vivekchand/clawmetryTools
See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.
411
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
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
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
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