Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Mooncake
AI repositoriesMooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
git clone https://github.com/kvcache-ai/Mooncake.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 -
NeoHorse-1-9B
Modelstext generation model by TokenRhythm · transformers
TokenRhythm/NeoHorse-1-9B -
LeanKG
MCP serversLeanKG: Stop Burning Tokens. Start Coding Lean.
git clone https://github.com/FreePeak/LeanKG.git -
dsh-see-now
AI repositories让 AI 实时看见你的屏幕:按变化量筛选帧、多帧拼进一张图,静止画面几乎不花 token
git clone https://github.com/SAOS-3624/dsh-see-now.git -
codesight
Tools & appsUniversal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
git clone https://github.com/Houseofmvps/codesight.git -
ollama-benchmark
Datasets & benchmarksOllama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
git clone https://github.com/LarHope/ollama-benchmark.git -
design-dna
SkillsTurn reference UIs (images, screenshots, URLs) into quantified Design DNA JSON—tokens, qualitative style, visual effects—then generate matching UI from your content.
git clone https://github.com/zanwei/design-dna.git -
clawcodex
AI repositoriesToken efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.
git clone https://github.com/agentforce314/clawcodex.git -
claude-devtools
Tools & appsThe missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
git clone https://github.com/matt1398/claude-devtools.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 -
tokenops
Agents & frameworksRun-aware token governance for multi-agent systems.
git clone https://github.com/theagentplane/tokenops.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 -
tokentop
Tools & appshtop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and coding agents
git clone https://github.com/tokentopapp/tokentop.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 -
ux-ui-agent-skills
SkillsTurn Claude into a senior design architect: DTCG tokens, 52 components, WCAG 2.2 AA-AAA, 138 design systems, any-framework code, and 50 objective gates that fail the build instead of faking success.
git clone https://github.com/plugin87/ux-ui-agent-skills.git -
stylekit
PromptsStyleKit(stylekit.top)— 149 curated web & UI design styles with copy-ready AI prompts, design tokens and component recipes. Open-source, by AnxForever.
git clone https://github.com/AnxForever/stylekit.git -
smg
AI repositoriesEngine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
git clone https://github.com/smg-project/smg.git -
ThinkingCap-Qwen3.6-27B
Modelsimage text to text model by bottlecapai · transformers
bottlecapai/ThinkingCap-Qwen3.6-27B -
dsh-cost-meter
AI repositoriesCost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.
git clone https://github.com/Han-1413141/dsh-cost-meter.git -
how-to-train-your-gpt
Docs & tutorialsBuild a modern LLM from scratch. Every line commented. Explained like we are five.
git clone https://github.com/raiyanyahya/how-to-train-your-gpt.git -
Swift-Qwen3.8-27b
Modelsimage text to text model by ukisai · transformers
ukisai/Swift-Qwen3.8-27b -
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 -
DBHub
MCP serversToken-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite
@bytebase/dbhub@1.7.0
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.