borhen68 / TokenTamer
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.
Why this job: matched by what the repo talks about: proxy, api, llm, cost
What it does
- Drop-in proxy. No changes needed to your coding agent. Just change the API base URL.
- Long-lived session hijacking. Injects Anthropic cache_control breakpoints into outbound requests. Long Claude Code sessions see up to ~73% off input tokens thanks to cache-first design (cached input is $0.30/Mtoken vs $3.00/Mtoken regular)
- Smart active file detection. Automatically identifies which files you're working on and leaves them 100% intact.
- AST-based compression. Strips function bodies while preserving signatures, imports, and class structures.
- Tool-aware compression. Skeletonizes stale tool_result reads while preserving the latest read of each file. Safe with agents that use function calling.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 months ago
- Stars
- 129
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 1 merged
- 0 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| jannybloug / openai-gemini | 50 | 5 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- ai-coding-agent
- anthropic
- context-compression
- cost-reduction
- developer-tools
- llm
- openai
- proxy
- python
- token-optimization
Project record
- JobModel gateways
- StatusListed
- Commits21
- Forks22
- Watching3
- Stars in 28 days+1
- CreatedJun 8, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026