Search

pytest for AI agents — trajectory-level recording, replay and assertions for LangGraph/LangChain agents

Agentic NLP — LLM loops + traditional NLP as tools, with human-in-the-loop

DSH 多 Agent 圆桌讨论：独立会话、角色 Prompt、交叉评审与 Markdown 消息流

社区百事通 —— 社区政策咨询智能助手(AI+社会治理):FastAPI + RAG 知识库 + 多轮对话 + 来源引用

AI engine, LLM provider integration (LiteLLM, Instructor, PydanticAI), and CQRS agent reflection for Hexastack

General-purpose agent with transport abstraction, state management, and attachment support

Provider-neutral LLM adapters for Jixu.

Verified evidence scans for a project brief: multi-query scholarly retrieval, citation-graph expansion, DOI verification. No LLM SDK — the hosting agent does the reasoning.

Nano Workforce — an Agent Graph Orchestration application for Agentic SDLC: durable BPMN processes that coordinate a graph of AI agents across the software delivery lifecycle.

A portable agent harness and supervisor orchestration loop for raw LLM backends and multi-agent frameworks.

DeepSeek Harness plugin: per-day token usage statistics — /token-usage command, JSON endpoint, sidebar UI

Browser API for AI agents, over HTTP

Universal Bridge Between Web/Cloud AI Agents (ChatGPT, Gemini, Grok, Claude) & Windows OS

Aegis Invariant Kernel Middleware & Tool Wrapper for Vercel AI SDK (Core / AI)

Python client for MarkVector — store documents, search them by meaning and wording, get grounded answers with citations, keep the original files, and run a streaming, tool-using agent over your own LLM.

LangChain / LangGraph adapter for sonar-tracing.

Universal AI interface - Access GPT-5, Claude, Gemini, Image Generation & more with one simple API

Agent runtime for faapi — LLM-driven ReAct loop over scanned agent / tool registries

LangChain integration for Hydrafetch. Load, search and extract clean web data for agents and RAG.

MemorySync integration for LangChain.js: chat message history, memory tools, and recall context.