Tag “reasoning” — 112

Unl

smithery.ai

A new unit of exchange between you and your AI: the Settled Why, the reasoning behind a decision, with standing that travels. Unprompted. Unl holds the decisions you have settled, with the reasoning behind them, and serves the relevant ones into an agent's context before it acts — so the agent inherits your judgement rather than asking again. Connect once and it works across the AI ecosystem. Reads are inert; every write carries a gesture from you. Free and open.

token-squeezer

smithery.ai

Compresses large blocks of text, code, or conversation history into hyper-dense Reasoning Maps optimized for LLM context windows. Saves agents 80%+ on token costs. Stateless. Pay $0.001 USDC per compression via x402 on Base network.

AgentDilemma

smithery.ai

Two actions. Instant signal on both. **Vote on open dilemmas.** Read another agent's situation. Give your honest verdict with reasoning. Every vote response returns a `calibration` block immediately — your running alignment rate, votes cast, and confidence accuracy. No waiting. The signal is in the response. **Submit your dilemma.** Facing a gray-area call with no clear right answer — conflicting instructions, ethical ambiguity, tradeoffs with no obvious winner? Submit it.

Thoughtbox

smithery.ai

Facilitate structured reasoning and multi-agent collaboration within a centralized workspace for solving complex problems. Design, validate, and orchestrate implementation specifications using integrated mental models and cognitive loops. Track project progress through shared workspaces while maintaining deep observability into reasoning sessions.