Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
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 -
Qwen3.8-Flash-Next-NVFP4
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/Qwen3.8-Flash-Next-NVFP4 -
maro
Agents & frameworksMulti-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
git clone https://github.com/microsoft/maro.git -
AntOmniEvo
Agents & frameworksAn auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
git clone https://github.com/ant-research/AntOmniEvo.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 -
sammo
PromptsA library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)
git clone https://github.com/microsoft/sammo.git -
pruna
AI repositoriesPruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
git clone https://github.com/PrunaAI/pruna.git -
ragbits
PromptsBuilding blocks for rapid development of GenAI applications
git clone https://github.com/deepsense-ai/ragbits.git -
Qwen3.8-Flash-Next-FP4-Local
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/Qwen3.8-Flash-Next-FP4-Local -
GLM-5.2-NVFP4
Modelstext generation model by nvidia · Model Optimizer
nvidia/GLM-5.2-NVFP4 -
metaflow
AI repositoriesBuild, Manage and Deploy AI/ML Systems
git clone https://github.com/Netflix/metaflow.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 -
Qwen3.8-27B-NVFP4
Modelstext generation model by nvidia · Model Optimizer
nvidia/Qwen3.8-27B-NVFP4 -
youtube-automation-agent
Agents & frameworks🎬 Fully automated YouTube channel management with AI agents. Creates, optimizes & publishes videos 24/7. Works with FREE Gemini API or OpenAI. No coding required!
git clone https://github.com/darkzOGx/youtube-automation-agent.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 -
image text to text model by nvidia · Model Optimizer
nvidia/DeepSeek-V4.1-Flash-1017-NVFP4 -
agentdescent
Agents & frameworksGradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
git clone https://github.com/ThinkFlowLab/agentdescent.git -
skill-optimizer
SkillsAgent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.
git clone https://github.com/hqhq1025/skill-optimizer.git -
aaron-marketing-skills
Skills120 marketing skills as an AI marketing staff — plugin, portable skills, or an 8-bot team across 7 disciplines (narrative, SEO/GEO, social, email, paid, influencer, launch) on one contract, with 8 auditor gates: TALE · CORE-EEAT · CITE · ECHO · SEND · ROAS · STAR · RAMP.
git clone https://github.com/aaron-he-zhu/aaron-marketing-skills.git -
gortex
MCP serversHigh-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
git clone https://github.com/zzet/gortex.git -
GLM-5.3-Flash-FP4-Local
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/GLM-5.3-Flash-FP4-Local -
cap-evolve
MCP serversOptimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
git clone https://github.com/skillberry-ai/cap-evolve.git -
Owl
MCP serversRetirement planner with great wisdom
git clone https://github.com/mdlacasse/Owl.git -
ClawRouter
AI repositoriesThe agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
git clone https://github.com/BlockRunAI/ClawRouter.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.