EDITORIAL BRIEFING
Jev inside established developer tools
Batch 18 connects 37 reviewed repositories with at least 500 stars to their concrete Jev implementation, including ten additional integrations with at least 1,000 stars, alongside two tools for finding and reviewing document text.
Frameworks and structured evaluation
AgentScope and Composio expose typed decisions; DeepEval and Opik bring evaluation and tracing into the same workflow.
-
AgentScope exposes Jev through its classifier interface, translating binary, choice and score questions into TypeSafe primitives. The adapter converts structured answers back into framework classifier results.
integration · Batch 18 -
Composio includes a TypeSafe provider for selecting tools and binding arguments with explicit choices. Its implementation separates closed argument sets from values that require an open-ended companion model.
integration · Batch 18 -
DeepEval offers Jev-based evaluation metrics and a TypeSafe model configuration. Custom evaluation criteria are converted into structured judgments for individual responses and conversations.
integration · Batch 18 -
Opik instruments synchronous and asynchronous TypeSafe SDK clients. Evaluation states, questions, returned answers and usage can be captured in application traces.
integration · Batch 18
Relevant context and readable sources
Research and memory integrations select passages before answer generation. Needle highlights the original sentence instead of drafting an answer.
-
GPT Researcher can use Jev to score scraped passages for usefulness to a research question. Its compressor selects context from the same chunk pool and output budget used by the alternative retrieval pipeline.
integration · Batch 18 -
MemSearch includes an optional Jev reranker for project-memory passages. Candidate excerpts are scored against the query before the application chooses which memories to return.
integration · Batch 18 -
ThoughtDAG searches local agent sessions and visual conversation canvases. Its optional Jev layer helps select relevant excerpts and topics before the chosen language model develops an answer.
integration · Batch 18 -
Needle uses Jev to rank passages and select the strongest source sentence for a natural-language query. Its Chrome extension highlights those sentences on the original webpage, and a React interface also accepts pasted text.
product · Batch 18
Decisions in interactive workflows
Prepared browser and Photoshop actions use explicit choices, while Ripple connects a document edit to statements that may need review.
-
Surf provides optional semantic commands that ask Jev to choose from allowed browser actions and check progress toward a goal. The controller validates each selected action against the current page.
integration · Batch 18 -
An experimental Photoshop chat router uses Jev to select supported direct editing commands and short recipes. Complex requests, visual checks and ambiguous instructions are routed to the configured language model.
integration · Batch 18 -
The source repository contains an experimental composer that uses Jev to select elements from a prepared UI grammar. A bounded composition loop builds a JSON render specification from those decisions.
integration · Batch 18 -
Ripple detects statements affected by an edit inside a Google Doc. Jev identifies likely inconsistencies, while Gemini drafts suggestions that the writer can review and apply.
product · Batch 18
Ten more integrations with 1,000+ stars
Office search, project routing, semantic tool selection and frozen-row trials connect Jev decisions to established applications.
-
A desktop office suite indexes local document text in SQLite and can use Jev to reorder search results. The optional reranker evaluates candidate files against the search question before showing the ranked list.
integration · Batch 18 -
Agent Squad includes JevClassifier implementations in TypeScript and Python. A typed Choice question selects among configured agents using the request and conversation context.
integration · Batch 18 -
Paca adds per-project Jev decisions for agent selection, task assignment and filling supported empty task fields. Automation conditions can branch on typed answers while keeping human-set values intact.
integration · Batch 18 -
Pi MCP Adapter can rank MCP tools by meaning using a System One evaluator. Project policy specifies which servers may share data for semantic search, alongside the existing word and regex search modes.
integration · Batch 18 -
OpenHarness ships a Jev Sheets harness for trying typed questions on table rows. Its Question Lab compares two formulations on a frozen sample and records answers, provider usage and review notes.
integration · Batch 18
For every addition, see the changelog or subscribe to the Atom / JSON feeds. Individual records keep project destinations and original sources separate.