Scheme0/local-agent-senses

Local multimodal vision & speech for text-only LLM agents (Codex, Claude Code, Cursor, Cline, Gemini CLI, and similar). OCR, image/video understanding, and audio transcription run entirely on your machine via Ollama + FunASR, with a CLI and MCP server.

1Stars on the repository
2Mods indexed here, across every type
20d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

vision

01

Scheme0/local-agent-senses

Skill Claude CodeCodex

Locally-runnable multimodal vision & speech for text-only LLM agents (Codex, Claude Code, Cursor, Cline, Gemini CLI, etc.). Use when the user asks to read, analyze, transcribe, or summarize images, screenshots, PDFs, charts, UI captures, videos, subtitles, audio, or media URLs — or when image input fails with "does…

not rated 1 20d ago C 179 tokens original MIT