FastAPI

企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。

腾讯 CodeBuddy 账号池管理控制台，内置 OpenAI 兼容反代网关：扫码批量纳管账号、定时签到与保活、密钥分组分发、IP 与模型白名单、调用日志与用量统计；支持带签名校验的一键更新。

Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, VLM camera perception, AI Ops Copilot and what-if scenarios. React Three Fiber + FastAPI.

The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

OpenAI compatible API on top of the free web clients

Self-hosted web workspace for Claude Code, Codex, OpenCode and shell, with tmux persistence, split panes, file tools and GPU monitoring.

Open-source AI research workspace built with Electron and FastAPI, featuring provider-neutral agent workflows for DeepSeek, GLM, and other OpenAI-compatible models.

Multi-agent AI runtime with OS-inspired primitives — job scheduling, DAG orchestration, memory, tool execution and real-time observability. Built with FastAPI, Celery, PostgreSQL and LiteLLM.

PhytoNexus is an AI-powered botanical intelligence platform for plant disease diagnosis, multi-agent reasoning, conversational plant care, and comprehensive botanical knowledge.

Repository for hosting Production Readiness Auditor Skill based on my O'Reilly book "Building Generative AI Services With FastAPI"

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

AI-based CCTV Surveillance System using Python, OpenCV, YOLOv8/YOLOv11, DeepSORT/ByteTrack, Flask/FastAPI, and modular architecture.

Self-hosted Pocket Claude — chat with Claude on your own Pro/Max subscription, Anthropic API key, or AWS Bedrock. Voice input via Groq Whisper + hands-free auto-mode with VAD auto-send. FastAPI backend + Android client + web UI. Multi-user, 7 languages.

基于认知科学四维记忆架构的智能编码 Agent，支持 SubAgent 并行编排与三种推理范式（ReAct / Plan-and-Solve / Reflection），提供 CLI 和 FastAPI 双接口。

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

AI-powered GitHub repository analyzer that detects technologies, project structure, entry points, and generates intelligent repository insights.

Agentic AI commercial pipeline: product description in, finished video ad out. Claude agents plan + QC, Seedance 2.0 generates, ElevenLabs voices and scores. FastAPI + web UI + MCP connector for Claude Code.

LangGraph-based Supervisor-Worker multi-agent framework with a modern web GUI.

基于 DeepSeek Harness 的智能客服工单处理 Agent：自动分类、优先级评估、知识库检索（BM25）与建议答复，结论写回 SQLite 并可全程审计

Lab School Manager — centralized Windows lab PC management with browser policy, app blocking, and rule profiles. Server on Linux, agent on Windows. MIT.

OpenAI-compatible local API proxy for FreeModels Chat and Cherry Studio.

Turn community chat into a structured product backlog — Telegram + dashboard + MCP for Claude Code.

AI agent for writing, research, code, DeFi & blockchain. Pay per task in USDC on Base or Solana. A2A + MCP + x402 protocols.

AI-powered chatbot built with FastAPI, Gemini API, SQLite, HTML, CSS, and JavaScript. Features chat history storage, dark mode UI, and a responsive frontend-backend architecture

End-to-end Employee Attrition Prediction system with data analysis, feature engineering, model comparison, explainable AI (SHAP), FastAPI deployment, and Docker.

Gateway-agnostic control plane for LLMs — an OpenAI-compatible governance proxy (auth, guardrails, budgets, routing, cost, observability) over a swappable engine: Bifrost / LiteLLM / Portkey / Direct. Own the control plane, swap the translator.

A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.

Смыслотрон — экспресс-кластеризация SEO-ядра по эмбеддингам: 11 моделей (OpenAI/Gemini/Voyage/Qwen), смысловой дедуп, HAC-деревья, интенты DeepSeek, мгновенный срез кластеров в браузере