RestGPT
An LLM-driven workflow for carrying out movie and music tasks through REST APIs.
- Source repo
- Yifan-Song793/RestGPT
- Stars
- ★ 1.4k
- Last updated
- 2y ago
- License
- MIT
- Primary language
- Python
- FA score
- 39/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificOpenAI API
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A researcher evaluating multi-step API planning for TMDB can run the 100 human-annotated RestBench-TMDB instructions and their gold solution paths.
- Not a fit if
- Developers wanting their own REST APIs; only TMDB and Spotify scenarios are provided
- Teams unwilling to risk Spotify data loss; the init script removes all Spotify data
- Maintenance
- No commits for 6+ monthslast commit 2024-06-07
- Source review
- 39/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
RestGPT is the code accompanying the paper “RestGPT: Connecting Large Language Models with Real-World RESTful APIs,” built to let a large language model control real-world applications. It uses an iterative coarse-to-fine online planning framework and an executor for RESTful API calls. Its stated modules are a Planner, API selector, and Executor; the Executor includes a Caller and Parser, with the Parser generating Python code from a response schema. The repository supplies TMDB movie-database and Spotify music-player scenarios and is run through command-line scripts; it does not document a hosted service, web UI, or long-running deployment model.
After a user runs python run.py, they enter a TMDB or Spotify scenario and a natural-language instruction. The Planner generates the current natural-language sub-task, the API selector maps it to a finer API-calling plan, and the Executor runs that plan. The Caller organizes API parameters from the plan and API documentation, while the Parser generates Python code to parse API responses using their response schemas. For batch evaluation, python run_tmdb.py sequentially executes RestBench-TMDB instructions; python run_spotify.py is provided for RestBench-Spotify, but requires manually changing query_idx and opening Spotify on the device.
- A researcher evaluating multi-step API planning for TMDB can run the 100 human-annotated RestBench-TMDB instructions and their gold solution paths.
- A developer who needs to decompose “Who is the director of today’s most trending movie?” can follow the TMDB flow from a trending request to movie credits.
- A Spotify user creating a playlist named “Love Mariah” with three Mariah Carey songs can study the documented search, user lookup, playlist creation, and track-addition path.
- A research team examining how natural-language sub-tasks, API selection, parameter construction, and response parsing form a REST call chain can use the repository’s stated module structure.
- Someone comparing API-path lengths across two real-world scenarios can use RestBench’s TMDB and Spotify statistics and gold paths.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
pip install langchain colorama tiktoken spotipy openai
- Config files
config.yaml
How do you install or deploy this agent?
Install the listed dependencies: pip install langchain colorama tiktoken spotipy openai. Create the log directory: mkdir logs. Obtain an OpenAI key, a TMDB key, and a Spotify key from their respective providers, then place your keys in config.yaml; the README does not document the config.yaml field format or a required Python version.
How do you use this agent?
After configuring credentials, run python run.py and enter a scenario (TMDB or Spotify) and an instruction. Use python run_tmdb.py for the TMDB benchmark; use python run_spotify.py for the Spotify benchmark after manually changing query_idx and opening Spotify on your device. The optional python init_spotify.py removes all Spotify data, so run it only when you explicitly intend to initialize that environment.
What are this agent's strengths and limitations?
- Separates planning, API selection, parameter organization, and response parsing into named components rather than presenting only one-off API calls.
- RestBench covers two real-world scenarios, TMDB and Spotify, with human-annotated gold solution paths.
- The Parser explicitly generates Python parsing code from a response schema, addressing post-call response handling.
- Provides an interactive entry point plus dedicated TMDB and Spotify batch scripts.
- Execution depends on an OpenAI key, and the README identifies OpenAI as the model-credential source.
- The only documented application scenarios are TMDB and Spotify; no procedure for integrating other REST APIs is provided.
- The Spotify benchmark requires Spotify to be open on a device and requires manual
query_idxchanges. init_spotify.pyremoves all Spotify data, creating a material initialization risk.- The README does not specify the
config.yamlfields, Python version, or a service deployment approach.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| RestGPT This agent | 39 · Major gaps | CLIFree + model costs | ★ 1.4k | 2y ago | Python | OpenAI API |
| Remembra Relay | 83 · Good | Agent plugin / skillFreemium | ★ 17 | 10d ago | Python | Claude Code |
| Genie | 78 · Good | CLIFree + model costs | ★ 354 | 1d ago | TypeScript | Codex · Claude Code |
| Planning with Files | 77 · Good | Agent plugin / skillFree | ★ 28k | today | Shell | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The README identifies OpenAI, TMDB, and Spotify keys and tells users to place them in config.yaml, giving limited visibility into credential sources and configuration. It does not explain secret protection, least privilege, data flows, or safeguards around external calls. It explicitly warns that the Spotify initialization script removes all Spotify data, but describes no confirmation step or recovery, so external effects are disclosed while rollback is unaddressed. The paper citation and code attribution support source attribution; no dependency-security evidence is provided.
The README describes the planner, API selector, executor, and submodules, and lists run commands and benchmark scripts, offering some operational guidance. It provides no error handling, failure messages, dependency versions, or availability measures. The documentation shows no clear internal contradiction, supporting a partial self-consistency score.
The README names TMDB movie data and Spotify music as scenarios and gives multi-step task examples, so scenario coverage is reasonably clear. The apparent scope centers on those two scenarios, but boundaries and applicability conditions are not explicit. Runtime guidance mentions Python scripts and keys but omits environment details; trigger guidance is limited to entering a scenario and instruction.
The README organizes material into overview, modules, data, setup, run instructions, and citation, with examples for TMDB and Spotify. Installation guidance lists pip dependencies, a logs directory, and key configuration, but omits versions and a complete environment specification. FAQ and limitations are sparse, though the demo is marked under construction. The MIT license text is complete. The update history contains 2023 release entries and the demo notice, while maintenance responsibility and a future update path remain unclear.
The documentation gives a readable module overview, task examples, and launch commands, but no sample runtime output or failure behavior, limiting evidence for output usability. Connecting LLM planning and execution to REST APIs, alongside TMDB and Spotify benchmarks, indicates a concrete task value. Costs, resource use, and quantified benefit are not documented, so cost-benefit evidence is thin.
The README makes architecture, benchmark size, example paths, and setup steps specific and cites the paper, making some claims traceable. The available evidence is limited to the README and license, with no code, tests, or configuration materials to corroborate them. Dataset statistics and feature descriptions are reported, but verified facts are not clearly separated from project goals or claims, limiting verifiability.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The README warns that init_spotify.py removes all Spotify data; verify its exact effects and recovery options before running it.
- Setup requires keys for multiple services but does not describe secret protection, permission scope, or external data flows; this assessment is limited to the README and LICENSE sample.
FAQ
Which credentials are required?
config.yaml.Which applications can it operate?
Does it make external calls?
Is Spotify initialization safe?
python init_spotify.py removes all Spotify data.Is RestGPT free?
Is RestGPT open source?
Is RestGPT still maintained?
Who makes RestGPT?
Thanks — we use this to improve the page.