ThinkLess good first issues (HTML)

Run a self-hosted System One model (Kev or OpenJev) on the decision benchmark 30 days ago

help wanted benchmark

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

Calibrated LLM confidence from token log probabilities 30 days ago

enhancement help wanted provider

inboxpraveen/ThinkLess

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

Test gate() under CrewAI and LlamaIndex tool decorators 30 days ago

good first issue integration

inboxpraveen/ThinkLess

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

Add a zero-shot NLI provider for Hugging Face models 30 days ago

help wanted provider

inboxpraveen/ThinkLess

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

Show the hardest classes per provider on the leaderboard 30 days ago

good first issue benchmark

inboxpraveen/ThinkLess

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

Add a majority-class baseline to the decision benchmark 30 days ago

good first issue benchmark

inboxpraveen/ThinkLess

1

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

HTML

#agents#ai-agents#decision-models#langgraph#llm#llm-routing#mcp#observability#openai-agents#python

inboxpraveen/ThinkLess

Open Issues Need Help