Jev.aitools.fyi

Command Palette

Search for a command to run...

Search the index

Explore Jev listings

Filter by category, MCP, demos, GitHub, and more. Same public ecosystem the community ships to, sorted the way builders actually browse.

600 matches of 600 listings

Clear filters
IntegrationsTypeScript5,253
DemoFeatured
Vercel's agent framework with Jev wired into the experimental evaluate path, so scoring stays typed.
integrationsagentseval
Browser and computer usePython4,799
DemoFeatured
Jev picks the browser op and DOM target in one shot; a tiny LLM only shows up when something needs typing.

by @gregpr07

browser computer usebrowser-useagents
BenchmarksPython3,844
DemoFeatured
Semantic ifs on a home 3090: open models doing structured branches without pretending to be TypeSafe.
benchmarksopen-sourceself-hosted
Agent toolingTypeScript2,735
Featured
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dro
agent toolingcompactionagents
Browser and computer useRust1,413
Featured
agent-desktop (github.
browser-computer-usedesktopaccessibility
BenchmarksPython851
Featured
Train a small model that chooses among a changing list of text options, one probability per option in a single pass.

by @hhkkmon

benchmarksgame
IntegrationsTypeScript796
DemoFeatured
Vercel Labs terminal CLI that can point evaluate at Jev instead of another vibes-based judge.
integrationseval
ApplicationsTypeScript794
DemoFeatured
One AI trade call every Monad block on Kuru MON-USDC, with Jev picking the move instead of a market essay.

by @jarrodwatts

applicationstrading
Agent toolingPython381
Featured
hermes-jev-skills (github.
agent-toolinghermesmcp
Official205
OfficialDemoFeatured
Official Claude Code / Codex skill pack for Jev primitives, patterns, and evaluation shape.
officialagentseval
OfficialTypeScript114
OfficialFeatured
The official TypeScript SDK: inferred answer types, System One primitives, and fewer any-shaped regrets.
officialsdk
Official
OfficialDemoFeatured
Every field in POST /v1/systemone, spelled out for engineers who ship gates, not grad students writing RFC fanfic.
official
Integrations
DemoFeatured
Hosted typesafe-ai/jev for AI SDK evaluate calls, no TypeSafe waitlist required.

by @typesafeai

integrationssdkeval
ApplicationsTypeScript
FeaturedDemoMCP
classifier.
applicationsclassificationmoderation
Applications
DemoFeatured
Ploy is a marketing site product that personalizes funnel pages without running a full A/B test program for every headline tweak.

by @bryantchou

applicationsmarketingpersonalization
IntegrationsTypeScript
DemoFeatured
TanStack AI is the TanStack team's AI SDK surface.
integrationssdktypescript
Applications
DemoFeatured
Dub (dub.

by @steventey

applicationssecuritylinks
Applications
DemoFeatured
PixelML (pixelml.

by @seanphan

applicationsvideorag
Applications
DemoFeatured
Hypit (hypit.

by @hypitai

applicationsmarketingugc
ApplicationsPython
DemoFeatured
DocJev (github.
applicationsdocumentsclassification
Games and sims
DemoFeatured
Browserbase builder Shubhankar Srivastava rebuilt a FIFA-style match as a love letter to real-time System One loops.

by @_shubhankar

gamessportsrealtime
Applications
DemoFeatured
Jev as a Judge (judge.

by @kylejeong

applicationslegalproduct
Games and sims
DemoFeatured
Jev Arcade at jevarcade.

by @thisiskp_

gamesintegrationsproduct
Applications
DemoFeatured
Virlo (virlo.

by @dsqjaffa

applicationsmarketingsocial
ApplicationsPython12,268
Open-source AI Trading OS: research, backtest, paper/live execution, Agent Gateway + MCP; optional TypeSafe Jev pre-trade filter on entries.
applicationstradingquant
IntegrationsPython6,740
Demo
Jared Palmer's open Jev-like Qwen decision models: System One-compatible serve, HF weights 0.8B to 27B, eval tables vs hosted Jev.
integrationsopen-sourceself-hosted
ApplicationsKotlin5,214
Demo
Android chat co-pilot overlay: Jev judges intent and danger on screen text, ranks three reply drafts, fill-only never auto-send.
applicationsmobilechat
BenchmarksPython2,108
Demo
NanoJev (github.
benchmarksopen-sourcegames
BenchmarksPython1,678
Demo
Nimble (github.
benchmarksopen-sourceself-hosted
IntegrationsPython1,633
Demo
Open multilingual non-autoregressive System 1 engine: a script-aware Router picks English, multilingual, or typed-decisions checkpoints, then one forward pass returns Choice, Score, and Noul.
integrationsopen-sourcedecision-model
IntegrationsPython1,527
Demo
Apple Silicon Core ML and Neural Engine runtime for open-weight Laya: short typed decisions, PyPI laya-coreml, Hugging Face bundles, Snake demo.
integrationsapple-siliconcoreml
Agent toolingTypeScript1,148
npm @dzhng/jevgrep (`jg`): coding-agent CLI for hierarchical semantic repo search with Jev relevance, verbatim excerpts, and `jg skill` installer.
agent-toolingclicode-search
Browser and computer usePython828
Demo
Computer use for about $0.

by @awlevin

browser-computer-usebrowser-usemacos
Agent toolingTypeScript771
GitHub Next Bun server: local POST /v1/systemone over oMLX DiffusionGemma chat JSON, TypeSafe SDK compatible, README honest on calibration.
agent-toolingself-hostedsystem-one
Agent toolingTypeScript753
Demo
Hippo Memory (hippo-memory.
agent-toolingmemoryrag
IntegrationsPython702
Demo
Mapika open System One family on Qwen3.5: one forward pass, Choice/Score/Noul, POST /v1/systemone via decider-ai on PyPI, weights on Hugging Face.
integrationsopen-sourcedecision-model
Agent toolingRust688
Rust coding agent harness: Jev routes reasoning consults, effort, and utility summaries; fail-open; Distill owns tool permissions.
agent-toolingroutingrust
Agent toolingTypeScript670
LLM plus Jev alloy: JevSift, JevLoop, and JevLong over a CLI JSON protocol so the host agent keeps the session.
agent-toolingharnesscli
Browser and computer useSwift663
macOS menu-bar companion: default JEV mode picks local controls for clicks; Gemini mode for voice and writing. Keys in Keychain.
browser-computer-usemacoscomputer-use
IntegrationsPython635
Apache-2.0 non-autoregressive System One model: one forward pass, order-invariant option scores, sub-25 ms local claims.
integrationsopen-sourcedecision-model
Agent toolingPython606
SGLang JSON Schema generation on existing AR LLMs: enums, numbers, depends_on graphs, JevBench 228/231 with thinking. Not a System One server.
agent-toolingsglangjson-schema
Agent toolingPython601
Nokia research: Decider API turns hub LLMs into calibrated Jev-style choices with L0 flip fixes and optional L2 heads on vLLM.
agent-toolingopen-sourcedecision-model
Browser and computer useJavaScript587
Codex Computer Use skill: Jev picks element, action, completion, and risk from AX text only; dry-run and confirm on sensitive ops.
browser-computer-usecodexcomputer-use
Browser and computer useJavaScript545
Codex skill: Jev clicks and scrolls on accessibility text; Codex types, interprets visuals, and verifies. Author claims about 5 to 10x faster browser ops at EZCollegeApp.
browser-computer-usecodexskill
ApplicationsPython530
Demo
Windows chat overlay: offline OCR, Jev judge on intent and tension, three ranked drafts, fill-only never auto-send.
applicationswindowschat
ApplicationsTypeScript510
Demo
One morphing text box becomes events, checklists, timers, and converters: parallel Jev intent fan-out plus deterministic value parsing, offline keyword fallback.
applicationsuiintent
Agent toolingPython506
Demo
Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.
agent-toolingagentssupervisor
IntegrationsTypeScript500
Node 20+ ONNX Runtime client for Convai Laya: typed systemOne, HF cache about 1.7 GB fp32, parity claims vs Python RLAgent.
integrationsnodejstypescript
By Rishit