Group: GitHub Aigoodle

Sort by:Popular▼

✓Popular✓Newest

Model management: provider/credential registry, model instance factory and a Spring AI based invocation layer (chat, embedding, rerank). Importable standalone.

Knowledge base / RAG: document loading, template-based chunking, embedding indexing and hybrid (vector + keyword) retrieval with reranking. Depends on agent-start-model.

Tool / connector ecosystem: a Tool SPI, built-in tools, a Spring AI ToolCallback adapter and an MCP client provider — the n8n-style integration layer agents and workflows call into.

Workflow / agent orchestration: a DAG engine with a variable pool and real nodes (LLM, agent, knowledge retrieval, condition, HTTP, template, classifier, iteration). Depends on agent-start-model; knowledge retrieval is optional.

Enterprise agent runtime: pluggable strategies (ReAct, function-calling), persistent conversation memory, multi-agent delegation and human-in-the-loop tool approval. Depends on agent-start-model and agent-start-tools.

Observability / LLMOps: per-call token + cost + latency metering for every LLM invocation, persisted for aggregation, with optional Micrometer metrics. Plugs into the model module via ChatModelDecorator.

Triggers and automation (n8n-style): webhook, cron and event triggers that asynchronously drive workflows (or any pluggable target), with invocation history and replay. Depends on agent-start-workflow.

Ready-to-use REST web layer that exposes every module (model providers, knowledge, workflow, agent, tools, observability) over HTTP. Built on Spring MVC (servlet) for the request/response surface; token-level SSE for AI chat lives in ...

Reactive AI-chat surface: OpenAI-compatible /chat/completions plus the Dify /chat-messages compatibility endpoint, both driven by the same AppGenerateService facade. Built on Spring WebFlux (Netty) so token-level SSE does not ...

Shared utilities: JSON, crypto, exceptions, paging — used by all spring-agent-start modules.

Modular, Dify-inspired AI building blocks for Spring Boot: model management, knowledge base (RAG) and workflow/agent orchestration. Import only the module you need.

Spring Boot Starter —— WebFlux/Netty 侧的流式 AI 聊天层聚合。 引入本 starter 即等价于同时引入: - agent-start-completion OpenAI 兼容 /chat/completions/{appId} + Dify 兼容 /chat-messages (含 springdoc / swagger-webflux) ...

Runnable demo wiring all modules together; also hosts cross-module integration tests.

Aggregator for optional ModelProvider starters that plug native vendor SDKs into agent-start-model. Adding a child jar (deepseek / zhipu / volcengine / ...) transparently upgrades the matching built-in OpenAI-compatible preset ...

DeepSeek model provider using the official spring-ai-deepseek SDK. Adding this jar transparently upgrades the built-in "deepseek" preset from the generic OpenAI-compatible client to the native DeepSeek client, which surfaces ...

Volcengine Ark (Doubao) model provider. Uses the OpenAI-compatible REST protocol under the hood but exposes an explicit "endpointId" credential field — Volcengine identifies inference endpoints by ep-xxx ids rather than model ...

Zhipu AI (GLM) model provider using the official spring-ai-zhipuai SDK. Adding this jar transparently upgrades the built-in "zhipu" preset from the generic OpenAI-compatible client to the native Zhipu client (which supports ...

Standalone Spring Boot server: bundles every module and exposes /api/v1 REST + SSE endpoints. Run this to have a working backend without embedding the SDK into your own app.

Aggregator for optional VectorStoreFactory starters that back agent-start-knowledge. Add one of the child jars (pgvector / elasticsearch / milvus) to your app to switch the vector store away from the in-memory default.

Elasticsearch-backed VectorStoreFactory for agent-start-knowledge. One index per dataset.