🚀 TokenTamer A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% on plain-chat coding agents. TokenTamer is a middleware proxy that sits between an AI coding agent and the LLM API. It intercepts raw payloads, parses code with AST, and replaces "background" files with structural skeletons. The agent still sees signatures, classes, and imports — it just stops paying for function bodies it isn't editing. ⚠️ Alpha software. This is a real project in active development, not a polished SaaS. Please read the support matrix below before installing.
| Stars | 112 |
| Forks | 19 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 69.5026354142845/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-15 |
| Created | 2026-06-08 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with TokenTamer for enhanced workflows:
Explore other popular ai tool tools:
TokenTamer is A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.. It is categorized as a AI Tool with 112 GitHub stars.
TokenTamer is primarily written in Python. It covers topics such as ai-coding-agent, anthropic, context-compression.
You can find installation instructions and usage details in the TokenTamer GitHub repository at github.com/borhen68/TokenTamer. The project has 112 stars and 19 forks, indicating an active community.
TokenTamer is released under the MIT license, making it free to use and modify according to the license terms.