savings

Token Saver

boltToken Saver

Compress tool output (RTK)

git/grep/ls/tree/logs → 60-90% fewer input tokens

Compress context (Headroom)

Checking…

Compress prompts via /v1/compress before routing to the model

Compress LLM output (Caveman)

Terse-style system prompt → ~65% fewer output tokens (up to 87%)

Lazy senior dev (Ponytail)

Bias the model toward minimal code: YAGNI, reuse stdlib, deletion over addition

Compress prompts as images (PXPIPE)

Checking…Dashboard

Transforms large textual context into optimized images before sending to the LLM. Ideal for huge prompts, tool outputs and long conversations.

shieldGuards & Shields

Loop Guard

Detects repeating tool call sequences and text-only planning loops. Injects corrections to prevent infinite agent run-loops.

Circuit Breaker

Temporarily halts upstream calls for offline or failing providers to prevent spamming and conserve connection resource.

Semaphore (Concurrency Limiter)

Enforces simultaneous request limits per provider account. Prevents rate-limits (429) and account blockings.