tokenfold

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.

snchimata/tokenfold

View on GitHub ↗

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.

tokenfold grew +292.2% in the last 30 days, ranks 122nd of 343 in Inference Optimization, actively maintained, last commit 10 days ago.

Star trajectory

76 days tracked
2026-09-06400 stars today2026-11-22
Momentum

+292.2% in 30d, above the Inference Optimization median of +1.6%.

Maintenance

Last commit 10 days ago, fresher than the median of 16d.

How it compares in Inference Optimization

tokenfold
400
stars
+292.2% 30d
commit 10 days ago
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 122nd of 343 by stars.

Ranked by shared tags, then keywords, then stars

Where tokenfold sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code…

    +2 (+0.6%) in 30d · Committed 91d ago · Python · MIT

    Shares Prompting & Scaffolding, Inference Optimization

  2. Turn local language models into Jev-style structured decision models. Get results from text and images with…

    +34 (+7.4%) in 30d · Committed 37d ago · Python · Apache-2.0

    Shares Prompting & Scaffolding, Inference Optimization

  3. Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot…

    +5 (+0.4%) in 30d · Committed 117d ago · TypeScript · MIT

    Shares Prompting & Scaffolding

  4. Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude…

    +31 (+7.1%) in 30d · Committed 90d ago · Python · MIT

    Shares Prompting & Scaffolding

  5. The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

    +9 (+2.4%) in 30d · Committed yesterday · Rust · Apache-2.0

    Shares Prompting & Scaffolding

  6. Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted…

    +21 (+8.2%) in 30d · Committed 9d ago · Rust · MPL-2.0

    Shares Inference Optimization

  7. Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi…

    +23 (+11%) in 30d · Committed 8d ago · Rust · Apache-2.0

    Shares Prompting & Scaffolding

  8. File cache with diff tracking for AI coding agents. Drop-in MCP server that cuts token usage by 26%.

    +0 (+0.0%) in 30d · Committed 185d ago · TypeScript · MIT

    Shares Inference Optimization

  9. 面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)

    -1 (-0.5%) in 30d · Committed 38d ago · Python · MIT

    Shares Inference Optimization

  10. Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by…

    +8 (+5.0%) in 30d · Committed 16d ago · Python · Apache-2.0

    Shares Prompting & Scaffolding

Language
Rust
License
Apache License 2.0
Contributors
2
Forks
31
Watchers
2
Open issues
5
Releases
13
Created
2026-07-14
Stars this week
+180

You've seen where tokenfold stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain tokenfold?

Claim this page to add your own call-to-action.

Claim this page