b4fbb6fe10
Adds eval-only benchmark for YC-Bench (collinear-ai/yc-bench), a deterministic long-horizon benchmark where the agent acts as CEO of an AI startup over a simulated 1-3 year run. Key design decisions verified against the official yc-bench repo: - Uses 'sim init' (NOT 'yc-bench run') to avoid starting a competing built-in agent loop - Correct DB table names: 'companies' and 'sim_events' - Correct 4 domains: research, inference, data_environment, training - Penalty values are preset-dependent (not hardcoded in system prompt) - Sequential evaluation (each run is 100-500 turns) - Follows TerminalBench2 patterns: KeyboardInterrupt handling, cleanup_all_environments(), tqdm logging handler, streaming JSONL yc-bench added as optional dependency: pip install hermes-agent[yc-bench] Closes #340
85 lines
2.3 KiB
TOML
85 lines
2.3 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "hermes-agent"
|
|
version = "0.1.0"
|
|
description = "The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
authors = [{ name = "Nous Research" }]
|
|
license = { text = "MIT" }
|
|
dependencies = [
|
|
# Core
|
|
"openai",
|
|
"python-dotenv",
|
|
"fire",
|
|
"httpx",
|
|
"rich",
|
|
"tenacity",
|
|
"pyyaml",
|
|
"requests",
|
|
"jinja2",
|
|
"pydantic>=2.0",
|
|
# Interactive CLI (prompt_toolkit is used directly by cli.py)
|
|
"prompt_toolkit",
|
|
# Tools
|
|
"firecrawl-py",
|
|
"fal-client",
|
|
# Text-to-speech (Edge TTS is free, no API key needed)
|
|
"edge-tts",
|
|
# mini-swe-agent deps (terminal tool)
|
|
"litellm>=1.75.5",
|
|
"typer",
|
|
"platformdirs",
|
|
# Skills Hub (GitHub App JWT auth — optional, only needed for bot identity)
|
|
"PyJWT[crypto]",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
modal = ["swe-rex[modal]>=1.4.0"]
|
|
daytona = ["daytona>=0.148.0"]
|
|
dev = ["pytest", "pytest-asyncio"]
|
|
messaging = ["python-telegram-bot>=20.0", "discord.py>=2.0", "aiohttp>=3.9.0", "slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
|
|
cron = ["croniter"]
|
|
slack = ["slack-bolt>=1.18.0", "slack-sdk>=3.27.0"]
|
|
cli = ["simple-term-menu"]
|
|
tts-premium = ["elevenlabs"]
|
|
pty = ["ptyprocess>=0.7.0"]
|
|
honcho = ["honcho-ai>=2.0.1"]
|
|
mcp = ["mcp>=1.2.0"]
|
|
homeassistant = ["aiohttp>=3.9.0"]
|
|
yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git"]
|
|
all = [
|
|
"hermes-agent[modal]",
|
|
"hermes-agent[daytona]",
|
|
"hermes-agent[messaging]",
|
|
"hermes-agent[cron]",
|
|
"hermes-agent[cli]",
|
|
"hermes-agent[dev]",
|
|
"hermes-agent[tts-premium]",
|
|
"hermes-agent[slack]",
|
|
"hermes-agent[pty]",
|
|
"hermes-agent[honcho]",
|
|
"hermes-agent[mcp]",
|
|
"hermes-agent[homeassistant]",
|
|
]
|
|
|
|
[project.scripts]
|
|
hermes = "hermes_cli.main:main"
|
|
hermes-agent = "run_agent:main"
|
|
|
|
[tool.setuptools]
|
|
py-modules = ["run_agent", "model_tools", "toolsets", "batch_runner", "trajectory_compressor", "toolset_distributions", "cli", "hermes_constants"]
|
|
|
|
[tool.setuptools.packages.find]
|
|
include = ["tools", "hermes_cli", "gateway", "cron", "honcho_integration"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
markers = [
|
|
"integration: marks tests requiring external services (API keys, Modal, etc.)",
|
|
]
|
|
addopts = "-m 'not integration'"
|