neruok
@neruok · Oct 7
A Pi extension that builds a neutral context and lets Jev or Clef return a probability distribution over choices, to advise the agent rather than command it.

Cloudflare, Inc.· Released Oct 1
Clef (27B) and Clef-flash (9B) are Cloudflare-trained open-weight (Apache 2.0) multimodal decision models: given a state and typed questions they return bounded structured answers with probabilities in one forward pass, Jev/System One API compatible, hosted on Workers AI with a 64k context. Launched alongside a new RL fine-tuning platform.
neruok
@neruok · Oct 7
A Pi extension that builds a neutral context and lets Jev or Clef return a probability distribution over choices, to advise the agent rather than command it.

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.

odiak
@odiak · Oct 6
A collection of Japanese demos built on Cloudflare Workers AI's Clef and Clef-flash decision models.

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.

kkarimi
@kkarimi · Oct 6
Reproducible fine-tune study with paired evaluation and tutorials, using a playable Tetris-like game as the task.

upendrasingh1
@upendrasingh1 · Oct 6
Fine-tunes Clef decision models on a 12 GB GPU for real-time entity resolution with TRL comparisons.

Yz613
@Yz613 · Oct 6
Service that uses Clef on Workers AI to flag possible checkout losses from store footage.

zalomea
@zalomea · Oct 6
Dockerised research prototype that explores language-model support for emergency triage using synthetic narratives and a local GGUF model.

giapnguyen74
@giapnguyen74 · Oct 6
NVFP4 quantised Clef Flash tuned for the DGX Spark box, tied to the community Balatro-playing demo setup.

mthomas100
@mthomas100 · Oct 6
Runs Clef 27B and Flash 9B through llama.cpp and MLX, with benchmarks including render QA for 3D models and prompt-injection robustness.
zachsents
@zachsents · Oct 6
CLI, MCP server and Chrome extension bridge that lets Clef operate your own signed-in browser session.

armbues
@armbues · Oct 5
Runs decision models, including Cloudflare's clef-flash, locally with MLX, with a table of speed and memory for each supported model.
DanielMcSheehy
@DanielMcSheehy · Oct 5
A SmolVLM2-500M based decision model with a Jev/CLEF-compatible API, plus data pipelines, synthetic generators, LoRA training and an eval harness.

greenlitlabs
@greenlitlabs · Oct 5
Code for a Portuguese article comparing Clef against two generative LLMs on 24 hand-labelled support tickets, using the probability as a certainty threshold for automation.

Kevthetech143
@Kevthetech143 · Oct 5
An MCP tool where your agent asks in plain words and a local Clef-flash judge on Apple silicon finds the file, checks the claim and remembers what you approved.
