InnerVault

Library

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

Results

  1. rtk

    AI repositories

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    Stale GitHub, rtk-ai 86.3k ★Apache-2.0Updated 4 days ago

    git clone https://github.com/rtk-ai/rtk.git
  2. 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
  3. token-optimizer-mcp

    MCP servers

    91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.

    Indexed GitHub, ooples 583 ★MITUpdated today

    git clone https://github.com/ooples/token-optimizer-mcp.git
  4. 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
  5. TokenEconomizer

    AI repositories

    Experience-Driven Black-Box Cost Control for Coding Agents

    Indexed GitHub, microsoft 6,748 ★Apache-2.0Updated today

    git clone https://github.com/microsoft/TokenEconomizer.git
  6. token_optimizer

    MCP servers

    Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

    Stale Official MCP Registry, io.github.omkar9854 Updated 4 months ago 1 note

    slimctx@0.1.0
  7. mcp-token-optimizer

    MCP servers

    Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

    Stale Official MCP Registry, io.github.rccola990-cloud Updated 5 months ago 1 note

    mcp-token-optimizer@0.1.1
  8. ecotokens

    MCP servers

    Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard

    Stale GitHub, hansipie 20 ★MITUpdated 28 days ago

    git clone https://github.com/hansipie/ecotokens.git
  9. headroom-desktop

    Tools & apps

    Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%

    Indexed GitHub, gglucass 647 ★MITUpdated today

    git clone https://github.com/gglucass/headroom-desktop.git
  10. octave-mcp

    MCP servers

    OCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical pipeline and schema validation.

    Stale GitHub, elevanaltd 54 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/elevanaltd/octave-mcp.git
  11. dsh-sieve

    Agents & frameworks

    dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

    Stale GitHub, Sev7eEn7 110 ★MITUpdated 15 days ago

    git clone https://github.com/Sev7eEn7/dsh-sieve.git
  12. ratel

    Skills

    Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

    Stale GitHub, ratel-ai 558 ★MITUpdated 5 days ago

    git clone https://github.com/ratel-ai/ratel.git
  13. contexere

    Agents & frameworks

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

    Stale GitHub, fajarhide 377 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/fajarhide/contexere.git
  14. 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
  15. ANOLISA

    Agents & frameworks

    ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

    Indexed GitHub, agentic-os-org 666 ★Apache-2.0Updated today

    git clone https://github.com/agentic-os-org/ANOLISA.git
  16. rustdsh

    MCP servers

    Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

    Stale GitHub, jimoto-no-llm 100 ★MITUpdated 15 days ago

    git clone https://github.com/jimoto-no-llm/rustdsh.git
  17. reshapr

    MCP servers

    The open source runtime that turns your APIs AI-Native, without rebuilding them

    Stale GitHub, reshaprio 169 ★Apache-2.0Updated 26 days ago

    git clone https://github.com/reshaprio/reshapr.git
  18. vibe-skill

    Skills

    Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

    Stale GitHub, pcx-wave 124 ★Updated 5 days ago

    git clone https://github.com/pcx-wave/vibe-skill.git
  19. An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

    Stale GitHub, elusznik 340 ★GPL-3.0Updated 11 months ago

    git clone https://github.com/elusznik/mcp-server-code-execution-mode.git
  20. toolism

    MCP servers

    Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

    Stale GitHub, rakeshnitb23 37 ★MITUpdated 23 days ago

    git clone https://github.com/rakeshnitb23/toolism.git
  21. axiomcodegraph

    Agents & frameworks

    Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.

    Stale GitHub, AxiomCodeAI 435 ★Custom licence (see repository)Updated 14 days ago

    git clone https://github.com/AxiomCodeAI/axiomcodegraph.git
  22. deepseek-as-subagent

    MCP servers

    Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.

    Indexed GitHub, PsChina 59 ★MITUpdated 2 days ago

    git clone https://github.com/PsChina/deepseek-as-subagent.git
  23. usagetrim

    MCP servers

    Fast local CLI and MCP tool for compacting verbose test runners and build output.

    Stale GitHub, 00200200 43 ★MITUpdated 23 days ago

    git clone https://github.com/00200200/usagetrim.git
  24. cachebeat

    Tools & apps

    A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.

    Stale GitHub, ARahim3 71 ★MITUpdated 34 days ago

    git clone https://github.com/ARahim3/cachebeat.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.