Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Sharp-Spark-X2.6-4B-GGUF
Modelstext generation model by peculiar-ragdoll · gguf
peculiar-ragdoll/Sharp-Spark-X2.6-4B-GGUF -
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 -
image text to text model by bottlecapai · transformers
bottlecapai/ThinkingCap-gemma-4-26B-A4B-it -
image text to text model by SC117 · gguf
SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF -
turbo-browser-mcp
MCP serversPlaywright MCP server built to cut agent turns and tokens: one-call form filling, delta snapshots, batched steps, and a submit guard on by default
git clone https://github.com/Tthanh2k6/turbo-browser-mcp.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 -
WorkFlowX
Agents & frameworks一个更强调可控、可追踪和 Token 效率的 AI 多智能体开发工作流 || An AI multi-agent development workflow that emphasizes controllability, traceability, and token efficiency
git clone https://github.com/TreeX-X/WorkFlowX.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 -
code-conductor
SkillsA governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.
git clone https://github.com/yeisonrestrepo/code-conductor.git -
agent-token-saver
SkillsTypeScript/Bun tools for coding agents. Run checks once, keep complete evidence, and test output filters against task-specific requirements. No runtime packages.
git clone https://github.com/Supersynergy/agent-token-saver.git -
dejavu
MCP serversAI agent skills marketplace — token-efficient skill search & execution
-
pitlane-mcp
Tools & appsToken-efficient navigation substrate for AI coding agents. Index code once and retrieve only the symbols you need.
git clone https://github.com/eresende/pitlane-mcp.git -
semantic-frame
MCP serversToken-efficient semantic compression for numerical data. 95%+ token reduction.
semantic-frame@0.2.1 -
Browsegrab
MCP serversToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
browsegrab@0.1.1 -
mcp-sql-rust
MCP serversToken-efficient MCP server for MySQL, PostgreSQL, and SQLite
https://github.com/rzlco666/mcp-sql-rust/releases/download/v0.4.0/mcp-sql-rust-x86_64-unknown-linux-gnu.mcpb -
gcf
MCP serversThe AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.
git clone https://github.com/blackwell-systems/gcf.git -
http
MCP serversMCP server for HTTP requests (curl) with structured, token-efficient output
@paretools/http@0.7.1 -
amenbo
MCP serversJapanese-web-native MCP server for low-impact, token-efficient web collection
amenbo@0.8.0 -
RLM Tools
MCP serversPersistent Python sandbox for token-efficient codebase exploration in MCP clients
rlm-tools@0.1.0 -
memory-mcp-lite
MCP serversA lightweight, structured, token-efficient local-first MCP memory server
memory-mcp-lite@2.0.0 -
make
MCP serversMCP server for Make/Just task runners with structured, token-efficient output
@paretools/make@0.7.1 -
search
MCP serversMCP server for code search (ripgrep + fd) with structured, token-efficient output
@paretools/search@0.7.1 -
tteop-mcp
MCP serversBuild, validate, and describe TTEOP telemetry envelopes for AI operator token efficiency.
tteop-mcp@0.2.1 -
agentsbestfriend
MCP serversMCP that provides fast, token-efficient tools for navigating, searching, and understanding codebases
agentsbestfriend@0.12.0
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.