$ loading_
Compress and recover local context for more efficient GPT/Codex token usage.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "TokenSkein" yet — see the docs or source repo.
Compress this local project brief and the last 20 conversation turns into compact context, preserve exact recoverability, and provide statistics for continued GPT/Codex interaction.
Returns a compact context representation, exact recovery details, and relevant statistics.
Recover the original content from this compact context and confirm whether the result matches the pre-compression content exactly.
Outputs the recovered original text and states whether exact recovery was achieved.
Analyze the compression results for this local context, including before/after size and retrieval-related statistics, so I can decide whether to keep sending it to the model.
Provides compression statistics and a brief basis for evaluating suitability.
Developers or researchers interacting with GPT or Codex over long sessions can compress local context before sending it to the model to reduce token usage. The original content can be recovered when needed.
When local notes, project briefs, or conversation logs become lengthy, this tool can compress and retrieve them while preserving information needed later. That makes continued use easier within limited context windows.
For users concerned with prompt cost and context efficiency, it also provides statistics to help assess whether compression is effective. It is useful for optimizing how content is organized for LLM interactions.
It provides compression, retrieval, and statistics for local context economy when interacting with GPT/Codex. Its focus is efficient token usage and exact recovery of compacted content.
Yes. The provided description explicitly says it enables exact recovery of compacted content.
The provided materials do not include installation steps, runtime requirements, or key information. See the source repository for details.
Compress LLM text and JSON to reduce tokens and lower usage costs.
Reduce token usage in Claude Code with automatic context optimization.
Compress conversation context deterministically to reduce token usage.
Store and recall cross-session context locally with token-efficient compression and ranking.
Count tokens for OpenAI-compatible models or encoding names.
Use a local LLM to index codebases and compress Claude Code context.