# wild-card-ai/agents-json

Repository: https://github.com/wild-card-ai/agents-json
Canonical: https://ross.abutalabs.com/products/agents-json
Homepage: https://agents-json.com
Language: Python
License: MIT
License Family: permissive
Last push: 2025-08-21T22:17:46+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 38, release rhythm 40, longevity 41
- inputs: {"age_days": 580, "days_push": 377, "days_rel": 570, "gap_med": 1.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1315, forks 66 (observed 2026-08-28T04:04:20.628187+00:00)

## What it is
agents.json is an open specification built on OpenAPI that formally describes contracts for API and agent interactions, translating OpenAPI definitions into LLM-callable tools. The Wildcard Bridge Python package loads, parses, and executes agents.json files so AI agents can call REST APIs.

## Use cases
- convert openapi spec into llm tools
- let ai agent call rest apis
- define api contracts for ai agents
- build agents that use stripe or resend apis
- parse agents.json files in python

## When to choose
- you want LLM agents to interact with existing OpenAPI-documented REST APIs
- you need a formal, portable spec for API-agent contracts
- you prefer a Python SDK with quickstart examples for common services

## When to avoid
- you need MCP or a different agent-tool protocol
- your APIs lack OpenAPI definitions
- you need a production-hardened framework rather than a v0.1.0 spec

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, api-framework, sdk, parser, auth
- domain: large-language-models, apis, developer-tools
- platform: python, cross-platform
- tags: openapi, llm-tools, api-integration, specification, tool-calling, ai-agents

## Member repositories
- wild-card-ai/agents-json (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.628187+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 2026-08-30T04:48:43.928101+00:00, confidence not recorded.
  - readme: https://github.com/wild-card-ai/agents-json (fetched 2026-08-28T04:04:20.628187+00:00, sha f4d5e1cb01a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.