KathanModh259/latent-gate

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens on a mixed dev corpus, 90%+ on logs.

This repository also configures its own agents. See what latent-gate tells them →

25Stars on the repository
7Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied

latent-gate

01

KathanModh259/latent-gate

MCP server Claude CodeCodexCursor +2

Local-first vision-language pipeline inspired by VL-JEPA. Compress images, text, conversations, and RAG documents locally via Ollama before sending to any LLM API. Deterministic, fact-preserving token optimizer plus MCP server, FastAPI server and video processing. Runs locally from the latent-gate Python package.

not rated 25 yesterday A Socket: warn tokens not measured