anygrep searches your notes, PDFs and screenshots by meaning, from the terminal. It runs one model, EmbeddingGemma 2 as int8 ONNX, on the CPU and keeps one local index. Results come back as up to ten files, closest in meaning first, not every match; a file whose text or name contains a query of three or more characters as typed — an invoice number, an error code — is promoted and marked exact, while weak matches are hidden by default and near-duplicates are shown once. Queries and documents can be in different languages, and you can search for pictures similar to an image.
Be the first to rate anygrep. Your feedback helps other users decide.
Run anygrep with a question and a path; new files are indexed first, then results come back by meaning.
Pass an image with --image to find visually similar pictures in a folder.
Use index --background for a large folder so the work runs at low priority.
Similar tools in the same category — compare side-by-side
Rezoom is one chat list for every AI coding session on your machine. It reads the session registry C...
Skillkeel Starter is a free, MIT set of guard hooks and repo skills for Claude Code. guard-bash bloc...
Flopper compares pricing and specs for the GPUs that power AI and HPC. It tracks GPUs, systems, desk...
Guides and comparisons about code tools
Ten launches that keep the model, the index and the facts on your own machine, from search that admits no match to GPU training in CUDA.
Eight Show HN projects for trusting long agent runs: work context capture, distilled memory, folder fences, dollar budgets, plan review and tool governance.
Eight Show HN projects that check what an agent actually built: runtime verdicts, agent onboarding audits, semantic review and in-loop evaluation.
Ten Show HN projects for running several agents at once: orchestrators, subagents in isolated worktrees, shared memory trees and browser relays.
Eight Show HN projects that handle the unglamorous layer: consumer-GPU serving, remote tensors, vector-ready storage, semantic layers and agent payments.