lucataco
@lucataco · Oct 1
Runs Cloudflare's clef-flash decision model on your webcam stream locally, answering typed questions about each frame. The most-starred community build of the week.

Cloudflare, Inc.· Released Oct 1
Open-source code, templates and lists.
lucataco
@lucataco · Oct 1
Runs Cloudflare's clef-flash decision model on your webcam stream locally, answering typed questions about each frame. The most-starred community build of the week.

ygwyg
@ygwyg · Oct 1
When a URL 404s, Clef reads the request and picks the most likely real destination, turning dead links into redirects. A neat small use of a decision model in the request path.

HighlyLoadedEgo
@HighlyLoadedEgo · Oct 3
Local MCP server that gives AI agents structured decisions with probabilities from Clef-Flash through llama.cpp, with no network needed.

Arcobalneo
@Arcobalneo · Oct 2
A vLLM-based Jev-compatible server for Clef-Flash claiming 45 ms p50 and double throughput while matching the reference outputs.

zknpr
@zknpr · Oct 3
A from-scratch C and Metal engine that runs Clef and Clef-Flash on Apple Silicon with a Jev-compatible API, for fast local decisions on a Mac.

dfinke
@dfinke · Oct 1
PowerShell module that calls Clef on Workers AI for typed, probability-scored decisions straight from scripts and pipelines.

RadRebelSam
@RadRebelSam · Oct 7
Crawls GitHub and npm and lets Clef or Jev judge each candidate against one sentence you write, then publishes the list.

jillesme
@jillesme · Oct 6
Pictionary game where Clef on Workers AI looks at your sketch and guesses what it is in real time.

mazar
@mazar · Oct 5
Swaps Claude Code's safety classifier for a local Clef model that judges whether actions are safe to auto-approve.

AbelNavarro
@AbelNavarro · Oct 4
A Claude Code mod that asks Clef which model and reasoning effort each turn needs, saving cost on trivial prompts.

Gjusev
@Gjusev · Oct 1
Uses Clef to decide whether a prompt needs a frontier model or a cheap one, behind an OpenAI-compatible proxy and library to cut spend.

Gjusev
@Gjusev · Oct 1
Has Clef score retrieved chunks against the question and keeps only the evidence, shrinking noisy RAG context before it reaches the LLM.

Gjusev
@Gjusev · Oct 1
Toolkit for judging outputs cheaply with Clef and auditing whether its confidence numbers are calibrated, with a rendered demo clip.
sakamoto-sann
@sakamoto-sann · Oct 7
Japanese-documented Codex skill that offloads public screen state checks to Clef-flash.

aaddrick
@aaddrick · Oct 7
Unofficial agent skill covering typed decisions, calibration and provider differences across Jev, Clef and others.

Thingscorp
@Thingscorp · Oct 7
An agent does the legwork while Clef makes each judgment call from discovery to regression.

dcowsill
@dcowsill · Oct 7
Adds an auto-approve mode to pi where System One decision models judge whether each action is safe.

nicolasmertens
@nicolasmertens · Oct 7
Shows exact context size per turn and a Clef judgment of whether now is a good moment to compact.

canonical
@canonical · Oct 7
Snap package for running Clef Flash inference locally on Ubuntu, a sign of fast distribution-level pickup.

u9401066
@u9401066 · Oct 6
Clef-Flash reviews each reasoning step of a llama-server model and triggers rollback or reflection.

Sj0605-DataSci
@Sj0605-DataSci · Oct 6
Common-ground comparison of Jev, Clef, Kev and others against embeddings, rerankers, NLI and prompted LLMs.

dchristopoulos
@dchristopoulos · Oct 6
Benchmarks Jev, Clef-flash and Laya against an LLM and six rerankers on BEIR with paired confidence intervals.
