aionedge.
Jev project category

Agent tooling: open source Jev projects

Agent tooling is where Jev sees the most experimentation. These projects sit inside coding agents and assistants such as Claude Code, Codex and Pi, and hand the many small, repetitive choices an agent makes to a fast decision model, leaving the large model free for reasoning and writing.

Projects
179
Jev code linked
50
Common languages
TypeScript, Python, JavaScript, Rust

Where to start

claude-code-templatesdavila7/claude-code-templatesEvaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.★ 31,082 · Jev code linkedjev-review (devagrawal09)devagrawal09/jev-reviewJudges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.★ 544 · Jev code linkedforemanthruwire/foremanAsyncTypeSafeClient.system_one with default jev-latest sends Noul questions for supervision.★ 512 · Jev code linked

All 179 Agent tooling projects

Sorted by GitHub stars, which belong to the whole repository rather than its Jev integration.

  1. AutoGPTSignificant-Gravitas/AutoGPTThe AutoGPT agent platform, which ships a TypeSafe route block that uses Jev to choose a workflow branch.★ 187,545
    Python
  2. claude-code-templatesdavila7/claude-code-templatesA community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.★ 31,082
    Python
  3. openworkdifferent-ai/openworkOpen-source Claude Cowork alternative whose eval testkit can use Jev as a typed verification judge for agent-produced work.★ 23,696
    TypeScript
  4. fast-jev-compactiontamaratran/fast-jev-compactionClaude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.★ 6,295
    TypeScript
  5. jev-review (devagrawal09)devagrawal09/jev-reviewReviews a Git diff or a codebase in stages and displays review leads in a local dashboard.★ 544
    TypeScript
  6. hermes-jev-skillskerpopule/hermes-jev-skillsHermes plugin and skill suite using Jev for model routing, skill selection, memory filtering, compaction, and GUI actions.★ 518
    Python
  7. foremanthruwire/foremanAn independent supervisor loop that reads worker diffs, logs and tests, asks Jev Nouls about stuck / off-track / verify, then applies a Python policy.★ 512
    Python
  8. jev-searchsuperagents-lab/jev-searchSearch the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.★ 408
    TypeScript
  9. jev-router (gargpratyush)gargpratyush/jev-routerRoute to the cheapest model in claude code for your task using jev-router.★ 340
    JavaScript
  10. jev-mcp (jkudish)jkudish/jev-mcpEight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.★ 282
    JavaScript
  11. typesafe-mcpitsmostafa/typesafe-mcpAn MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.★ 258
    Go
  12. jev-codex-router0xNatoshi/jev-codex-routerUses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.★ 222
    JavaScript
  13. abidecoldteadotai/abideSupervises coding-agent edits and uses Jev to flag violations of project rules.★ 210
    TypeScript
  14. jev-review (NiazMorshed2007)NiazMorshed2007/jev-reviewA local MCP code-quality reviewer returning structured scores to coding Agents.★ 203
    TypeScript
  15. compact-adviserkunchenguid/compact-adviserAgent plugin that uses Jev to judge when a coding session should compact its context.★ 178
    TypeScript
  16. JevRouterBillionsBobby/JevRouterA lightweight Jev-powered router for models, tools, and subagents.★ 167
    TypeScript
  17. jev-prunertamaratran/jev-prunerA Claude Code output-pruning plugin filtering selected Bash output before it reaches the main model.★ 140
    TypeScript
  18. pi-jev (y0usaf)y0usaf/pi-jevA Pi extension that flags tool risks before execution and checks output for secrets and failure types.★ 140
    TypeScript
  19. pi-wardenDevMortimer/pi-wardenAdds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.★ 135
    TypeScript
  20. jev-semgrepuehaj/jev-semgrepA semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.★ 130
    JavaScript
  21. building-with-jev-skilldbreunig/building-with-jev-skillA skill for writing and improving programs that call Jev, TypeSafe's System One model.★ 128
  22. skillrankerDicklesworthstone/skillrankerRust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.★ 113
    Rust
  23. jev-codedevagrawal09/stanley-codeHelps coding Agents locate code, check change intent, triage test failures, and organize review findings.★ 113
    TypeScript
  24. jev-dsh-decisionDevin-AXIS/jev-dsh-decisionDecision plugin for DeepSeek Harness and iPolloWork that lets OpenCode, Codex, and other agents use Jev to select tools, skills, and task owners and evaluate outputs.★ 107
    JavaScript
  25. jegrepcan1357/jegrepSemantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query.★ 83
    Rust
  26. grok-bot-jevBodila51/grok-bot-jevGrok Bot integration where Jev applies usage gates and routes requests before the generative model runs.★ 75
    Python
  27. jev-lintmizchi/jev-lintText linter that uses Jev Score judgments to evaluate strings embedded in source code against configurable writing rules.★ 73
    TypeScript
  28. winnowGhalebDweikat/winnowA context filter for Claude Code that hides irrelevant tool-output blocks and keeps the original text available for recall.★ 66
    Python
  29. agent-routernidhi-singh02/agent-routerCLI that uses Jev task classification to choose and launch Cursor, Claude Code, Codex, or OpenCode with an appropriate model and effort level.★ 66
    TypeScript
  30. jevgrepnassim-arifette/jevgrepSemantic code search CLI and MCP server: Jev scores authorized repository excerpts and returns exact file paths and line numbers to coding agents.★ 52
    TypeScript
  31. jev-rulesEliaAlberti/jev-rulesClaude Code plugin where Jev decides which project rules apply to each prompt and edited file.★ 48
    JavaScript
  32. jev-code-revieweregma-ai/jev-code-reviewerReview behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill + GitHub extension.★ 47
    JavaScript
  33. jev-siftkbhuw/jev-siftAgent plugin and MCP tool where Jev classifies batches of text so agents can read only the relevant items. No repository-level license file was found during review.★ 45
    JavaScript
  34. hono-jev-routeryusukebe/hono-jev-routerAn experimental semantic HTTP router for Hono using natural-language route descriptions.★ 45
    TypeScript
  35. duet-agentdzhng/duet-agentFull-stack agent harness with memories, long-running tasks, multi-agent relay, and a Jev-backed model-routing table.★ 44
    TypeScript
  36. pi-jev (TheoOliveira)TheoOliveira/pi-jevHelps Pi Agents find tools and skills for a task, with structured evaluation and optional history filtering.★ 39
    TypeScript
  37. ask-jev-skillshantanugoel/ask-jev-skillSkill for Hermes, and other agents, to ask typesafe's jev.★ 39
    Python
  38. jev-mcp (burnigtm)burnigtm/jev-mcpMCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.★ 36
    TypeScript
  39. jev-seoAkashPriyadarshii/jev-seoAn experimental Rust SEO/GEO CLI and MCP tool combining page checks, DuckDuckGo queries and optional Jev scoring.★ 34
    Rust
  40. pi-jev-skill-pickersafzanpirani/pi-jev-skill-pickerRank Pi Agent Skills for the current task with TypeSafe Jev.★ 32
    TypeScript
  41. pluginscline/pluginsCline's official plugin collection, including a jev-browser plugin where Jev chooses browser actions.★ 31
    TypeScript
  42. snifftestDanRWilloughby/snifftestA Markdown and plain-text prose linter using local rules and optional Jev judgments.★ 29
    TypeScript
  43. jev-guardleepokai/jev-guardTool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.★ 26
    JavaScript
  44. yoshicompozy/yoshiContext-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into [Compozy](https://github.com/compozy/compozy).★ 24
    TypeScript
  45. pi-jev-auto-modejomatsu/pi-jev-auto-modeAdds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.★ 23
    TypeScript
  46. is-maliciousluantak/is-maliciousScans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.★ 22
    TypeScript
  47. jev-cli (Nasrallah-AL)Nasrallah-AL/jev-cliThe jevctl command-line tool connects verification, classification and scoring questions to text input and scripts.★ 20
    TypeScript
  48. jev-mcp (blakestone-x)blakestone-x/jev-mcpWraps Jev classification, scoring, yes/no judgments and candidate matching as MCP tools.★ 20
    Python
  49. jgrepkeltokhy/jgrepGrep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.★ 20
    Python
  50. slop-graderlukstei/slop-graderJev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.★ 20
    TypeScript
  51. jev-axishiftynick/jev-axiA CLI for Jev pick, rate, check, rank, triage, and guard tasks, with optional hooks before Agent tool calls.★ 19
    TypeScript
  52. jevwireBrainwires/jevwireProvides Jev MCP tools, an embeddable library and Claude Code hooks for Agents.★ 18
    TypeScript
  53. jcrNiazMorshed2007/jcrJev Capability Resolver: agents query a nested capability tree and receive only the deterministic commands and context relevant to the task.★ 18
    JavaScript
  54. jev-belayvalentynkit/jev-belayClaude Code Stop hook that asks four Jev questions when files changed without a passing check, blocking unverified completion claims while failing open on errors.★ 18
    JavaScript
  55. jev-agent-skill-routerGodsBoy/jev-agent-skill-routerTyped, confidence-aware agent skill routing with TypeSafe Jev.★ 17
    Python
  56. jev-superpowersAkashPriyadarshii/jev-superpowersCross-agent software-development skills that add Jev decisions to planning, execution, debugging, and completion gates.★ 14
    HTML
  57. jev (BorisLeMeec)BorisLeMeec/jevA Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.★ 14
    Go
  58. public-browserSilbercue/public-browserLets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no paid tier.★ 14
    TypeScript
  59. hermes-jevkeeltrace/hermes-nerveAn asynchronous Jev companion for Hermes Agent covering relevance, completion, recovery and optional admission decisions.★ 14
    Python
  60. pi-jev-router (philippdubach)philippdubach/pi-jev-routerPi model router that uses Jev task classification and a measured Pareto frontier over quality, cost, and latency to select an OpenRouter model.★ 14
    TypeScript
  61. patdowntyler-dot-earth/patdownBlock, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, and more. Built with Effect.★ 14
    TypeScript
  62. typesafe-skill-routerDECRUX9812/typesafe-skill-routerAn opt-in Hermes Agent plugin that asks Jev to suggest one relevant skill before a model call.★ 13
    Python
  63. hermes-jev-approvalsanpicasso/hermes-jev-approvalsAn experimental Hermes command-approval provider for the auxiliary.approval task only.★ 13
    Python
  64. pi-jev-routermejiasd3v/pi-jev-routerAutomatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway.★ 12
    JavaScript
  65. evokeevoke-build/evokeSoftware, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK.★ 11
    Rust
  66. JevLintiamtoomas/JevLintConfigurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.★ 11
    TypeScript
  67. pi-quiet-askHyunjunJeon/pi-quiet-askTypeSafe Jev as the pi coding agent's quiet decision layer.★ 10
    TypeScript
  68. clean-code-reviewfrostney/clean-code-reviewEvery code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.★ 10
    TypeScript
  69. learn-jev-end-to-endharshithsunku/learn-jev-end-to-endLearn Jev end to end: a free hands-on course. Build 13 AI agent use cases with a fast brain (Jev) and a slow brain (LLM). One OpenRouter key.★ 10
    Jupyter Notebook
  70. pi-verdictjesset/pi-verdictA minimal permission gate for Pi in the style of Claude Code's auto mode.★ 10
    TypeScript
  71. pi-fast-jev-compactionjoelhooks/pi-fast-jev-compactionPi extension: verbatim context compaction with TypeSafe Jev decisions.★ 10
    TypeScript
  72. jev-commitvalentynkit/jev-commitPre-commit hook where Jev checks the message against the staged diff and flags debug leftovers, unmentioned work, and added credentials.★ 10
    Python
  73. jev-browser-bridgelexmount/jev-browser-bridgePlug any CDP browser into Jev — cloud, local or self-hosted, including browsers that never draw a page.★ 9
    Python
  74. jev-router (prismhq)prismhq/jev-routerOpen-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.★ 9
    Python
  75. pi-jeviefnaf/pi-jevPi extension suite for Jev-powered context compaction and model routing.★ 8
    TypeScript
  76. omp-jev-compactionjerryfane/omp-jev-compactionVerbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter.★ 8
    TypeScript
  77. jev-routerrajdhakad9826/jev-routerLLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.★ 8
    TypeScript
  78. dsh-jev-interceptorAskTheWay/dsh-jev-interceptorA DeepSeek Harness plugin that asks Jev to classify the risk of every tool call, auto-approving only with supporting evidence and failing closed.★ 7
    TypeScript
  79. pi-heedNyarlathoteppppp/pi-heedRuntime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.★ 7
    TypeScript
  80. jev-mcp (arunav25)arunav25/jev-mcpConnect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.★ 7
    JavaScript
  81. jev-mcp (rashedInt32)rashedInt32/jev-mcpMCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.★ 7
    TypeScript
  82. switchboardruban-24/switchboardAn open-source, model-agnostic decision router for Claude Code and Codex.★ 7
    TypeScript
  83. opencompanyuseopencompany/opencompanyAI workspace whose approval review uses Jev to gate workspace actions with typed decisions.★ 7
    TypeScript
  84. Augustus24601/AugustusAgent skill for designing Jev-assisted systems with decision theory, composition patterns, question diagnostics, and validation gates.★ 6
    Python
  85. pi-jev-contextNyarlathoteppppp/pi-jev-contextModel performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact.★ 6
    TypeScript
  86. jev-tool-routerjackbarunz/jev-tool-routerMCP router for Codex that uses Jev to select an external tool on demand instead of exposing the agent to every tool schema.★ 6
    JavaScript
  87. jev-architectkaranb192/jev-architectAgent skill for finding, designing, and validating useful Jev decision loops before committing them to an application.★ 6
    HTML
  88. riffscale-venture-partners/riffA small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.★ 6
    Python
  89. JevXvij-sameerb5/JevXCLI and MCP tool that finds decision-shaped code, proposes Jev replacements and checks changes with project tests.★ 6
    TypeScript
  90. jit-contextwojciechwiesner/jit-contextArchitectural Moat: JIT-JEV Context OS — Epistemic runtime & JEV System 1 context gate for AI agents (L0 SQLite WAL <3ms, Epistemic Invariants I1–I10, CERN Zenodo DOI: 10.5281/zenodo.22649542).★ 6
    Python
  91. bicameralAbdelStark/bicameralHybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.★ 5
    TypeScript
  92. diffjuryraihankhan-rk/diffjuryDiffJury — TypeSafe Jev PR risk router + code review coach.★ 5
    TypeScript
  93. hunchKelbie/hunchSemantic code review with Jev, plain-English rules, and installable agent skills.★ 4
    TypeScript
  94. jev-skill-gateShivamPansuriya/jev-skill-gateRanks Claude Code skills for the current project to reduce the descriptions loaded by default.★ 4
    JavaScript
  95. jev-oas-sentinelShuhanSun/jev-oas-sentinelCatch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.★ 4
    Python
  96. jcm-routeradarshmishra07/jcm-routerLocal proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.★ 4
    TypeScript
  97. jev-prefdoeixd/jev-prefTurns AGENTS.md preferences into rules checked by Jev against hunks, staged files or PRs.★ 4
    JavaScript
  98. slidepilotharshil1712/slidepilotVoice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev.★ 4
    TypeScript
  99. reflexkaustav1996/reflexA coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent.★ 4
    TypeScript
  100. fast-dev-compactionleonaaardob/fast-dev-compactionCodex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.★ 4
    TypeScript
  101. jev-specnozomi-koborinai/jev-specSpecification-driven semantic verification engine that uses Jev to check AI-generated code and specs against explicit requirements.★ 4
    TypeScript
  102. tenetzoidsh/tenetCommit-time review gate where Jev judges plain-language rules against agent-written code.★ 4
    Go
  103. mastra-jev-moderationCodeAlive-AI/mastra-jev-moderationMastra input processor that uses Jev for a typed block decision and moderation category.★ 3
    TypeScript
  104. jev-predict-skillDanielKillenberger/jev-predict-skillAn Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.★ 3
    HTML
  105. jev-judgmentHyunjunJeon/jev-judgmentAdds judgment checks for authorization, operation risk, and failure causes to coding Agents.★ 3
    Python
  106. jev-flash-routerRavinder82/jev-flash-routerMCP server that uses Jev to route coding-agent decisions such as file selection, task paths, and test-impact checks.★ 3
    TypeScript
  107. jev-mcp-dispatcherabhishekashokvkumar/jev-mcp-dispatcherNatural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence. No repository-level license file was found during review.★ 3
    Python
  108. hermes-jev-pluginajensenwaud/hermes-jev-pluginTypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate★ 3
    Python
  109. open-jev-approvalsalexj11324/open-jev-approvalsApproval gate for Claude Code and Codex: intercepts tool calls, gets a Jev risk judgment, then applies a versioned local allow/deny policy.★ 3
    Go
  110. jev-shieldcaiovicentino/jev-shieldSemantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.★ 3
    JavaScript
  111. typesafe-cli (geilt)geilt/typesafe-cliCLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.★ 3
    Python
  112. tiershiftiamvatsalpatel/tiershiftShift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.★ 3
    TypeScript
  113. jevexjvsteiner/jevexAn Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute.★ 3
    Python
  114. todo-jevmaker-KK/todo-jevA task-routing experiment combining skill conditions and environment checks to suggest rules, skills or a large model.★ 3
    Python
  115. dsh-jev-decidenanami-0713/dsh-jev-decideA DeepSeek Harness plugin that registers Jev as an agent tool returning calibrated yes/no, choice and score probabilities for routing and triage.★ 3
    JavaScript
  116. dsh-jevnoetion/dsh-jevDSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.★ 3
    TypeScript
  117. limpetnoplan-inc/limpetA Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.★ 3
    Python
  118. codex-jev-routersuenot/codex-jev-routerPortable JevRouter setup for cost-aware Codex subagent model selection, with English and Russian instructions.★ 3
    JavaScript
  119. prompt2jevsumleo/prompt2jevAgent 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★ 3
    Python
  120. jev-swap0xjba/jev-swapScans TypeScript, JavaScript and Python for decision-like LLM calls, generates Jev replacements and shadow-tests recorded traffic.★ 2
    HTML
  121. jev-gitAkashPriyadarshii/jev-gitSub-second pre-commit and pre-push semantic gate that screens staged diffs with Jev.★ 2
    Rust
  122. jev-scoutAkashPriyadarshii/jev-scoutA repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.★ 2
    Rust
  123. typesafe-ai-firewallAnshChoudhary/typesafe-ai-firewallShadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md. No repository-level license file was found during review.★ 2
    Python
  124. jev-mcp (BYK)BYK/jev-mcpAn eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.★ 2
    TypeScript
  125. typesafe-modBeLazy167/typesafe-modClaude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.★ 2
    TypeScript
  126. pi-fast-jev-compaction (QuentinDanblon)QuentinDanblon/pi-fast-jev-compactionPi context pruning that uses Jev to drop or truncate stale tool calls while preserving retained content verbatim.★ 2
    TypeScript
  127. jev-skillfulbestagentkits/jev-skillfulPer-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.★ 2
    TypeScript
  128. jev-mcp (freepik-company)freepik-company/jev-mcpMCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe★ 2
    Go
  129. decision-firstharrymunro/decision-firstAgent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt★ 2
    Python
  130. jeariJ03l/jearJev-routed client for NEAR AI Cloud inference and IronClaw agents.★ 2
    Rust
  131. pi-typesafe-jevlegacybridge-tech/pi-typesafe-jevA pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.★ 2
    TypeScript
  132. skill-routerlomeshdutta/skill-routerTell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.★ 2
    Python
  133. jev-workbenchmolis-ai/jev-workbenchDefines, tests, and publishes Jev decision functions in a local UI so backends and Agents can call fixed versions.★ 2
    TypeScript
  134. typesafe-migration-guardopaielsheikh/typesafe-migration-guardAutomated database migration safety reviewer powered by TypeSafe AI (Jev System One model).★ 2
    TypeScript
  135. jev-compaction (picaye)picaye/jev-compactionHermes context compaction that has Jev score tool calls, drops stale content, and preserves everything retained verbatim.★ 2
    JavaScript
  136. jev-builder-looprainbowpuffpuff/jev-builder-loopGrok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act).★ 2
    Python
  137. jev-system-architectsamtay32/jev-system-architectSystem-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.★ 2
  138. ailerixtylerjharden/ailerixType-safe model router. Jev (System One) banks each request to a typed catalog route.★ 2
    TypeScript
  139. jev-bugfixxiaoxiaomugong/jev-bugfixCodex bug-investigation skill with optional Jev ranking of manually collected code candidates.★ 2
    Python
  140. jevonianxinyao27/jevonianLocal model-routing proxy where Jev selects the model route and reasoning depth, and also judges which tool history can be compacted.★ 2
    TypeScript
  141. JevGuardJhonnyr97/JevGuardClaude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model★ 1
    TypeScript
  142. pi-jev-helmZ761293629/pi-jev-helmPi extension that classifies tasks with Jev and routes each run to an explicitly configured model.★ 1
    TypeScript
  143. jev-triagecephalization/jev-triageUses typeful jev, zero sync to pull and sync large repositories for issue triage.★ 1
    TypeScript
  144. stepwardengetexcited/stepwardenClaude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it.★ 1
    TypeScript
  145. Antigravity-mcp-semantic-search-with-TypeSafeAigreenyamao/Antigravity-mcp-semantic-search-with-TypeSafeAiFast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.★ 1
    Python
  146. jevkeephatt-io/jevkeepCodex plugin that uses Jev to preserve useful conversation excerpts alongside compacted summaries.★ 1
    TypeScript
  147. jev-toolkitjbt95/jev-toolkitMCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.★ 1
    TypeScript
  148. ask-jevomni-/ask-jevA Windows PowerShell tool for auditing recorded Codex execution evidence with :jev.★ 1
    PowerShell
  149. askjev (pZacca)pZacca/askjevUnofficial MCP server for Jev (Typesafe AI)★ 1
    TypeScript
  150. jev-retrievalromeromarcelo/jev-retrievalSemantic code and document search CLI — BM25 recall + TypeSafe Jev calibrated precision.★ 1
    Rust
  151. jev-skill-routershimo4228/jev-skill-routerClaude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.★ 1
    Python
  152. omp-typesafesiddicky/omp-typesafeTypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.★ 1
    TypeScript
  153. hermes-jev-routerussyverse/hermes-jev-routerExperimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.★ 1
    Python
  154. jev-agent-kitwalidboulanouar/jev-agent-kitjevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.★ 1
    JavaScript
  155. dsh-jev-verifyxienda/dsh-jev-verifyJev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.★ 1
    JavaScript
  156. progressgateAshutoshVJTI/progressgateDetect semantic stagnation in AI agent loops★ 0
    TypeScript
  157. jevmateGastonGelhorn/jevmateCLI, MCP server and coding-agent plugin that uses Jev to rank files, select tests and triage failures.★ 0
    Python
  158. pi-jev-codeKamilPostrozny/pi-jev-codeSingle-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.★ 0
    TypeScript
  159. jev-pluginsPinutss/jev-pluginsCursor and Hermes plugin marketplace for JEV Labs routing tools.★ 0
  160. agent-gate-loopRipwords/agent-gate-loopReusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.★ 0
    TypeScript
  161. omp-jevens-classifierSTRML/omp-jevens-classifierJev-powered model-judged permission gate for OMP (TypeSafe System One).★ 0
    TypeScript
  162. zcode-jevZahrannnn/zcode-jevTyped judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.★ 0
    TypeScript
  163. pi-agent-foremanalexshpunt/pi-agent-foremanSend Pi agents back to work when they stop before the job is done.★ 0
    TypeScript
  164. switchboardaniruddh-krovvidi/switchboardGuardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.★ 0
    Python
  165. Jev-Checkpointashishakkumar/Jev-CheckpointA local MCP server that uses TypeSafe Jev to confidence-gate an AI agent’s next step, routing uncertain decisions to proceed, deeper review, or human input.★ Unknown
    TypeScript
  166. typesafe-demo-mcpbestagentkits/typesafe-demo-mcpMCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.★ 0
    TypeScript
  167. AskJev-MCPcbruyndoncx/AskJev-MCPMCP server for typed Jev Choice, Noul, and Score judgments with probabilities and confidence.★ 0
    JavaScript
  168. decide-mcpdakdevs/decide-mcpConfigurable decision MCP server with AI SDK, Jev, percentage scores, and bias-profile routing.★ 0
    TypeScript
  169. jev-packsdtduc-git/jev-packsEvidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints★ 0
    Python
  170. pi-jev-router (gloridifice)gloridifice/pi-jev-routerJev model-routing integration for the Pi coding agent.★ Unknown
    TypeScript
  171. pi-typesafe-routerjekozyra/pi-typesafe-routerA Pi coding-agent extension that routes each task to a model configuration using TypeSafe Jev judgments.★ 0
    TypeScript
  172. frostmarcus/frostA flexible and configurable CLI model router using TypeSafe Jev.★ 0
    Go
  173. check-riskmoezubair/check-riskA CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.★ 0
    TypeScript
  174. typesafeai-reviewrbalch/typesafeai-reviewUsing Typesafe.AI to generate diff reviews.★ 0
    Python
  175. jev-review (thiago-ss)thiago-ss/jev-reviewAutonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.★ 0
    Python
  176. pi-typesafetwilwa/pi-typesafePi coding-agent extension built on the TypeSafe AI System One API (Jev).★ 0
    TypeScript
  177. jev-atlasv60samurai/jev-atlasMap where Jev and System One models actually belong in your project, test the strongest ideas, then implement them. A skill for Claude Code and Codex.★ 0
    Python
  178. jev-agent-skillyuyang2230/jev-agent-skillA Claude Code skill that offloads classify, screen, score and verify steps from an AI agent to Jev through OpenCode Zen.★ 0
    Python
  179. agent-handoff-gatezsoXi/agent-handoff-gateExperimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.★ 0
    Python

Related categories