# openresponses/openresponses

Repository: https://github.com/openresponses/openresponses
Canonical: https://ross.abutalabs.com/products/openresponses
Homepage: https://openresponses.org
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-07-14T21:55:16+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 35, longevity 16
- inputs: {"age_days": 231, "days_push": 50, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1100, forks 66 (observed 2026-08-28T04:03:35.309180+00:00)

## What it is
Open Responses is an open-source specification for multi-provider, interoperable LLM interfaces modeled on the OpenAI Responses API, defining a shared request/response schema, semantic streaming events, and tool invocation patterns. The repo ships the OpenAPI spec, documentation, and a compliance test suite (web UI and CLI) for validating provider implementations.

## Use cases
- build LLM apps that work across multiple model providers
- validate my LLM API against the OpenAI Responses API spec
- implement a provider-compatible responses endpoint
- standardize tool calling and streaming across LLM vendors
- run compliance tests on my inference server in CI
- avoid vendor lock-in for LLM API integrations

## When to choose
- you want one schema that maps to many LLM providers
- you're building an agentic workflow with consistent streaming and tool calls
- you need to verify your API's compatibility with the Responses API shape
- you want an extensible spec that accommodates provider-specific features

## When to avoid
- you only call a single provider's SDK directly and don't need portability
- you need a full inference runtime or model server rather than a specification
- you depend on provider-specific features outside the spec's core schema

## Facets
- artifact type: framework
- maturity: active
- function: llm-inference, agent-framework, api-framework, testing, sdk
- domain: large-language-models, apis, developer-tools
- platform: bun, cross-platform
- tags: openai-responses-api, openapi-specification, llm-interoperability, multi-provider, streaming-events, tool-calling, compliance-testing, specification, ai-agents, nodejs, web-server

## Member repositories
- openresponses/openresponses (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.309180+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 2026-08-30T06:45:48.925805+00:00, confidence not recorded.
  - readme: https://github.com/openresponses/openresponses (fetched 2026-08-28T04:03:35.309180+00:00, sha 60b2061aeaef)
  - homepage: https://openresponses.org (fetched 2026-08-29T12:49:02.853349+00:00, sha 1a1fc6fc9100)
  - site_page: https://www.openresponses.org/changelog (fetched 2026-08-29T12:49:02.855811+00:00, sha a0928649335e)
- Data as of 2026-08-30T08:39:29.467469+00:00.