A token compression CLI tool for coding agents.
Raw Developer Origin & Technical Request
Hacker News
Oct 1, 2026
Hey HN! Yolanda and Spencer here - wanted to share a token compression tool that we’ve built for ourselves to save 30% costs on codex!After maxing out sub and burning $700/day per person on api, we fine tuned a compression model to trim codex's tool call output to reduce input token + cache. It cut down tokens by 29.6% and now I just leave it on by default in Codex.To avoid messing up w/ cache, we use proxy + fine tuned qwen model trained on preserving agent trajectory to remove tool call results before they go back to the model, leaving kv cache untouched.The cli is free for everyone to use (github.com/spenmcke/compress Just lmk ur feedback and hacks to shave even more costs on astra! If you want to integrate it into your product to offer the best models at low cost, I can set you up with an sdk and api keysPS: It’s built for coding agents, not conversational agents. I optimized it for file retrieval accuracy, trajectory preservation, and quality to get up to 30% cost reduction depending on how context-heavy the task is.On security and privacy side, it's a proxy wrapping your local codex and ZDR so it doesn't retain any queries. It’s on by default in codex and when you don’t want compression, you can use `codex --uncompress` to disable it.Give it a try: code is in github.com/spenmcke/compress... can install the cli using`curl -fsSL install.everestagi.com/install.sh | sh && source ~/.config/everest/shell.sh`Love to hear any feedback and learn your hacky ways to save token costs too!
Developer Debate & Comments
No active discussions extracted for this entry yet.
Frequently Asked Questions
Market intelligence mapped to A token compression CLI tool for coding agents..
What is the technical positioning of A token compression CLI tool for coding agents.?
What is the general sentiment around A token compression CLI tool for coding agents.?
What are the foundational technologies related to A token compression CLI tool for coding agents.?
Engagement Signals
Cross-Market Term Frequency
Counts stored text matches for foundational terms like API and cache in analysed public discussions. These counts do not measure adoption.
Stored text matches, not adoption or market-share measurements.
- API: 259 records
- cache: 67 records
- coding agents: 47 records
- SDK: 45 records
- proxy: 42 records
- API keys: 24 records
- queries: 17 records
- input token: 6 records
- token compression CLI: 1 records
- Codex/Astra costs: 1 records
- fine tuned compression model: 1 records
- trim tool call output: 1 records
- fine tuned qwen model: 1 records
- preserving agent trajectory: 1 records
- kv cache: 1 records
- conversational agents: 1 records
- file retrieval accuracy: 1 records
- trajectory preservation: 1 records
- cost reduction: 1 records
- context-heavy task: 1 records
- ZDR: 1 records
SaaS Metrics