# Yifan-Song793/RestGPT

An LLM-based autonomous agent controlling real-world applications via RESTful APIs

Repository: https://github.com/Yifan-Song793/RestGPT
Canonical: https://ross.abutalabs.com/products/restgpt
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-07T13:22:15+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 78
- inputs: {"age_days": 1103, "days_push": 817, "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 1404, forks 106 (observed 2026-08-28T04:04:37.969215+00:00)

## What it is
RestGPT is an LLM-based autonomous agent that controls real-world applications like TMDB and Spotify by planning and executing RESTful API calls. It also ships RestBench, a human-annotated benchmark of user instructions with gold API solution paths.

## Use cases
- control real-world apps with an llm agent via rest apis
- benchmark llm agents on multi-step api calling tasks
- plan and execute sequences of restful api calls from natural language
- evaluate llm planning and api response parsing
- research on connecting large language models to real-world apis

## When to choose
- you need an agent that orchestrates real RESTful APIs like TMDB or Spotify
- you want a benchmark dataset for evaluating API-calling agents
- you are reproducing or extending the RestGPT research paper

## When to avoid
- you need a production-ready agent framework with broad API integrations
- you want a maintained tool with active releases and support
- you need non-REST protocols like GraphQL or gRPC

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-inference, http-client, benchmarking
- domain: artificial-intelligence, large-language-models, apis, developer-tools
- platform: python, cli
- tags: restful-apis, llm-agent, restbench, api-calling, research-paper, openai, ai-agents

## Member repositories
- Yifan-Song793/RestGPT (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:37.969215+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 2026-08-30T04:38:49.620766+00:00, confidence not recorded.
  - readme: https://github.com/Yifan-Song793/RestGPT (fetched 2026-08-28T04:04:37.969215+00:00, sha c02919922ef2)
- Data as of 2026-08-30T08:39:29.467469+00:00.