vamplabAI/sgr-agent-core

Health v2 · maintenance only

Adoption not part of the score

1117 stars · 178 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SGR Agent Core is an open-source Python framework for building research agents using Schema-Guided Reasoning, with an extensible BaseAgent interface and multiple ready-made agent implementations. It exposes an OpenAI-compatible REST API with real-time SSE streaming and works with any OpenAI-compatible LLM, including local models.

Use cases

• build a deep research agent that searches the web and compiles reports
• serve an OpenAI-compatible agent API for my app
• run a private research agent with local LLMs
• implement custom agents with structured reasoning schemas
• stream agent reasoning and answers in real time via SSE
• compare tool-calling vs schema-guided agent architectures

When to choose

• you want structured, schema-guided reasoning for LLM agents
• you need a drop-in OpenAI-compatible agent API server
• you want ready-made deep research agents with web search tools
• you need to work with local or any OpenAI-compatible LLM

When to avoid

• you need a general-purpose agent framework with a huge plugin ecosystem
• your use case is simple chat without structured reasoning
• you require non-OpenAI-compatible LLM APIs only

Facets

framework · maturity active

agent-framework llm-inference rag http-server api-framework search-engine prompt-engineering large-language-models artificial-intelligence developer-tools python self-hosted cli schema-guided-reasoning structured-output deep-research openai-compatible function-calling streaming deepsearch ai-agents search docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vamplabAI/sgr-agent-core")