GitHub agents

Your personal chatGPT as Telegram Bot

Chat with Github Repositories (w/ multiple filetypes). Provides flexible backend: Select from different Vectorstores, Context Retrieval-methods and LLMs.

A powerful starting point for creating a feature-rich Discord bot that utilizes modern slash commands.

Wheat Farming AI Disease Detection and Chatbot Support

An Gemini AI Story Maker App along with Story Viewer. User could Read Stories and also make their own Stories using AI

📄 Serverless MinerU 2.5 Pro PDF parser on RunPod. Scales to zero. PDF → Markdown + JSON.

A visual webapp that helps you figure out how to ingest, extract, and RAG. Design a pipeline, see the tradeoffs, get an architecture recommendation, export a plan.

Guia técnico aberto de engenharia de agentes de IA em produção (em português): agentes ReAct e multi-agente, engenharia de contexto, avaliação e observabilidade (LLM-as-a-Judge, Langfuse), LangGraph e RAG avançado/Graph/Agentic (LlamaIndex, Neo4j).

Multi-agent LLM trading system implementing arXiv:2510.04787: agents develop grid-trading strategies offline and a low-latency bot executes them on Binance spot. Research implementation under active correction, not for live capital.

Legal-RAG — A law-grounded, graph-aware retrieval-augmented generation system, featuring statute-centric hybrid retrieval, task-aware routing, and LLM provider-agnostic generation.

The best-benchmarked open-source AI memory system and the first AI memory built to forget.

Agent Skills & DeepSeek Harness (DSH) 扩展库：通用智能体技能（General_skills）+ DSH 标准插件（dsh-plugin），开箱即用的 AI Agent 能力增强集合。

Send the task. Caraka runs it. — a thin bridge from Telegram to the coding agent already installed on your machine.

Curated collection of agency-style profiles with bundled skills for Hermes Agent

Best dev DB for agents — a test database cloned straight from your production. No seeding, no dumps. Real-time Postgres replication of rows and schema, with copy-on-write clones and snapshots.

[EMNLP 2026] Agentic Visual Perception for Long-Document Understanding

Korean stock market data for AI - KOSPI/KOSDAQ closing prices and DART disclosures as free JSON, plus an MCP server. No signup, no API key.

Native iOS companion and Pi extension for controlling an active Pi coding-agent session over a paired WebSocket

Community-maintained self-contained Tauri desktop distribution for DeepSeek Harness

Turn any public GitHub repository into professional, repository-native Agent Skills for ChatGPT and Claude - free, browser-first, no AI API required.

Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.

Why the LLM Wiki pattern breaks past 1,000 files, and the five invariants that fix it. A quote is a pointer, not a copy. Paper + full decision record. Free to read noncommercially with attribution; commercial use licensed.

🦙 chat-o-llama: A lightweight, modern web interface for AI conversations with support for both Ollama and llama.cpp backends. Features persistent conversation management, real-time backend switching, intelligent context compression, and a clean responsive UI.

Control coding agents on your Mac — Claude Code, Codex, Pi, Gemini — from your phone via Telegram. Kick off tasks, stream progress, and approve dangerous commands while away from your desk. Per-chat per-agent sessions, confirm gate, launchd auto-start, corporate-TLS (Zscaler) auto-detection.

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

面向 AI 角色互动的全栈应用，集成 H5 用户端、运营后台、Spring Boot 后端与 SillyTavern。

Curated open-source small tools and workflow recipes for Chinese e-commerce/retail: Douyin/Xiaohongshu/WeChat Channels scraping, Taobao/1688/PDD/JD ops, WeChat SCRM, live-streaming, logistics, Chinese NLP, cross-border. Universal tools kept and tagged.

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

🥈 2nd Prize Winner (Expert Nomination) — Multi-agent clinical AI platform for InterSystems IRIS with FHIR R4, Vector Search RAG, LangChain, live FHIR agents, and a no-code Agent Builder.

A multi-agent engineering crew for Claude Code — one manager plans and verifies, specialist agents read, write, test, research, and review. Hard role separation, cost-tiered models, custom gateway ready.

Deterministic control plane for Codex Agents with typed delegation, durable lifecycle receipts, and journaled writer isolation.

Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server

让 DeepSeek Harness(dsh) 在 HarmonyOS 完整跑起来：缓存优化对话预设 + 启动补丁 + 工具链 | Run DeepSeek Harness on HarmonyOS: cache-optimized agent presets, patches & tooling

Ask and query your markdown notes using AI

Bidirectional Lark/Feishu controller for DeepSeek Harness

The original data contains 500k conversations, but this is just a sample. You can download the 10k dataset with personal and sensitive information removed.

Declarative agent runtime in Go: define governable AI agents as YAML, not code — run them headless, as a service, or on triggers, with policy, limits and an audit trail built in.

Solidity contract auditor: bundled JavaScript call-graph extractor (@solidity-parser/parser) plus a stdlib Python CLI that POSTs each function to a Model Alpha audit endpoint.

HuntForge 铸猎 —— AI 攻防全链路自主解题 Agent（百度 Agent+ 挑战赛作品）：Claude Code 驾驶舱 + 三通道纪律调度 + 88 条离线 CVE 指纹库 + 33 本通用方法论手册 + 二进制/APK 逆向自动化（bin_triage·angr·jadx）+ 幂等提交与证据门禁

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

OpenMotion: The AI-Native Motion Design Platform, Redefining AI-Native Animation and Design. 🕹️

HTTP + WebSocket 反向代理：把局域网端口转发到本地 DSH 服务

## 👨‍💻 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

AI-generated animated explanations of code — paste any function, get a cinematic animation of what it does

Open-source context and memory control layer for LLM applications. Inspect, manage, and selectively reuse the context your AI works with.

Official TypeScript/JavaScript SDK for Cognipeer Console — OpenAI-compatible chat, batch, realtime voice, embeddings, RAG, MCP, agent tracing, and guardrails for multi-tenant AI products.

把学校规章、培养方案和公告变成能提问、可追溯到原始文件与页码的大学 RAG 知识库。

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.

Build-time meta-prompting framework for LLM agents. Treats a prompt as an operator, not a key — designs, audits, and scores it across 7 shapes and 3 modes, and ships a verifier.

All in one memory system for your harness

Windows QQ聊天记录搜索、导出与备份 CLI — QQ NT 本地数据库访问，支持显式授权的 AI Agent 工作流。

Lightweight context-aware agentic api scanner & tester directly in your terminal

Discord server management MCP for AI agents. Chat, moderation, administration, and full server building from one brief. 150+ tools, with destructive actions gated behind a preview.

MCP-сервер внутри 1C:EDT: дает AI-агентам семантический доступ к проекту - код BSL, метаданные, валидация и живая отладка

Local AI workbench for supervised VRChat avatar editing, with a bundled Unity integration, MCP 2.0 (2026-07-28), approvals, checkpoints, and rollback-oriented tools.

Turn any AI agent into a persistent, mission-driven teacher. K Teach is an open Agent Skill + deterministic TypeScript CLI with a structured teaching loop, single-source Lesson Bundle, and cross-session evidence tracking. Derives Web lessons, HTML presentations, and WeChat articles from one source.

DSH Studio — a local development workbench for DeepSeek Harness: project tree, Git review, terminal, and plugin marketplace (Desktop + Web)

可观察、可干预的中文 AI 写作工作台｜Observable AI writing workspace with orchestration, memory, evaluation, and feedback.

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out. DSH plugin + Claude Code plugin + CLI. | 给 AI agent 的稳定可编辑 PPTX 生成：语义 IR 进，原生 DrawingML 出。DSH 插件 / Claude Code 插件 / CLI。

DeepSeek Harness 成年人(18+/adult)互动叙事 Skill：NPC 活人感（有记忆/立场/底线）、自带破甲与张力引擎、随机开局可预锁、时间推进、全维 YAML 存档。仅限虚构成年人。

Design Skills for Agents

Grok Build 从零到精通 · 智见 AI 蓝皮书 · 面向小白与 Claude Code / Codex 迁移用户的 AI Agent 实战指南 · HTML/PDF 免费下载

面向控制理论科研的 AI Agent：论文检索 / 理论推导 / 仿真实验闭环，含工具调用、Docker 沙箱、上下文压缩与本地可观测性。

Supabase CRUD tools for DeepSeek Harness agents (PostgREST, zero-dependency)

AtMem is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

Self-hosted control plane for governed AI agents: approval-first execution, persistent context, reusable profiles and skills, and auditable results.

Screenshot-friendly Social Glass theme and workflow plugin for Herdr on macOS.

Turn client feedback into pull requests automatically.

An AI agent for your desktop and terminal.

A modern, responsive AI chat bot application supporting multiple AI providers including Google Gemini, Groq, OpenRouter, Hugging Face, and OpenAI and enable to store the chat history. Built with React, TypeScript, Vite including typewriter effect, animated icons, application insights & performance dashboard for the best user experience

Ready-to-use, customizable WhatsApp AI GPT4o Chatbot in C# for your Business. Supports GPT-4o with text + audio + image input, audio responses, and improved RAG + MCP Tools 🤩

Generalized implementation of IdleRPG, a game which rewards participants for remaining idle.

SkillFabric: Weaving Task-Specific Wikis for Agentic Skill Routing

DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.

An AI Chief of Staff in plain markdown. Version two: torn down, rebuilt smaller, works better. Model agnostic, ADHD-first, open to anyone.

Connect a coding agent (Claude Code, Codex, Antigravity) to Telegram. Dependency-free, robust, secure.

Parent-operated Hermes profiles for children in WisdomForge bands 5–10, 11–14, and 15–18. Fresh profiles only. Not a kids-AI product.

Use repository evidence to turn requirements into a small set of independently verifiable tasks, then register them in Linear.

dsh plugin: flexible model switch for sub‑agent & plan execution. 为子代理和计划执行选择更合适的模型。

Sticky notes for DeepSeek Harness: draggable notes with text & image support, 9 skins, and AI-powered read/write. DeepSeek Harness 便签插件:可拖拽,支持文字与图片、9 款皮肤,AI 可读写。

Build local Dify workflows through real-time conversation in DeepSeek Harness

A real PowerPoint file. Not a picture of one. Tell your AI what to cover and pptwise builds an editable deck on your own machine. Agent skill + DSH plugin, no account and no API key to render. | 真正的 PPT，不是一张图。跟 AI 说要讲什么，pptwise 在你自己电脑上做出一份能改的 PPT。Agent skill + DSH 插件，不用注册，渲染不用 API key。

AegisAl：基于 Tauri 2、FastAPI 与 LangGraph 的跨平台桌面安全智能体

Aki's rules and skills for UNIFY [Claude, AGY, Grok, Kiro, Ollama,v.v..] packaged for easy install on any machine

Final Year Project of Bachelors of Science (Computer Science). A Voice-Enabled-Urdu-Chatbot build using RASA specifically designed for farmers in Pakistan, they would be able to talk to Chatbot in Urdu Language and get to know the weather forecast for next week, Machinery prices, Fertilizers and Pesticides prices in Urdu Language.

Most intelligent telegram bot

Agent-native research workspace. A deterministic CLI that ingests arXiv / PDF / LaTeX / Zotero papers into an Obsidian-compatible knowledge graph, with local hybrid search (BM25 + vectors), claim-level provenance, and a nightly literature radar.

A Rag App with Spring AI and MongoDB

Groundlens checks RAG answers for grounding and faithfulness against their retrieved sources, the job people reach for hallucination detection, citation checking, or RAG evaluation to do — and differs in returning marks and evidence for a reviewer rather than a verdict or a score to threshold.

Build autonomous AI workflows with multi-agent orchestration, intelligent routing, hybrid RAG, knowledge graphs, MCP tools, persistent memory, and human-in-the-loop execution.

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

[SEC 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems

SIGPAZ | Sistema Full-Stack (Laravel + Angular) | Seguridad: JWT, RBAC, MFA, AES-256 | Arquitectura: SOLID, GoF, C4, FDD | Base de Datos: PostgreSQL + pgvector | IA: RAG (Chatbot semántico) | Backblaze B2

MCP server unifying 169 Google Workspace tools across Drive, Docs, Sheets, Slides, Gmail, Calendar, and Forms behind a single OAuth 2.0 flow. Read-before-edit guards, lazy auth, multi-account profiles, no telemetry.

企业级安全研判多智能体平台，基于多 Agent 协同与 Supervisor-Worker 分层推理架构，融合全链路 RAG 能力体系（文档解析、Hybrid Retrieval、多意图识别、Query Rewrite）与分层记忆机制，实现多源安全事件接入、风险研判、处置决策与智能运维的闭环协同。平台内置可观测与质量评估体系，支持请求级 Trace、Token 消耗分析、成本核算及 KPI 量化评估，实现多 Agent 协同的全流程监控与运行治理。

Local-first semantic memory engine for AI agents - scores, trusts, and forgets so your agent stops making the same mistake twice.