Python agents

Personal-use MCP server that gives Microsoft 365 Copilot real hands on your own laptop: files, Python, Office, SQL, Web. 100+ tools, autonomous relay, easily extensible, no extra licences.

LinkedIn Content Generator Claude Code Skill

Persistent, semantic news intelligence layer for AI agents — built on GNews (106k+ monthly PyPI). Python lib + MCP server + Claude Code skill.

mlx safetensors qwen3_5 qwen3_6 token-efficient efficient-thinking

A structured library of web security flaws for humans and coding agents with vulnerable examples, attack paths, and secure replacements.

Lightweight AI API cost tracking proxy - one-line base_url change, transparent token and cost monitoring.

本地优先的个人 AI 记忆系统：自动沉淀授权语料，生成可审核记忆，按任务向 Codex、Claude Code 和 Local Agent 提供上下文，并用真实结果持续复核。

Safe AI print concierge for Bambuddy with MCP workflows and human-confirmed queueing

Verified tutorials and demo videos from your README. An AI agent runs it in a hardened Docker sandbox and replays it in a fresh container before anything is published.

Hardware voice recorder audio processor & task dispatcher (SecondBrain style)

Responsible & ESG investment portfolio analyzer (Portfolio Lab style)

Proactive executive AI assistant for autonomous task scheduling (Hey Noah style)

Voice-first dictation & multimodal note synthesizer (Wispr style)

Vibe coding IDE extension helper providing real-time code completion

Real-world AI task evaluation & custom benchmark runner (oqoqo style)

Enterprise AI agent control plane & cost governor (Cohesor style)

AI coding agent context compressor & cost reducer (Paritok style)

Real-time AI agent execution observability & token tracing (Progress AI style)

War - agentic warfare simulation

Your personal chatGPT as Telegram Bot

Give your agent a memory it can prove. One Python file: local SQLite vault, hybrid FTS5 + vector retrieval, Cloudflare-aware fetching, and a research loop whose [V]/[E]/[H] citations are machine-verified by CLI, not prompt-enforced.

[EMNLP'26] Agentic Visual Perception for Long-Document Understanding

MCP server for the GL.iNet GLKVM device

A curated bundle of 38 Claude Skills for quantitative, qualitative, experimental & mixed-methods research in business, finance & social science — from framing a question to submission and replication packages (bilingual 中/EN)

A curated Claude Code plugin marketplace of reusable, self-improving skills and agents — each an independently versioned plugin.

static region:us

Cross-modal brand visual identity & multi-platform ad matrix planner (Omniwork style)

Voice-to-action semantic intent parser & webhook dispatcher (Wispr Action style)

Desktop GUI action recorder & RPA macro generator replay engine

Database schema & query results transformer into high-density LLM context (Polygres style)

Visual canvas workflow node generator & DAG layout synthesizer (Nuphos style)

Visual screen screenshot analyzer & blackboard diagram explainer (Attyn Blackboard style)

Command-line terminal agent for automated scaffolding & vibe coding (Kane CLI style)

Cloud-hosted multi-LLM agent cluster coordinator & sandbox (AgentSky style)

Self-driving software agent & error self-healing runner (Coldtea style)

Real-time LLM inference throughput profiler & benchmark (Inferock Bench style)

Multimodal generative art prompt synthesis & diffusion renderer (SeaArt style)

Agentic decision provenance & cryptographic audit trail logger (Semantica style)

AI Gateway proxy router, rate limiting & PII masking engine (ngrok style)

Multi-agent creative studio for copy & marketing campaign asset generation

Local LLM fine-tuning orchestrator & GPU memory profiler (Unsloth style)

Edge hardware model quantizer, 4-bit tensor adapter & on-device engine (Soup CLI style)

Autonomous sales pipeline stage velocity & deal outcome forecaster (Outcome style)

AI LLM visibility tracker monitoring brand share of voice (Lettertrace style)

Natural language to end-to-end browser test generator & validator (Kane CLI style)

Neural avatar stylization & photo-to-anime transformer (AI Mirror style)

OpenTelemetry distributed tracing & latency profiler for agent pipelines (TraceLLM style)

Automated CI/CD AI regulatory compliance scanner & model risk auditor

Inline cursor context intelligence, instant text rewriter & screen assistant (Attyn style)

Proactive founder calendar negotiation copilot & meeting triage (Hey Noah style)

Agentic software engineer for full-stack application synthesis (LaraCopilot style)

Multi-agent collaborative bug reproduction & patch synthesizer (Muse Code style)

Enterprise agent execution environment & permission boundary governor (Tines style)

High-throughput agent artifact cache & snapshot checkpointer (BearDrive style)

Enterprise issue-to-code contextual graph linker & impact analyzer (Atlassian Context style)

High-fidelity AI photo enhancement & super-resolution upscaler (Fotor style)

Intelligent file routing, dynamic categorizer & cloud sync (FileRouter style)

AI-native DevOps workspace, Terraform IaC synthesizer & drift detector (Nuphos style)

Secure AI agent file sharing & virtual workspace drive (BearDrive style)

Autonomous CI/CD build failure diagnosis & self-healing patch generator

AI-native CRM automating lead scoring & relationship management (Lightfield style)

Autonomous AI PR reviewer & security taint analyzer (Ito style)

Viral social ad variant generator & hook resonance predictor (AdAnt style)

Text and image to 3D polygon mesh generator & glTF synthesizer (VAST 3D style)

Interactive conversational mind map generator & tree structuring (ChatMind style)

Distributed edge AI operating system scheduler & worker router (Cloudflare OS style)

Conversational candidate screening & voice interview agent (Talvo style)

One-click autonomous agent fleet deployer & container orchestrator (BetterClaw style)

Repository-wide codebase migration agent & AST modernization refactorer (Fleet style)

Multi-agent git commit graph visualizer & branch conflict coordinator (GitLens style)

Composable plug-and-play agent harness dispatcher dynamically linking tools

Approval-first AI agent OS for human-in-the-loop autonomous workflows (Soloop style)

Autonomous AI teammate delegation manager & task scheduler (Grok Bot style)

Your personal AI agent. 72 built-in tools, 21 messaging channels, voice, vision, and persistent memory. Runs locally.

Open-source AI-native engineering plugins for Claude Code — project context, code review, security audit, task clarification, and more

Detects intent drift in AI-assisted development by comparing original goals against current execution plans using the Intent Alignment Engine. Features 9 evidence providers and exportable reports (text/markdown/json).

Interactive CLI for Retrieval-Augmented Generation (RAG) with ranking — uses Ollama embeddings + HNSW vector DB + optional reranker for more accurate results

Self-driving web application action driver & headless browser agent (Coldtea style)

Ultra-low-latency real-time voice dictation & meeting memo synthesizer (Wispr style)

Autonomous GitHub PR issue diagnosis & self-merging code fixer (Gitar style)

Multi-agent desktop creative workflow scheduler & batch asset exporter (Omniwork style)

A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem

Emercoin as an identity + memory layer for AI agents: node + adapter + the emercoin-agent MCP server (on-chain identity & durable memory via NVS).

Official SDKs, API clients, and CLI/MCP tools for Daytona, the secure and elastic infrastructure for running AI-generated code

A carnivorous honeypot for AI agents. Every deployment generates a unique persona so no two instances look alike. Detects, fingerprints, and classifies autonomous agent attacks in real time.

Hardened local-only LiteLLM gateway — auto-discovers free/trial LLM models from 15+ providers (OpenRouter, Groq, Gemini, Cerebras, NVIDIA NIM, SambaNova, Cohere, GitHub Models, etc.). Single OpenAI-compatible endpoint at 127.0.0.1:4000. Role-based aliases for AI coding agents.

An Intelligent, Agentic Web Scraping Framework for Automated Schema Discovery and Structural Analysis.

Interactive terminal-first developer agent (Claude Code style)

No-code interactive 3D and XR spatial scene generator (Ctruh style)

SaaS customer churn risk scorer & proactive retention dispatcher

Model-agnostic agent harness switch & provider fallback manager

Conversational spec-to-fullstack code generator (Vibe Coding style)

Conversational user research transcript analyzer & thematic insight clusterer

Autonomous LLM agent failure circuit-breaker & state rollback orchestrator

Scaffold, run & deploy production LangChain agents — frontend and agent in one command. Built-in proxy, 3 chat UIs, zero CORS.

Ask and query your markdown notes using AI

AI智能作业批改系统 - 基于 FastAPI + Vue 3 + LangChain 的全栈教学辅助平台，支持多大模型接入、AI自动批改、智能教学助手、文档查重等功能。

面向 CTF 竞赛评测平台（TSec Benchmark）的自动化 Web/逻辑漏洞挖掘与利用 Agent：分层调度 + 多会话并发 + 跨会话共享黑板 + 平台权威校验

## 👨‍💻 About Me Hi! I'm **Divanshu Singh**, an aspiring **Data Scientist and AI Developer** with a strong interest in Artificial Intelligence, Data Analytics and Software Development. I enjoy building practical projects that combine data, AI and automation. Currently, I'm working on **Pixotic AI Assistant**, a Telegram-based personal AI assi

safetensors llama Arabic English LLM Decoder