ooples/
token-optimizer-mcp
ooples/token-optimizer-mcpConnectors
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
516
OptimiLabs/
velocity
OptimiLabs/velocityHarnesses
Local-first workspace for Claude Code, Codex CLI, and Gemini CLI with sessions, analytics, workflows, and tools
44
addyosmani/
web-quality-skills
Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
2.8k
affaan-m/
ECC
affaan-m/ECCHarnesses
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
258k
VinvAI/VinvAITools
Tools for AI agents to test, fix and optimise your codebase
46
Dave-London/
Pare
Dave-London/PareConnectors
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
138
gokeshenzhen/
awesome-formal-verification-skill
Open-source, agent-agnostic RTL formal verification skill library for AI coding agents: JasperGold FPV, SVA, proof optimization, and TCL workflows for Claude Code, Codex, Gemini CLI, and Cursor.
33
juyterman1000/
entroly
juyterman1000/entrolyConnectors
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
443
yvgude/
lean-ctx
yvgude/lean-ctxConnectors
LeanCTX — Context Intelligence for AI systems.
3.8k
rtk-ai/rtkHooks
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
80k
AgusRdz/
chop
AgusRdz/chopTools
CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the context window. Supports 52+ commands — git, docker, kubectl, npm, terraform, and more.
44
callstack/
agent-device
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
4.5k
fajarhide/
omni
fajarhide/omniTools
Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.
369
jgravelle/jcodemunch-mcpConnectors
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
2.7k
claudioemmanuel/
squeez
Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.
200