- 1501pen-findFind any frame in a Pen (pen.dev) design file by describing it. Jev ranks every node by meaning; your AI agent only reads the top matches. CLI + Claude Code plugin.
adelghaenian/pen-find · JavaScript
10ai-agentsclaude-codeclaude-code-pluginclidesigndesign-toolsmcp - 1502permit-mcpStop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits.
qinpei-dev/permit-mcp · Python
10ai-agent-securityai-agent-skillsai-agent-toolsai-agentsmcpmcp-servermodelcontextprotocol - 1503pi-jeva Jev classification layer for the Pi coding agent
riposta/pi-jev · TypeScript
11typescript - 1504pi-jev-anti-sloppi-jev-anti-slop: TypeSafe Jev ecosystem repository.
BubbatheVTOG/pi-jev-anti-slop · TypeScript
10typescript - 1505pi-Jev-browserBrowser and macOS desktop agent for pi: Jev (TypeSafe System One) chooses each action from a structured observation in a bounded, surface-agnostic loop. Isolated Playwright tools, an allow-listed accessibility-tree tool, deterministic selectors, four-tier benchmarks.
laihenyi/pi-Jev-browser · TypeScript
13accessibilityai-agentsbenchmarkbrowser-automationmacospi-extensionplaywright - Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully.
Wang-auspicious/pi-jev-compaction · TypeScript
10ai-agentscontext-compactionpipi-packagetypescript - 1507pi-jev-controlSystem-One control plane for Pi Coding Agent powered by TypeSafe Jev.
goodruizhan/pi-jev-control · TypeScript
10typescript - 1508pi-jev-eyeUltra-lean supervisor for Pi coding agent using local regex filters, verification state tracking, and TypeSafe Jev semantic gate
bismawy/pi-jev-eye · TypeScript
10ai-agentsguardrailspi-packagetypescript - 1509pi-jev-helmTypeSafe / Jev community project: Z761293629/pi-jev-helm.
Z761293629/pi-jev-helm · TypeScript
10 - 1510pi-jev-scorepi-jev-score: TypeSafe Jev ecosystem repository.
marszhongx/pi-jev-score · TypeScript
10typescript - 1511pi-jev-wikiAgent managed wiki for a project's conceptual space, utilizing Jev to ensure legitmate, relevant, and robust information at scale.
xAndreiLi/pi-jev-wiki · TypeScript
11typescript - 1512pi-laya-bridgeLocal typed decisions for Pi: the TypeSafe Jev /v1/systemone wire protocol as a Pi tool, backed by Laya for Agents on your own machine. Choice, Score and Noul judgments in ~0.5s, offline, no API key.
DrGekoz/pi-laya-bridge · TypeScript
10decisionslayalocal-firstofflinepipi-coding-agentpi-extension - 1513plotveilA quiet spoiler blocker for YouTube comments. One typed Jev (TypeSafe System One) Noul decision per comment; covered while checked, still covered if the check fails.
Dearest/plotveil · TypeScript
10chrome-extensioncloudflare-workersmanifest-v3spoiler-blockertyped-decisions - Autonomous Pokemon Showdown battle agent powered by Jev AI (System One Model by TypeSafe AI), with a validated poke-env harness, safe fallback decisions, and a live dashboard for transparent battle state, legal moves, probabilities, telemetry, and Jev decision history.
NatBrian/pokemon-showdown-jev-agent · JavaScript
10ai-agentsai-observabilityautonomous-agentbattle-aidecision-enginefastapigame-ai - 1515polymarket-jevPolymarket resolution-lag scanner built on TypeSafe's Jev model. Finds markets where a published fact already satisfies the written resolution rules but the price has not caught up. Alert-only.
swang666/polymarket-jev · Python
10python - 1516pr-scoutTriage every open pull request of a GitHub repo in minutes: Jev typed questions, local Ollama descriptions, git test-merge, take / consider / skip board
gentslava/pr-scout · TypeScript
11code-reviewfastapigithubollamapull-requestsself-hosted - Cloudflare Worker to check for profanity using TypeSafe Jev
4rays/profanity-checker · TypeScript
10cloudflare-workershonojev-apiprofanity-filter - Analyze prompts with TypeSafe Jev before GitHub Copilot
shubhangi013/prompt-oscilloscope · TypeScript
10typescript - 1519prose-checkChecks a coding agent's final reply against the project's writing rules with TypeSafe Jev (Claude Code, Codex, Muse Code)
vgeshel/prose-check · TypeScript
10typescript - 1520psearchParallel web search for terminals and agents, with local Chromium and Jev-guided exploration.
komikat/psearch · Python
10python - 1521qc-useTest the most important path in your app. Describe it in plain words. Powered by TypeSafe Jev.
aadilghani1/qc-use · Python
12agent-skillsai-agentsbrowser-automationclaude-codecritical-pathe2e-testinggithub-actions - Proof of concept: auto-tagging and triage of Readwise Reader articles using TypeSafe AI's Jev
osrim/readwise-jev-classifier · TypeScript
10pocpocketbasereadwise-readertypescript - 1523reflexreflex: TypeSafe Jev ecosystem repository.
conuko/reflex · TypeScript
10typescript - 1524resume-jev-matchResume-to-job-description fit classification using TypeSafe AI's Jev model via LangChain
vishalyadav28/resume-jev-match · Python
10python - 1525s1-coreS1-Core — a zero-dependency Python harness for System 1 decision models (Jev & friends): choice/score/noul specs, fail-closed calibration gates, wave-parallel fan-out, replayable audit ledger.
acbcore-labs/s1-core · Python
10auditabilitycalibrationconformal-predictiondecision-modelinferencellm-harnessmachine-learning - 1526s1-rsTyped System One layer for Rust (Choice/Score/Noul).
AbdelStark/s1-rs · Rust
11rustmachine-learningsdk - 1527s1gateNative System One inference gateway for HTTP and MCP.
alekseitylindus/s1gate · Rust
10ai-agentsrust - 1528s1kitTest, calibrate and route System One decision models (Jev, Laya, kev, llama.cpp, Ollama) on your own data.
Eliot5566/s1kit · Python
10calibrationclidecision-modelgithub-actionslayallm-evaluationllm-routing - Enrich fields in Sanity with an instant feedback utilising the decision model Jev from Typesafe. Show a score to the editors realtime on things like readability, tone, trustworthiness, credibility or anything else.
frederikvonsperling/sanity-plugin-jev-fields · TypeScript
10typescript - An abstraction for System One models, currently supporting TypeSafe's Jev and Laya. Typed questions, probabilities, and "don't know" instead of a guess, from Python, the command line, or MCP
jasonduncan/semantic-operators · Python
10climcppython - 1531Should-I-JevFind the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.
yzbcs/Should-I-Jev · Python
10cost-optimizationdeveloper-toolsllmpython - 1532siegeSIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.
vnmoorthy/siege · TypeScript
10typescriptagent-loopsai-agentscoreweave - 1533sieveSift a whole folder of notes by any judgment powered by Jev at OpenRouter
nothans/sieve · JavaScript
10siftjavascript - 1534siteclarityEvidence-backed AI answer-readiness auditing for web pages. Tells you what to fix, with a verbatim quote for every finding — never a score. Built on TypeSafe's Jev System One decision model, so no generative AI is used and no evidence can be invented. MIT.
sanjuacodez/siteclarity · TypeScript
10typescript - 1535skill-dashSkill Dash uses Jev to judge Claude Code and Codex skills and plugins: usefulness, redundancy, clarity, duplicates, safety. Local dashboard plus the corpus pipeline behind whichskills.dev. MIT.
48Nauts-Operator/skill-dash · Python
10agent-skillsai-safetyclaude-codeclaude-skillscodexdashboardprovenance - smart-router-chatbot: TypeSafe Jev ecosystem repository.
SairajGavhane/smart-router-chatbot · Python
10python - 1537smcraftsmcraft: TypeSafe Jev ecosystem repository.
jgwill/smcraft · TypeScript
10typescript - Read AI coding agent outputs in seconds. Jev, TypeSafe's decision model, highlights what needs your decision or action and dims the rest. Tauri + CodeMirror app for macOS.
TomySpagnoletti/speed-reading-app · TypeScript
11ai-agentsclaude-codecodemirrorcoding-agentsmacosopenrouterproductivity - 1539stepwardenEvery tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept
getexcited/stepwarden · TypeScript
10ai-agents
1501–1550 of 3054