.

Production-grade multilingual RAG for scientific research across 12 languages (English + 11 Indic). Uses BGE-M3, ChromaDB, hybrid BM25+dense retrieval, cross-encoder reranking, and Gemini 3.6 Flash. Includes fast RAG, LangGraph agents, 6 research tools, NLI verification, multimodal indexing, and grounded citations (<2% hallucinations).

Lightweight RAG library with ONNX embeddings, DuckDB storage, and three-tier hybrid search (semantic + BM25 + FTS

Local NotebookLM alternative for private document analysis, local RAG, document chat, and AI report exports

This project implements an adaptive, multi-step retrieval system inspired by CoRAG. The system will break down a complex query, perform an initial retrieval, analyze the results to identify knowledge gaps, and then autonomously generate and execute follow-up queries to gather missing information.

Auto generation of UniFi network documentation

Git-native structural memory for AI coding agents. Index once — stays fresh on every pull, merge, and branch switch. MCP server for Claude Code, Cursor & any agent.

Multi-DB RAG translation agent — FAISS translation memory, glossary, and ChromaDB style retrieval, orchestrated with a LangGraph router/critic loop. ENGLISH - SPANISH - FRENCH

An open-source engine for deciding when messy records of people, places, organisations, and products refer to the same real-world entity, with evidence, not just similarity scores or identifiers.

HelpDesk Enterprise open source: agente RAG de soporte IT con memoria autocapacitada, Gemini gratis, FastAPI + Streamlit + conector Copilot Studio

HookRadar Creative Intelligence skill/plugin for Codex, Claude, MCP, and SKILL.md-compatible agents

Chat-driven AI agent that builds full-stack apps through an autonomous SDLC pipeline. 18 specialist agents, self-learning loop, any LLM provider.

Data tracker for signals called from MarketAnalysis — records TP/SL results into complete per-asset monthly data. Clean table format for AI chat agents. Integrated with MarketAnalysis for accurate trading data logging.

Multilingual voice and text conversational AI agent that automates sales calls, contextually answers questions using RAG, and dynamically segregates leads into HOT/WARM/COLD pipelines in 10 Indian languages.

393 AI-generated research artifacts produced by Enoch with provenance metadata, evidence bundles, claim-ledger files, and public audit reports.

Static system dashboard for a Hermes Agent installation: host status, security, model routing, honest cost, memory, cron economics and a capability map — built by cron from the agent's own telemetry. Stdlib-only Python, EN/RU.

PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.

A multi-agent conversational financial analytics platform that combines company fundamentals analysis, SEC filing intelligence, and machine learning-based stock price prediction through an intuitive chat interface.

An interactive chatbot built with LangChain, featuring memory support to keep track of conversations and provide context-aware responses.

SWARM is an open-source Codex plugin for directing a coordinated team of AI agents from one control task.

Private, self-hosted coordination control plane for coding agents

问津 · Thither — a travel planning agent that is honest about what it does not know. Every figure carries its provenance; a missing number never becomes a zero.

Run MiniMax-H3 video plus synchronized audio in 4 sampling steps using the Turbo LoRA, with drop-in nodes for ComfyUI workflows.

multi model capable single harness orchestrator. Apache 2.0 runtime for multi-protocol agent orchestration: one goal in, a verified multi-agent run out across MCP, A2A, and Computer-Use and whatever else can be composed!

A multi-agent LLM framework for diagnostic, multi-objective calibration of complex simulation models. Pluggable model and LLM layers. Demonstrated on distributed hydrology, designed to generalize.

A RAG agent that answers from your docs with citations, or abstains when the evidence isn't there.

transformers safetensors iquestcoder text-generation code industrial-code

Static code analyzer for any repository — classify codebase, extract HTTP routes, detect tech stack, map dependency graph. Multi-language (Python, JS, Java, Go, Ruby, PHP). Zero dependencies. Optional LLM enrichment

Self-host Claude Managed Agents tool execution on Blaxel sandboxes.

A standalone, all-on-by-default token-optimization layer for LLM requests: minifies tools/system/messages (code-fence aware), dedups tool results, distills old turns, prunes to a budget, type-compresses output. Async proxy for Anthropic, OpenAI & Ollama + MCP server (stdio) + CLI. MIT; ships orjson/xxhash/tiktoken.

Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code must keep passing them — zero LLM calls at inference. Try: uvx temper-skills audit <skill.md>

AI-powered quantitative investment platform with 7-agent swarm orchestration, fractal debate algorithm, 3-tier LLM routing, and automated eToro trading — built for autonomous portfolio management.

Pharmacist-facing drug-interaction decision support — deterministic detection over 152K records, LLM explains only. FastAPI · Postgres · React · RAG

Syncs Home Assistant areas, devices, entities, automations and integrations into a (self-hosted) BookStack wiki — manual notes are preserved. Optional opt-in Markdown back-export turns the wiki into a universal RAG / LLM input source.

One-click deployable RAG agent with meeting transcription and project knowledge base

Chatbot open-source de orientação, saúde e apoio emocional para a comunidade LGBTQIA+. 🏳️‍🌈

safetensors qwen3 TeichAI unsloth text-generation conversational

gguf llama text-generation base_model:01-ai/Yi-1.5-6B-Chat base_model:quantized:01-ai/Yi-1.5-6B-Chat license:apache-2.0

safetensors qwen3 chatgpt codex v2 unsloth

⚡ Advanced AI iteration framework featuring an 8-stage pipeline, automated fine-tuning, voice interaction, and security scanning.

A multifunctional QQ Bot based on OneBot protocol

MCP server for developer environment diagnostics and PostgreSQL query and index analysis.

LLM-Orchestrated Agent Pipeline for Music-Driven Video Mashup & AMV Generation

Universal remote control for AI coding agents via messaging apps

Official EzRemove AI skills for background removal — remove image backgrounds and create transparent PNGs with AI agents.

A context engineering platform for AI-assisted software development.

vv — an AI co-pilot coach for Codex & Claude Code: remembers who you are, judges what's safe to automate, coaches your first real task.