InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

7 results with any of your words Clear search and filters
  1. A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

    Indexed GitHub, pleasedodisturb 123 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/pleasedodisturb/awesome-llm-token-optimization.git
  2. headroom

    Prompts

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    Indexed GitHub, headroomlabs-ai 79.8k ★Apache-2.0Updated yesterday

    git clone https://github.com/headroomlabs-ai/headroom.git
  3. tokenfold

    Prompts

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

    Indexed GitHub, snchimata 220 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/snchimata/tokenfold.git
  4. hush

    Prompts

    Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

    Indexed GitHub, V-Songbird 54 ★MITUpdated today

    git clone https://github.com/V-Songbird/hush.git
  5. honey-for-devs

    Prompts

    Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.

    Stale GitHub, Green-PT 340 ★MITUpdated 29 days ago

    git clone https://github.com/Green-PT/honey-for-devs.git
  6. llmtrim

    Prompts

    Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

    Indexed GitHub, fkiene 274 ★MPL-2.0Updated 4 days ago

    git clone https://github.com/fkiene/llmtrim.git
  7. agentic-os

    Prompts

    Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

    Indexed GitHub, KbWen 236 ★MITUpdated 3 days ago

    git clone https://github.com/KbWen/agentic-os.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.