paritok-4b-v1
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cu
Use a compression model to optimize coding tasks, reducing input size and costs while maintaining performance.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeNon-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cu
paritok-4b-v1 has 913 stars on GitHub. It has been forked 114 times. paritok-4b-v1 is written mainly in Python. It has been in active development since 2026. paritok-4b-v1 is available under the Apache-2.0 license. Its main topics are agentic-coding, ai, ai-agents, ai-coding.
What is paritok-4b-v1?
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cu
Is paritok-4b-v1 open source?
paritok-4b-v1 is an open-source project. It is released under the Apache-2.0 license.
Is paritok-4b-v1 free?
Yes. paritok-4b-v1 is free and open source — you can use, modify and self-host it.
What license does paritok-4b-v1 use?
paritok-4b-v1 is available under the Apache-2.0 license.
What language is paritok-4b-v1 written in?
paritok-4b-v1 is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/paritok-official-paritok-4b-v1.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.