im-looking-for
llms.txt9 starsChanged 33 days agoMITView on GitHub
Local, cross-platform search of a computer's files by their content (photos, PDFs and scans, documents, audio, video) using EmbeddingGemma 2 via llama.cpp. Command ilf; MCP server ilf mcp; --json on every command. Nothing leaves the computer.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- im-looking-forSkill
The file
Files
# im-looking-for > Local, cross-platform search of a computer's files by their content (photos, PDFs and scans, documents, audio, > video) using EmbeddingGemma 2 via llama.cpp. Command `ilf`; MCP server `ilf mcp`; `--json` on every command. > Nothing leaves the computer. ## For agents using it - [Agent guide](docs/agents.md): connecting over MCP, tools, JSON shapes, exit codes, how to read scores - [Agent skill](skills/im-looking-for/SKILL.md): step-by-step use of the `ilf` CLI - [README](README.md): install, the app, what files are read, limits ## For agents changing it - [AGENTS.md](AGENTS.md): code layout, invariants, how to test ## Optional - [한국어 README](README.ko.md) - [한국어 에이전트 가이드](docs/agents.ko.md) - [Third-party notices](THIRD_PARTY_NOTICES.md)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.