Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
rtk
AI repositoriesCLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
git clone https://github.com/rtk-ai/rtk.git -
awesome-llm-token-optimization
PromptsA curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.
git clone https://github.com/pleasedodisturb/awesome-llm-token-optimization.git -
token-optimizer-mcp
MCP servers91.5% 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.
git clone https://github.com/ooples/token-optimizer-mcp.git -
headroom
PromptsCompress 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.
git clone https://github.com/headroomlabs-ai/headroom.git -
TokenEconomizer
AI repositoriesExperience-Driven Black-Box Cost Control for Coding Agents
git clone https://github.com/microsoft/TokenEconomizer.git -
token_optimizer
MCP serversReversible context compression for AI agents: cut token usage up to 94%, originals retrievable
slimctx@0.1.0 -
mcp-token-optimizer
MCP serversCut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
mcp-token-optimizer@0.1.1 -
ecotokens
MCP serversToken optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard
git clone https://github.com/hansipie/ecotokens.git -
headroom-desktop
Tools & appsMenu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%
git clone https://github.com/gglucass/headroom-desktop.git -
octave-mcp
MCP serversOCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical pipeline and schema validation.
git clone https://github.com/elevanaltd/octave-mcp.git -
dsh-sieve
Agents & frameworksdsh-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。
git clone https://github.com/Sev7eEn7/dsh-sieve.git -
ratel
SkillsContext 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.
git clone https://github.com/ratel-ai/ratel.git -
contexere
Agents & frameworksThe one place for the skills, keys and memory of every agent you use. Formerly OMNI.
git clone https://github.com/fajarhide/contexere.git -
tokenfold
PromptsPrivate, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
git clone https://github.com/snchimata/tokenfold.git -
ANOLISA
Agents & frameworksANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
git clone https://github.com/agentic-os-org/ANOLISA.git -
rustdsh
MCP serversFast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools
git clone https://github.com/jimoto-no-llm/rustdsh.git -
reshapr
MCP serversThe open source runtime that turns your APIs AI-Native, without rebuilding them
git clone https://github.com/reshaprio/reshapr.git -
vibe-skill
SkillsClaude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
git clone https://github.com/pcx-wave/vibe-skill.git -
mcp-server-code-execution-mode
MCP serversAn 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.
git clone https://github.com/elusznik/mcp-server-code-execution-mode.git -
toolism
MCP serversMeasure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.
git clone https://github.com/rakeshnitb23/toolism.git -
axiomcodegraph
Agents & frameworksTurn 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.
git clone https://github.com/AxiomCodeAI/axiomcodegraph.git -
deepseek-as-subagent
MCP serversRun 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.
git clone https://github.com/PsChina/deepseek-as-subagent.git -
usagetrim
MCP serversFast local CLI and MCP tool for compacting verbose test runners and build output.
git clone https://github.com/00200200/usagetrim.git -
cachebeat
Tools & appsA 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.
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.