Awesome Jev

Awesome Jev

Projects built on Jev, curated by Jev. Every repository below was collected from GitHub and judged by Jev in a single call. Code applies the policy; nothing was hand-picked. How it works.

1445judged
1003listed
148review
294excluded
2026-09-18generated
Status
View
1003 entries

  • DevMortimer/pi-warden

    ★ 61

    Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop

    genuine0.92cat1.00subst2.90Agent and Dev ToolingTypeScriptreadme pick

  • jomatsu/pi-jev-auto-mode

    ★ 8

    Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

    genuine0.96cat1.00subst2.91Agent and Dev ToolingTypeScriptreadme pick

  • TheoLeeCJ/SemIf

    ★ 1.5k

    Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

    genuine0.79cat1.00subst2.04Research and EvalsPythonreadme pick

  • TheoLeeCJ/openjev

    ★ 1.5k

    Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

    genuine0.81cat1.00subst2.04Research and EvalsPythonreadme pick

  • AbdelStark/jev-benchmarks

    ★ 6

    Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

    genuine0.97cat1.00subst2.58Research and EvalsPythonreadme pick

  • realZachi/pg-jev

    ★ 137

    Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

    genuine0.90cat1.00subst2.60IntegrationsPythonreadme pick

  • Brainwires/jevwire

    ★ 3

    Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)

    genuine0.95cat0.98subst2.95Agent and Dev ToolingTypeScriptreadme pick

  • Brainwires/jev-mcp

    ★ 3

    Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)

    genuine0.94cat0.99subst2.96Agent and Dev ToolingTypeScriptreadme pick

  • nekuda-ai/WindTunnel

    ★ 50

    A WebMCP benchmark, measures WebMCP against other browser-agent interfaces.

    genuine0.64cat0.99subst2.91Research and EvalsHTMLreadme pick

  • Ying-Kai-Liao/jev-browser

    ★ 9

    Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

    genuine0.97cat0.81subst2.70Agent and Dev ToolingJavaScriptreadme pick

  • reachjalil/jev-tree

    ★ 2

    Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.

    genuine0.89cat0.90subst2.78SDKs and ClientsTypeScriptreadme pick

  • jomatsu/zod-jev

    ★ 6

    No description provided.

    genuine0.93cat0.86subst2.80IntegrationsTypeScriptreadme pick

  • StefanoITA/ts-jev-cost-calculator

    ★ 1

    Unofficial CLI + Python estimator of tokens, cost and context limits for TypeSafe (System One / Jev) API requests. Not affiliated with TypeSafe.

    genuine0.87cat0.62subst2.66SDKs and ClientsPythonreadme pick

  • aabolfazl/typesafe-local

    ★ 4

    Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.

    genuine0.91cat1.00subst2.15Research and EvalsPythonreadme pick

  • typesafe-ai/system-one-adapter-python

    ★ 103

    Drop-in TypeSafeClient replacement backed by LLM APIs

    genuine0.91cat0.41subst2.71OfficialPythonreadme pick

  • shiftynick/jev-axi

    ★ 12

    Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

    genuine0.97cat0.78subst2.82Agent and Dev ToolingTypeScriptreadme pick

  • mateonunez/jod

    ★ 3

    Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.

    genuine0.96cat0.95subst2.78SDKs and ClientsTypeScriptreadme pick

  • AbdelStark/heist-one

    ★ 2

    Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.

    genuine0.95cat1.00subst2.74Games and SimulationTypeScriptreadme pick

  • TheBous/jev-flash-review

    ★ 1

    No description provided.

    genuine0.95cat1.00subst2.86Agent and Dev ToolingTypeScriptreadme pick

  • shiro-0x/hersona

    ★ 52

    346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality everywhere.

    genuine0.51cat0.74subst2.95Agent and Dev ToolingPythonreadme pick

  • kieranklaassen/ruby_llm-typesafe

    ★ 9

    TypeSafe structured-output provider for RubyLLM 2

    genuine0.91cat0.95subst2.79IntegrationsRubyreadme pick

  • keeltrace/hermes-jev

    ★ 3

    Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

    genuine0.95cat0.57subst2.82Agent and Dev ToolingPythonreadme pick

  • jmanhype/jev-dspy-lab

    ★ 0

    Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

    genuine0.89cat1.00subst2.47Research and EvalsPythonreadme pick

  • konstantinosbotonakis/codex-context-diet

    ★ 0

    Codex plugin: Jev-guided dieting of bulky tool results

    genuine0.96cat0.95subst2.65Agent and Dev ToolingTypeScriptreadme pick