Home
Storia in 1 fonti
My agent kept hitting context limits. This one function fixed it.
A zero-dep Python lib that trims LLM conversation history to fit a token budget — and always keeps tool_use/tool_result pairs together.
Raccontata da
dev.to
Timeline cronologica
- ·
My agent kept forgetting what it was doing. A scratchpad fixed it.
A zero-dep Python lib for agent working memory — keyed notes, lists, counters, prompt injection, and JSONL logging in under 200 lines.
- ·
My agent kept hitting context limits. This one function fixed it.
A zero-dep Python lib that trims LLM conversation history to fit a token budget — and always keeps tool_use/tool_result pairs together.
- ·
My Hermes agent's stop condition was a 40-line if/elif chain. I replaced it with 3 lines.
A zero-dep Python lib with composable stop conditions for LLM agent loops — turn limits, cost caps, response patterns, and custom predicates that you can OR/AND/NOT together.
- ·
My Hermes agent spent $3 before I noticed. Now it can't.
A zero-dep Python lib that tracks cumulative LLM API cost and raises before you go over budget — with per-label breakdown and warn-at callbacks.
- ·
Context window exceeded at turn 23. Here's how I track token usage without a tokenizer.
A zero-dep Python lib that tracks estimated token usage across a conversation and fires warning callbacks at configurable thresholds — no tokenizer required.