AI Agent2025
Coordinates role-playing agents to automate real-world tasks — web search and browsing, code execution, document parsing, and multimodal handling. Built on the CAMEL-AI framework; scored 69.09% on the GAIA benchmark, topping open-source frameworks.
AI Agent2025
Provider-agnostic framework for orchestrating multi-agent LLM workflows in Python: agents that delegate via handoffs, function/MCP/hosted tools, input/output guardrails, automatic session memory, and a visual tracing UI for debugging runs.
AI Infra2025
Transforms unstructured financial content—papers, news, blogs, and filings—into a queryable semantic knowledge graph for retrieval-augmented research. Combines domain-tuned LLMs, embedding-based search, and modular ingestion pipelines; aimed at quant research teams and institutional workflows.
AI Deploy2025
Splits LLM inference into separate prefill and decode GPU pools, then routes requests with KV-cache awareness to cut redundant recomputation. Reports up to 30x throughput on DeepSeek-R1 (GB200 NVL72) and works across TensorRT-LLM, vLLM, and SGLang.
AI Agent2025
Builds, evaluates, and deploys multi-agent systems in Python, code-first. A graph-based runtime handles routing, fan-out/fan-in, loops, retries, and human-in-the-loop; a Task API covers agent-to-agent delegation, plus a CLI and web UI.
AI Agent2025
Lets LLM agents drive real Android and iOS devices from natural-language commands by turning each screen's accessibility tree into structured text the model reads directly, not just screenshots. LLM-agnostic; runs via CLI, Python, or Docker.
AI Deploy2025
Run large-language and multimodal models locally on edge devices (Android, iOS, desktop, web, Raspberry Pi) with hardware acceleration, function-calling, and multi-language SDKs—designed for low-latency, privacy-sensitive on-device inference.
AI Agent2025
Framework for building an organization's internal coding agents — runs tasks in isolated cloud sandboxes, integrates with Slack/Linear/GitHub, orchestrates subagents, and automates commits/PRs. Built on LangGraph and Deep Agents for easy customization.
AI Infra2025
Extends RAG beyond text: parses PDFs and Office files containing images, tables, equations, and charts, then queries them through one multimodal knowledge graph. Built on LightRAG, it replaces separate parsing and retrieval tools.
AI Infra2025
Reimplements the vLLM inference engine from scratch in ~1,200 lines of readable Python, matching its offline throughput on small models. Prefix caching, tensor parallelism, torch.compile, and CUDA graphs are all kept legible.
AI Train2025
Trains and optimizes AI agents with reinforcement learning using almost zero code change. Works with any agent framework (LangChain, OpenAI Agents SDK, AutoGen, CrewAI) or none, and can selectively optimize a single agent inside a multi-agent system.
AI Agent2025
Chinese-enhanced fork of TradingAgents that runs multi-agent LLM stock analysis for A-share, HK and US markets, adding domestic models (Qwen, DeepSeek) and local data sources (Tushare, AkShare, BaoStock), with report export to Word and PDF.