Entries 49 to 96 of 430, in the hub's default order. The introduction is on page 1.
Showing 49 to 96 of 430
A 151M-parameter non-autoregressive decision model, inspired by Jev's approach but trained independently, evaluated on the LocalLLaMA typed-decisions benchmark at 77.10% accuracy, 0.0636 Brier score and 0.0144 expected calibration error.
Streams speech word by word from the browser's Web Speech API to a Node server, which asks Jev about a dozen typed questions per partial transcript, such as intent, target element and whether the command is complete, and decides whether to act before the sentence finishes.
271 starsDecision latency ~250-350 msCost per call ~$0.0002
Papers, open reproductions and independent evaluations behind System One models and Jev, rather than a tools directory.
270 starsEntries 142Open reproductions 39
Educational Jev-like visual inference on Apple Silicon: Qwen3.5-0.8B under MLX answers several questions about one image by reusing shared multimodal context and scoring candidates from logits. Ships a browser UI, CLI, HTTP API and sorting-factory, Breakout and camera-gesture demos.
Per-call model routing for Codex: Jev answers four choice questions to pick the model tier and thinking depth, so the cheapest sufficient model serves each call. A 7-day replay of 237 real turns measured about 60% savings against always using Astra, under an older policy.
262 starsHistorical replay ~-60% cost
Browser-use tool driving a real headless browser through an MCP server, CLI or library, with Jev choosing the actions. Returns text, markdown, HTML or accessibility-tree output plus traces and screenshots.
256 starsWikipedia nav ~4s, $0.0016
Self-hosted, versioned skills library for AI agents. Serves skills over MCP with scoped clients, and adds optional Jev recommendations for which skill to reach for.
Official TypeScript/JavaScript client published to npm as @typesafe-ai/sdk (v0.6.0), requiring Node.js 20+ and shipping ESM, CommonJS and type declarations.
Unclutter is a WXT browser extension that removes page clutter using Jev decisions, with reusable template rules per site.
Official Python client for the TypeSafe System One API, published to PyPI as typesafe-sdk with sync (TypeSafeClient) and async (AsyncTypeSafeClient) clients.
Local-first MCP plugin giving Claude Code, Codex, Cursor and OpenCode structured code-quality scores (correctness, complexity, modularity, security) while they work. Sends focused diffs to Jev and keeps keys and code local.
Open System One model that scores states against actions with a contrastive objective, serving CLM-8B behind a TypeSafe-compatible API. The authors report Jev-level results on computer-use, gaming and tool-calling with up to 9x lower latency, plus scaling laws and a fine-tuning guide.
Jacky Kwok (@jackyk02)OpenCLM: Contrastive Language Models on github.com215 starsvs Jev latency up to 9x fasterDeepSWE (tuned) 81.6%
Generative engine optimization platform that tracks brand mentions across ChatGPT, Claude, Gemini and Perplexity. Jev runs its chat router, GEO judge and feedback classifier by default, with LLM fallbacks; the NOTRA_JEV_CLASSIFIERS setting turns it off.
Open source tool that scores every turn a coding agent takes against project rules that can't be codified into a linter, using Jev, then tells the agent what to fix.
Ohans Emmanuel (@OhansEmmanuel)Opencoldteadotai/abide on github.com211 starsRule breaks 1 in 13 turnsPer check ~300 ms
A directory of open-source projects built with TypeSafe Jev. Submissions are reviewed and categorized by the Jev Review Action, a Jev-only GitHub Action.
204 starsListed projects 163
A Claude Code and pi plugin that uses Jev to judge whether a session has reached a safe point to run /compact, in a hint mode or a fully automatic mode.
Kun Chen (@kunchenguid)Openkunchenguid/compact-adviser on github.com183 starsEval set 40 sessionsHint floor (empty) 0.90
Community directory of projects built on Jev, backed by a data/projects.json file; the README listed 990 entries as of 2026-09-23.
hellogumboOpenhellogumbo/awesome-jev on github.com179 starsProjects listed 990
Camera-only autonomous drone simulated in MuJoCo with Jev in the control loop at 2.5 Hz.
RomanSlackOpenjev-drone on github.com164 starsCalls per flight ~110Decision rate ~2.5 Hz
A Swift package for local computer use on Apple Silicon that reads a form through the Accessibility API and asks a small on-device model what belongs in each field. Its Laya integration runs FluidInference's Core ML port of Laya on the Neural Engine at 3.7 ms per decision on an M5 Pro, about seven times faster than the upstream GPU figure.
FluidInferenceOpenFluidUse on github.com152 starsPer decision 3.7msSpeedup ~7x faster
An AI API server that abstracts multiple models and providers behind one layer, for local use with Ollama or LM Studio or in the cloud via OpenRouter, OpenAI, Anthropic or Google. It now supports Jev.
A local, open-weight port of browser-use's jev-ultrafast agent that swaps Jev's hosted decisions for Laya running on Apple Silicon through MLX, while keeping the original hosted Jev policy as a fallback mode.
ipenywisOpenLaya Ultrafast on github.com145 starsDecision latency ~33ms
Extension making Jev the decision layer for the Pi coding agent: a measured tool-call gate plus a jev_ask tool. Judges whether an action is destructive, exfiltrates data or exceeds scope, then blocks or warns on calibrated thresholds.
144 starsGate latency ~300ms
A Claude Code plugin that uses Jev to trim noisy Bash output after a command runs but before the result reaches the main model, once the output passes an estimated token threshold.
Guardrails for the Pi agent built on pi-typesafe. Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified completion claims and flags low-quality output, steering the agent rather than interrupting the user.
DevMortimerOpenpi-warden on github.com138 starsHolds per 1000 calls 3
A grep that matches lines by meaning instead of regular expressions: Jev scores each line against a plain-language description and the tool applies a threshold, combining meanings with AND, OR and NOT.
134 starsBatch speed <1s/210 lines
An open re-creation of Jev built on Qwen3.5-4B that you run on your own GPU. It takes a state and a list of fixed-option questions and answers all of them at once with a probability per option, never free text.
An Agent Skill that guides a coding agent through writing and improving programs that call Jev.
A benchmark that has language models play chess against a random-move player and the Komodo Dragon engine, scoring both chess skill and whether the model keeps making legal moves without hallucinating.
Navigates a Neo4j graph one hop at a time: the outgoing relationships of each node become Choice options and Jev returns a distribution over which to follow, with a Noul question about reaching the goal riding in the same call. Top-k over summed log-probabilities makes it a beam search, drawn in an interactive graph.
An open-source decision engine inspired by Jev: give it state and typed questions and it scores each option independently, then normalizes the scores into a probability distribution, using any OpenAI-compatible provider key instead of TypeSafe's API.
Rust CLI that hands an agent's live session context to Jev, which compares the available skills and estimates which fit the next step. Ships Claude Code hooks, structured JSON, abstention, a terminal display and local feedback.
Command-line toolkit a coding agent can delegate judgment work to: ranking relevant files, checking a diff against its task and project rules, and triaging test failures or review comments. Each request runs one bounded typed workflow and returns a structured report.
Scores source-file quality by asking Jev a set of yes/no questions, runs the test command you already use, and turns uncovered paths into small queries a coding agent can work through. Scoring costs about a cent per megabyte of source; coverage needs no account, config file or hosted service.
supercorp-aiOpensupercorp-ai/supercov on github.com109 starsScoring cost ~1c/MB
Fish-style autosuggestions for zsh ranked by Jev. As you type, the plugin sends your last 100 distinct history entries and asks which one you are most likely completing, then shows the best match in grey with its score for you to accept.
Independent reimplementation inspired by jevlike that scores pre-written options in one batched forward pass by log-probability over a local Gemma 3 4B, shipping an HTTP server, CLI and a TypeSafe System One API implementation.
Personal-assistant agent built with Vercel's eve framework and 100 mocked tools, served through OpenRouter. Measures how many steps the agent needs when the LLM picks the tool itself versus when Jev picks it via a 101-option Choice.
Browser agent that indexes the page into candidate actions and has Jev pick one, so it cannot click something that was never on the page, while an LLM plans and reads. Every claim in an answer cites a quote stored verbatim from the page, and Jev checks the claim against its quote.
agent-labs-devOpenagent-labs-dev/fastbrowse on github.com100 starsSuite cost $0.36Checkout ratio 195x
A Chrome extension and small web app that find sponsor reads in a YouTube video's transcript using Jev, then skip or flag them; needs a TypeSafe key and, for some modes, a Deepgram key.
Tony Dinh (@tdinh_me)Opentrungdq88/youtube-sponsor-detection on github.com95 starsTranscript mode under 1 cent/hrListen mode ~$0.46/hr
Laya, running locally on Apple Silicon via MLX, and Jev, over TypeSafe's hosted API, play Chrome's T-Rex game side by side on a shared obstacle course, with response times, survival streaks and crash replays recorded.
A computer-use harness for macOS that reads the screen through the Accessibility API and lets Jev pick the action, with no vision model in the loop.
Small type-safe client for asking questions about your data, powered by Jev. Returns probabilities, choices and scores in a single request, and ships an agent skill that teaches coding agents how to design the questions.
A 151M-parameter non-autoregressive decision model on ModernBERT with calibrated uncertainty, inspired by Jev but trained independently, including a benchmark audit against Jev and an in-browser WebGPU playground.
Turns Jev into a chatbot by repeatedly asking it which symbol comes next from an alphabet of options, then sampling from the returned probabilities. An experiment built by describing the sampling strategies to Claude and having it implement them.
Standalone C++ inference for Laya's typed decisions using ggml, with CUDA and Vulkan backends, a Jev-compatible /v1/systemone HTTP server, and automatic request batching.
lkarlslundOpenlaya.cpp on github.com85 starsCUDA BF16 speedup 1.11-2.71x
Pre-alpha PostgreSQL extension that calls TypeSafe Jev from SQL for Choice, Noul and Score, including a batched function that classifies many distinct rows in one request.
giuliosmallOpengiuliosmall/pg_typesafe on github.com82 starsOne-by-one time 23sBatched time 0.86s
Browser automation where an LLM plans and Jev decides each tactical action, executed through Playwright without feeding page snapshots to the LLM. README reports 40/42 tasks passing and roughly 5x less token context.
Ying-Kai-LiaoOpenYing-Kai-Liao/jev-browser on github.com82 starsTask accuracy 40/42Checkout time ~14s
A Python evals and guardrails library for agent traces that uses Jev-style decision models instead of an LLM judge, running Jev through TypeSafe or Vercel, or Kev or Laya locally on a Mac. All checks for a trace go out as one request in a few hundred milliseconds.
openlayer-aiOpenjevals on github.com81 starsVariance vs LLM 92-913x
Puts a live Jev meter on any video: every sentence is scored, every dodge flagged, and the result rendered as a 16:9 edit. The repo reports 99% preset accuracy on a held-out set and about $0.05 for a full debate.
ChetasLuaOpenChetasLua/jevmeter on github.com81 starsFull debate cost $0.0497Jev calls 1,191
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.
