jevcore: TypeSafe Jev typed-judgment library ships for DeepSeek Harness, MCP, and plain Node

Releases·Tool Release

langgraph-jev: developer wraps TypeSafe's Jev API into a typed LangGraph decision node with confidence-scored answers

A developer released langgraph-jev, an open-source package that wraps TypeSafe's Jev API as a LangGraph node and LangChain Runnable. It returns typed answers with confidence scores, eliminating parsing, and supports deterministic routing and confidence thresholds for human review. The tool targets developers building decision points into LangGraph agent graphs.

A developer released langgraph-jev, an open-source package that wraps TypeSafe's Jev API as a LangGraph node and LangChain Runnable. It returns typed answers with confidence scores, eliminating parsing, and supports deterministic routing and confidence thresholds for human review. The tool targets developers building decision points into LangGraph agent graphs.

Simon Willison released llm-typesafe 0.1a0, a plugin for his LLM CLI tool that adds support for TypeSafe AI's new Jev model. The plugin supports three answer types — yes/no 'noul' questions, choice questions, and scoring questions — returning structured JSON output. It gives LLM users CLI access to Jev for classification-style tasks.

Releases·Tool Release

Nokia Applied Research releases AnyJev, turning any LLM into a Jev-style typed-decision model with real probabilities and no training

Nokia Applied Research, with a Tencent Hunyuan collaborator, released AnyJev, an open-source Python package (Apache-2.0, on PyPI) that converts any LLM into a Jev-style decision model producing typed decisions and real probabilities with no training. The release demonstrates that raw logit readout is order-sensitive — Qwen3-8B flips a BANKING77 answer with 1.00 confidence when options are reversed — while AnyJev's L0 mode stays consistent with zero labels.

Nokia Applied Research, with a Tencent Hunyuan collaborator, released AnyJev, an open-source Python package (Apache-2.0, on PyPI) that converts any LLM into a Jev-style decision model producing typed decisions and real probabilities with no training. The release demonstrates that raw logit readout is order-sensitive — Qwen3-8B flips a BANKING77 answer with 1.00 confidence when options are reversed — while AnyJev's L0 mode stays consistent with zero labels.

Products·launched

Jevless: Jev-style typed decisions (Choice/Noul/Score) from any logprobs-exposing model API

Jevless is an open-source tool that produces Jev-style typed decisions — Choice, Noul, and Score outputs — using any LLM whose API exposes logprobs, rather than requiring a single supported backend. It also ships a local /v1/systemone-compatible server. The author built it to keep Jev's low cost, speed, and bias-canceling accuracy while working across as many model backends as possible.

Jevless is an open-source tool that produces Jev-style typed decisions — Choice, Noul, and Score outputs — using any LLM whose API exposes logprobs, rather than requiring a single supported backend. It also ships a local /v1/systemone-compatible server. The author built it to keep Jev's low cost, speed, and bias-canceling accuracy while working across as many model backends as possible.

Releases·Tool Release

dsh-handbook: DeepSeek Harness 从 0 到 1 深度手册发布

GitHub 用户 Electricitysheep 发布了 dsh-handbook，一份关于 DeepSeek Harness (dsh) 的深度手册，涵盖安装、插件开发、性能调优和实测案例。手册提供中英文版本，并包含同模型多 Agent 实测对比。

GitHub 用户 Electricitysheep 发布了 dsh-handbook，一份关于 DeepSeek Harness (dsh) 的深度手册，涵盖安装、插件开发、性能调优和实测案例。手册提供中英文版本，并包含同模型多 Agent 实测对比。