The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
-
Updated
Oct 19, 2026 - Python
#
rlcd
Here are 55 public repositories matching this topic...
🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.
awesome calibration typesafe awesome-list zero-shot-classification llm llm-evaluation structured-outputs decision-models rlcd calibrated-probabilities jev typesafe-ai system-one system-one-models typed-decisions jev-ai awesome-jev
-
Updated
Oct 22, 2026 - Python
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
machine-learning deep-learning text-classification encoder calibration uncertainty-quantification webgpu decision-engine onnx non-autoregressive selective-prediction agentic-ai structured-outputs modernbert brier-score rlcd jev typesafe-ai system-one openjev
-
Updated
Oct 21, 2026 - Python
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
calibration webgpu decision-engine onnx edge-ai structured-outputs modernbert gliclass brier-score system-1 rlcd jev typesafe-ai zero-token-generation
-
Updated
Oct 21, 2026 - Python
Dohnuts builds small multimodal models for direct decisions. -> System One model
-
Updated
Oct 6, 2026 - Python
Claude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One model. All materials pull directly from their canonical cookbooks and documentation.
skills typesafe codex claude typesafe-api evals claude-code decision-models evaluation-harness claude-skills claude-plugin codex-skill skill-md rlcd jev typesafe-jev jev-ai jev-api jev-model jevelopers
-
Updated
Oct 19, 2026 - HTML
⚡ Foq — the FREE, local, open-source alternative to Jev. Typed System 1 decisions in ~25 ms — no waitlist, no cloud, no per-token cost. foq.fr
ai offline inference self-hosted decision-engine local-first system1 llm foq llama-cpp local-ai gguf agentic-ai system-1 rlcd jev system-one-model jev-alternative
-
Updated
Oct 18, 2026 - Python
NIRNAY 450M: open-weight calibrated decision model (Apache-2.0). Banking77 intent classification 87.9%, fitted ECE 0.045. Laya fork plus concept bottleneck, coarse-to-fine pointer and RLCD. Built by Eulogik.
machine-learning text-classification transformers pytorch calibration lora decision-model triage vector-quantization intent-classification on-device guardrails edge-ai banking77 concept-bottleneck small-language-model apache-2-0 rlcd system-one eulogik
-
Updated
Oct 6, 2026 - Python
A MicroPython Driver for the Waveshare ESP32-S3 4.2inch RLCD display
-
Updated
Mar 22, 2026 - Python
Fine-tune Laya, the open System One decision model, for any typed-decision task: synthetic data, RLCD, calibration and long context.
-
Updated
Oct 2, 2026 - Python
A simple desk clock built around the Waveshare ESP32-S3-RLCD-4.2 — a 4.2" reflective LCD (e-paper-like) development board.
-
Updated
Oct 3, 2026 - C
A TypeSafe-native (Jev) coding agent built on Recursive LLM Context Decomposition (RLCD), with a native macOS client
-
Updated
Sep 22, 2026 - Python
Local Hybrid System-One Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Cascade, OpenJev-RLCD² Trainer, Zero-Shot AI Safety Guardrails)
python routing calibration low-latency agents ai-safety decision-engine onnx conformal-prediction fastapi guardrails zero-shot-classification llm local-ai agentic-ai mcp-server system-1 rlcd jev system-one
-
Updated
Oct 22, 2026 - Python
Multilingual, non-autoregressive System 1 decision model.
multilingual calibration chinese-nlp decision-model bert fine-tuning laya guardrails non-autoregressive system-1 rlcd jev
-
Updated
Sep 24, 2026 - Python
ESP32-S3 RLCD desktop display for Codex quota, room sensor data, battery status, and a mood pet synced over BLE.
-
Updated
Jul 15, 2026 - Python
Add this topic to your repo
To associate your repository with the rlcd topic, visit your repo's landing page and select "manage topics."