Webinar Brutalist — Live Sessions for PractitionersのLPの技術スタックは？

Sentient Foundation | Open-Source AGI のWebデザイン

The Sentient Foundation is uniting builders, researchers, and communities to empower the development of open-source AGI.

def dream(thought): if thought == "open AGI": return "∞ (machine's dream ∩ human's dream)" data =collect_from_contributors(thought) return synthesize([dream(fragment) for fragment in data]) BUILDING THE OPEN-SOURCE FUTURE OF INTELLIGENCE We empower the development of open-source artificial intelligence that is aligned with humanity and never controlled by a single entity UNITING BUILDERS, RESEARCHERS, AND COMMUNITIES TO EMPOWER THE DEVELOPMENT OF OPEN-SOURCE AGI A neutral, transparent steward of the open AGI ecosystem, with a mandate spanning research, governance, and global outreach OUR MISSION LEARN MORE [ + ] Where AI learns to feel, and you shape what it becomes OPEN SOURCE. OPEN SENSES. OPEN FUTURE. We are a growing collective of researchers, engineers, thinkers exploring the frontier of artificial intelligence, in the open, for everyone JOIN US [ + ] RESEARCHERS BUILDERS CEOS FOUNDERS COMMUNITY BUILDERS ENGINEERS import dspy from roma_dspy import Aggregator, Atomizer, Executor, Planner, Verifier, SubTask from roma_dspy.types import TaskType # Optional tool that the Executor may call def get_weather(city: str) -> str: """Return a canned weather report for the city.""" return f"The weather in {city} is sunny." # Executor geared toward ReAct with a Fireworks model executor_lm = dspy.LM( "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", temperature=0.7, cache=True, ) executor = Executor( lm=executor_lm, prediction_strategy="react", tools=[get_weather], context_defaults={"track_usage": True}, ) # Atomizer decides when to branch into planning atomizer = Atomizer( lm=dspy.LM("openrouter/google/gemini-2.5-flash", temperature=0.6, cache=False), prediction_strategy="cot", context_defaults={"track_usage": True}, ) # Planner produces executable subtasks for non-atomic goals planner = Planner( lm=dspy.LM("openrouter/openai/gpt-4o-mini", temperature=0.85, cache=True), prediction_strategy="cot", context_defaults={"track_usage": True}, ) aggregat