# vamplabAI/sgr-agent-core

Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community

Repository: https://github.com/vamplabAI/sgr-agent-core
Canonical: https://ross.abutalabs.com/products/sgr-agent-core
Homepage: https://vamplabai.github.io/sgr-agent-core/
Language: Python
License: MIT
License Family: permissive
Topics: agent, llm, sgr, so, structured-output, openai-api, deep-research, research, function-calling
Last push: 2026-07-16T15:57:08+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 93, longevity 26
- inputs: {"age_days": 372, "days_push": 48, "days_rel": 49, "gap_med": 15, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1117, forks 178 (observed 2026-08-28T04:03:38.915178+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, http-server, api-framework, search-engine, prompt-engineering
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, self-hosted, cli
- tags: schema-guided-reasoning, structured-output, deep-research, openai-compatible, function-calling, streaming, deepsearch, ai-agents, search, docker, web-server

## Member repositories
- vamplabAI/sgr-agent-core (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.915178+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:55.503303+00:00, confidence not recorded.
  - readme: https://github.com/vamplabAI/sgr-agent-core (fetched 2026-08-28T04:03:38.915178+00:00, sha 49dfe5149917)
  - registry_pypi: https://pypi.org/pypi/sgr-agent-core/json (fetched 2026-08-29T12:45:51.706216+00:00, sha 0889df167447)
- Data as of 2026-08-30T08:39:29.467469+00:00.