Projects tagged with “llm”
Browse Jev GitHub projects tagged with llm. Filter, sort and explore their source repositories.
- 393levJev-style decision model based on LFM2.5-350M
franckverrot/lev · Python
130classifierllmmlpython - 413jev4kA Kotlin DSL and client for TypeSafe's Jev model
pambrose/jev4k · Kotlin
122dsljavajev-apikotlinktorktor-clientllm - 442hunchAsk Jev over columns of data: closed-set questions, cached and joined back.
steven-shoemaker/hunch · Python
101classificationllmpython - Real-world Jev use cases, open-source projects, benchmarks and criticism — what people actually build with TypeSafe AI's Jev, and where it fails. Machine-readable, updated daily.
Jessie-QingYu/jev-in-the-wild · JavaScript
104ai-agentsawesome-listbenchmarkclassificationllmtyped-decisions - Adaptive reasoning effort for OpenCode via Jev, with an in-process plugin and Responses API proxy
robertn702/opencode-jev-router · TypeScript
100code-agentllmopenaiopencoderesponses-apitypescript - 455OpenJevSwiftNative Swift implementation of OpenJev, the Jev-compatible typed-decision server: yes/no, choice and score answers read from model probabilities, on Apple silicon Macs and in iPhone apps. Serves Verdict, Laya, DiffusionGemma and JevK5. Apache-2.0.
Algorythm-Canada/OpenJevSwift · Swift
102apple-siliconcoremldecision-modeldiffusiongemmaioslayallm - 459typed-lmSingle-forward-pass semantic routing in Rust: turn dense LLMs (Llama, Qwen, Mistral, Gemma) into a typed decision API with LoRA/QLoRA training and FP8/FP4 quantization, built on Candle.
neurono-ml/typed-lm · Rust
100actix-webcandleclassificationhuggingfaceinferencellmlora - Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision
TholeG/typesafe-chess · JavaScript
103javascriptchessllm - DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.
justhalfbit/dsh-plugin-jev-effort-selector · JavaScript
91ai-agentsdeepseek-harnessdeepseek-harness-plugindshdsh-pluginllmplugin - 485prompt2jevAgent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script
sumleo/prompt2jev · Python
92agent-skillsclaude-codedecision-makingllmpython - 499jev-aiJev AI quickstart & FAQ — TypeSafe AI's System One model. Try it free: jevtypesafeai.com
codaaiteam/jev-ai
82apillm - Find, design, and evaluate TypeSafe Jev decision loops.
karanb192/jev-architect · HTML
86agent-skillsai-agentsclaude-codellmopenai-codex - 502jev-docsCommunity-maintained history of Jev / TypeSafe System One APIs, SDKs, agent guidance, and engineering best practices.
chenrui333/jev-docs · Python
80agentic-aiai-agentsai-engineeringdeveloper-toolsdocumentationllmsdk - 513jevgoUnofficial Go client for the TypeSafe AI System One API (Jev) — typed questions in, calibrated answers out.
devbackend/jevgo · Go
80api-clientclassificationgollmsdk - 518openjevTurn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.
lookski/openjev · Python
83classificationdecision-modelhugging-facellmllm-inferencelocal-llmsoftmax - 520pytest-jevSemantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.
allebee/pytest-jev · Python
81llmllm-evaluationpytestpytest-pluginpythontesting - 534gutJudgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.
Kungie/gut · Python
70llmpythonsmall-language-modelszero-shot-classification - 547jevbriefClean, traceable state briefings for TypeSafe's Jev model
Parthkomalwad/jevbrief · Python
70ai-agentsllmplaywrightpython - 571decidekitA System One model in the browser: typed, calibrated text decisions on the user's device. Learns from an LLM when it isn't sure.
debuffjp/decidekit · TypeScript
60classificationdecision-modelllmtypescript - Native DuckDB extension composing fast System One judgments with selective System Two reasoning, provenance, batching, and caching.
prasanthj/duckdb-dual-cognition · C++
60c++data-enrichmentduckdbllmsql - 591jevmeTalk to your Mac and it does it — in any app, while you're still talking. Open-source voice agent that gets faster the more you use it.
danielyedaniel/jevme · Python
61accessibilityai-agentsanthropicautomationclaudecomputer-usellm - Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.
clouatre-labs/decisions-judge-mcp · JavaScript
51ai-agentsclidecision-makingdecisionsjudgellm - A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.
Waxmell114514/jev-compaction · Python
51agent-memoryai-agentscontext-compactioncontext-managementllmprompt-cachingpython - Fifty real-world financial use cases for TypeSafe's Jev model: typed, structured LLM answers over ledgers, fraud, portfolios, trades and filings, each graded against data where the right answer is known.
IslamBaraka90/jev-typesafe-real-financial-use-cases · JavaScript
51ai-agentsbacktestingfinancial-datafintechjavascriptllmllm-evaluation - 647jevtokExact token counting and request-cost prediction for TypeSafe's Jev (tiktoken-style)
LabGuy94/jevtok · Python
51llmtiktokentokenizerpython - Swift SDK for TypeSafe AI
InsaneArts/typesafe-sdk-swift · Swift
50swiftllmsdkswift-package - 665ask-jev-aiA public wall where anyone asks a question in three to fifteen words and Jev, TypeSafe's judgment model, answers yes, no, or it depends in about 100 milliseconds. Every judged ask lands on the wall in realtime, with a running count toward one million, showing cost.
waynesutton/ask-jev-ai · JavaScript
42llmjavascript - A curated list of decision models (System One / typed-decision models): Jev, Laya, Kev, SemIf and the tools, runtimes and research around them.
sfmqrb/awesome-decision-models
43ai-agentsawesomeawesome-listdecision-modelkevlayallm - A curated hub of the Jev / TypeSafe "System One" model ecosystem — concepts, 51 verified projects (12 categories), 10 community lists, official repo screenshots.
supermanc417-alt/awesome-jev-hub · HTML
41ai-agentsawesome-listllmhtml - 673compactioSystem 1 for your coding agent: cut token use by deciding, not generating.
RamaAditya49/compactio · TypeScript
40claude-codeclaude-code-plugincoding-agentscontext-engineeringllmsystem-1tokens - Unofficial async Rust SDK for the TypeSafe AI System One API: typed questions via #[derive(QuestionSet)], a port of typesafe-sdk-python.
zchee/decision-model-sdk-rust · Rust
40api-clientasyncllmrustsdktokio - Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.
kolawong/fast-compaction-dsh · TypeScript
40compactioncontext-managementcordisdeepseek-harnessdsh-pluginllmtypescript - 699jev-localJEV-Local: System-1 decision engine for local LLMs. Mimics TypefAI JEV: structured choices only, no chatter, calibrated confidence. Works with Ollama, vLLM, llama.cpp, LM Studio.
tapsin/jev-local · Python
40ai-agentsbrowser-automationdecision-enginellama-cppllmlm-studiolocal-llm - 704jev-rerankerRerank, filter, and compress JSON search results with TypeSafe AI's Jev.
shinpr/jev-reranker · Rust
41clicontext-compressiondeveloper-toolsinformation-retrievalllmragreranker - Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.
himomohi/jev-skill-router · Python
41agent-skillsclaude-codecodexcontext-engineeringllmmcppython - 711jev-starterTyped, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
hamakyo/jev-starter · TypeScript
41confidence-routingdecision-enginedecision-workflowsfallbackhuman-in-the-loopllm - Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.
CrowdLinker/JevPromptCoach · TypeScript
42ai-coding-assistantclaude-codeclaude-code-plugincode-qualitydeveloper-toolsllmprompt-engineering - 719jevqaJev-guided monkey tester: $0.35 and 5 minutes to find missing features, validation gaps and dead controls before QA
Todmy/jevqa · Python
40github-actionsllmplaywrightqatestingpython - 720jevseekDeepSeek proposes the next token, TypeSafe's Jev chooses it: a decision model used as a sampler
blingdivinity/jevseek · Python
40deepseekllmsamplingpython
51–100 of 261