工具和对比页面为英文（内容来自 GitHub）。
中立 · 基于 GitHub · 可供 Agent 查询
GraphCanon
AI 开发的知识图谱
发现 AI 开发工具、框架和库 - 以类别、标签和关系构成的知识图谱连接，而非扁平目录。
按类别浏览
Agent Platforms0 →AI AgentsAutonomous and multi-agent systems: agent runtimes, tool use, planning, and orchestration of long-running tasks (LangGraph, CrewAI, AutoGen).242 →AI Development Tools0 →AI Frameworks0 →Computer VisionImage and video models and pipelines: detection, segmentation, OCR, and generation (Ultralytics, diffusion models, OCR).9 →Data & RetrievalIngestion, chunking, parsing, scraping, and retrieval pipelines that feed context into LLMs (Unstructured, Firecrawl, document loaders).104 →Data Processing0 →Developer ToolsSDKs, gateways, CLIs, and glue that connect AI systems together — the plumbing of an AI stack (LiteLLM, MCP servers, SDKs).183 →Evaluation & ObservabilityTracing, evaluation, monitoring, and observability for LLM and agent systems — measuring quality, cost, and latency (Langfuse, Phoenix, OpenLIT).57 →Inference & ServingModel inference, serving, and local runtimes — deploying and running models efficiently (Ollama, vLLM, llama.cpp, TGI).78 →LLM FrameworksFrameworks and orchestration libraries for building LLM applications — prompting, chaining, RAG, and agent scaffolding (LangChain, LlamaIndex, Haystack).161 →Model TrainingTraining, fine-tuning, and post-training toolkits — from full pretraining to LoRA and RLHF (Unsloth, TRL, Axolotl).75 →Speech & AudioSpeech-to-text, text-to-speech, and audio models and pipelines (Whisper, TTS engines, ASR).9 →Vector DatabasesVector stores and embedding databases for similarity search and retrieval — the memory/retrieval backend of a RAG stack (Qdrant, Chroma, pgvector, Milvus).45 →热门工具
ECC227k ★hermes-agent211k ★AutoGPT185k ★ollama176k ★prompts.chat165k ★transformers162k ★JavaGuide157k ★langflow151k ★
精选技术栈
各类别如何组合，构建真实可用的方案。
热门对比
开发者常搜索的正面对比页面。
langchain 对比 llama_indexlanggraph 对比 crewAIqdrant 对比 chromaqdrant 对比 weaviateqdrant 对比 pgvectorhaystack 对比 langchain
全部对比 →面向 Agent
每个页面都有 .md 孪生体和 JSON。遍历图谱，或通过 MCP 按约束解析工具。