Skip to main content

Deterministic fake APIs for AI agent tests

Project description

ghost-env

Deterministic, in-process fake HTTP APIs for testing agents and tools. Swap real network calls for canned GitHub, Stripe, Postgres-shaped data, OpenAI / Anthropic-style LLM JSON, S3-like objects, Slack Web API responses—while recording traffic, exporting JSON / Markdown / HAR, running eval scenarios, and optionally injecting chaos (latency, random failures).

Same ideas in TypeScript (npm) and Python (PyPI / local install).


Install

JavaScript / TypeScript (npm)

npm install ghost-env

Requires Node.js ≥ 18. No runtime npm dependencies.

Python

pip install ghost-env

From a clone (editable):

pip install -e ./python

Requires Python ≥ 3.10.


Quick start

TypeScript

import { GhostEnv, github, exportRecordingJSON } from "ghost-env";

const env = new GhostEnv({
  seed: 42,
  providers: [github({ issues: [{ repo: "acme/api", title: "Bug" }] })],
});

const res = await env.fetch("https://api.github.com/repos/acme/api/issues");
console.log(await res.json());
console.log(exportRecordingJSON(env.calls()));

Python

from ghost_env import GhostEnv, github, export_recording_json

env = GhostEnv(
    {"seed": 1, "providers": [github({"issues": [{"repo": "acme/api", "title": "Bug"}]})]}
)
status, text = env.fetch("https://api.github.com/repos/acme/api/issues")
assert status == 200
print(export_recording_json(env.calls()))

Features

Area What you get
Presets GitHub issues, Stripe customers, Postgres db().query(), OpenAI chat, Anthropic messages, S3 GET/list, Slack auth.test / chat.postMessage
GhostEnv.fetch Same shape as globalThis.fetch; routes to the first matching provider
Recording calls(), wasCalled(), exportRecordingJSON / Markdown / HAR
Eval runEval + defineScenario for scripted agent tests
Replay ReplayFixture replays canned responses in order
Chaos chaos: { minLatencyMs, failureRate } on config

Documentation

Doc Contents
Getting started Providers, fetch, recording
Presets URLs, config shapes, matching rules
API reference GhostEnv, Provider, eval, replay, exports
Testing & chaos runEval, chaos options, failure recording
Python notes Node vs Python differences

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ghost_env-0.1.0.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ghost_env-0.1.0-py3-none-any.whl (9.7 kB view details)

Uploaded Python 3

File details

Details for the file ghost_env-0.1.0.tar.gz.

File metadata

  • Download URL: ghost_env-0.1.0.tar.gz
  • Upload date:
  • Size: 7.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.14.3 HTTPX/0.28.1

File hashes

Hashes for ghost_env-0.1.0.tar.gz
Algorithm Hash digest
SHA256 2327f184488aadb1d326f9425ab4061eae3a2e99a3482f62bb9bb12351f3d045
MD5 f600ba488560f466150bf7adc5543b35
BLAKE2b-256 86ca14a332253947d36db543b5113af5e8cd3f6b52bc8399d5d4b541d9a29dc6

See more details on using hashes here.

File details

Details for the file ghost_env-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ghost_env-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.14.3 HTTPX/0.28.1

File hashes

Hashes for ghost_env-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e444e4f1a269809025c117d1d235aa211a34b69ac54a9f57416d3d20c93bb422
MD5 50400a7807c11ff69dd0c4193e8044f3
BLAKE2b-256 0f0edaca6e3bd630d75ac1c0f2d125c481d15fe7a01b2b16d7236fab1aa43af1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page