awesome jev projects / system-1 architecture radar
Leave thinking to LLMs, delegate decisions to Jev.
Inspect verified open source codebases to see where Jev sits in production Agent loops. Curated 330+ projects spanning browser automation, model routing, MCP servers, and guardrails.
Indexed Projects
333
Categories
17
Tags
20
Source Evidence
100%
jev-ultrafast — by browser-use
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
langchain-ai
langchain
An optional Jev classifier integration for Python LangChain workflows.
Submits binary, categorical and ordered-score questions and returns typed answers with probabilities.
↳ Adds a classification step that can participate in existing LangChain pipelines.
virattt
ai-hedge-fund
An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.
Converts strategy questions to System One requests and normalizes native answers to the project’s result format.
↳ Allows Jev or other model backends to be used in the same research workflow.
BerriAI
litellm
LiteLLM can use Jev to classify requests for its complexity-based model router.
Maps requests to configured complexity classes that drive backend routing.
↳ Makes the complexity judgment behind routing inspectable.
can1357
oh-my-pi
Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows.
Sends agent state and typed questions to Jev and parses structured answers.
↳ Adds a replaceable judgment provider to existing agent workflows.
davila7
jev-model-router
A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.
Evaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.
↳ Makes routing rules and per-request choices explicit and configurable.
ComposioHQ
composio
An optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.
Turns tool or action conditions into structured questions and passes Jev answers to local invocation logic.
↳ Adds structured judgments to existing tool interfaces.
vercel
ai
The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.
Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.
↳ Reuses a common evaluation interface within AI SDK applications.
trycua
cua
Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.
Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.
↳ Provides Python and TypeScript loops with separate offline and live checks.
pydantic
pydantic-ai
An optional TypeSafe provider and Jev model integration for Pydantic AI.
Converts supported structured output fields into typed Jev questions and maps answers back to the output model.
↳ Lets supported classification outputs use the existing Pydantic AI interface.
elizaOS
eliza
An optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.
Only an explicit systemOne call sends state and questions, returning validated typed answers.
↳ Provides a reusable server-side module; its presence is not evidence of deployed Jev adoption.
langchain-ai
langchainjs
An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.
Uses invoke to call TypeSafe and parse choice, noul, score and probability fields.
↳ Adds typed decisions to LangChain workflows without treating Jev as a chat generator.
vercel-labs
json-render
A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.
Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.
↳ Provides an inspectable composition path alongside token-by-token JSON generation.
openchamber
openchamber
OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.
Jev selects a task category; local category mappings determine the model configuration.
↳ Keeps routing categories and their model assignments explicit.
0xPlaygrounds
rig-typesafeai
An experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.
Sends application state and questions to Jev and parses Choice, Score or Noul answers.
↳ Reuses field layouts between questions and answers and validates answers against questions.
kunchenguid
firstmate
Firstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.
Sends the task brief and candidate rules to Jev, then resolves execution profiles with confidence and local conditions.
↳ Separates semantic matching from the final dispatch policy.
browser-use
jev-ultrafast
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
Chooses an action and its matching DOM element in one request; a text model generates input text.
↳ Separates UI choices, text generation, and browser execution so each step can be inspected.
agentgateway
agentgateway
A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.
Jev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.
↳ Demonstrates gateway integration, not guaranteed prevention of all attacks.
latitude-dev
latitude-llm
Latitude includes an optional Jev preclassifier for conversation checks and their selection records.
Judges which checks apply and can add checks when thresholds and rate limits permit.
↳ Records models, thresholds, latency and selection reasons alongside the baseline.
tamaratran
fast-jev-compaction
Prunes old tool calls and outputs for Claude Code while retaining surviving text verbatim.
Separately judges whether a tool call and its full output are still needed; code keeps, truncates or drops them.
↳ Avoids rewriting paths, commands and errors into a new summary.
ax-llm
ax
Ax provides a TypeSafe integration for boolean or finite-class signatures and native Jev answers.
Maps supported signatures to Jev questions or sends native System One requests.
↳ Reuses structured signatures and Jev probabilities within Ax workflows.
vellum-ai
vellum-assistant
An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.
Submits state and question bundles to System One and returns structured answers to the Assistant.
↳ Adds choices, probabilities, and scoring to an existing assistant.
lahfir
jev-desktop
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.
↳ Keeps the full UI tree out of the main Agent context while exposing the selected action.
CelestoAI
celesto
A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.
Judges whether a finding was introduced by the change, is supported and merits a fix.
↳ Shows execution records and reviewer judgments together.
jarrodwatts
jev-trader
A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.
In Jev mode, order-book judgments feed code that simulates fills or submits configured post-only limit orders.
↳ Defaults to a mock model and dry-runs without a private key; simulated results do not establish profitability.
17 Architecture Categories
Explore dedicated category landing pages for architecture patterns and case studies:
SDK & Decision Frameworks
Official & community SDKs, decision primitives, and Agent execution frameworks.
High-Frequency & Simulation
Low-latency game AI, real-time simulation, and high-frequency branch evaluation.
Evaluation & Observability
Evaluation harnesses, latency profiling, tracing, and telemetry for Jev decisions.
Browser & OS Action
Browser automation and desktop OS control with bounded action candidate selection.
Routing & Cost Optimization
Complexity-based request routing to tier generative models and optimize token spend.
Security & Guardrails
Real-time safety guardrails, prompt injection detection, and moderation gates.
Domain & Vertical Tools
Domain-specific decision engines for finance, legal, e-commerce, and vertical ops.
Context GC & Filter
Context compaction, tool output pruning, and memory garbage collection.
MCP & Integrations
Model Context Protocol (MCP) servers and third-party connector integrations.
CLI & Pipelines
CLI utilities, Git gates, CI/CD pipeline checks, and DevOps automations.
Data & Search
Search intent classification, query routing, vector re-ranking, and ETL triage.
Decision Tools
Standalone decision helpers, schema validators, probability decoders, and utilities.
Codebase & Graph Pathfinding
AST traversal, code graph dependency analysis, automated PR review, and pathfinding.
Creative Tools
UI layout composition, audio/music pipelines, and creative workflow parameter triage.
SDK & Integrations
Third-party framework adapters for LangChain, LlamaIndex, and enterprise stacks.
Voice & Conversation
Voice turn-taking, interruption detection, and real-time dialogue routing.
Classification & Taxonomy
Hierarchical taxonomy tagging, document categorization, and ontology mapping.
Frequently Asked Questions (FAQ)
What is the Awesome Jev Projects Radar?
The Awesome Jev Projects Radar is a developer-centric registry dedicated to TypeSafe Jev and System-1 Agent architectures. Beyond static repo links, it highlights the exact decision point in each codebase where Jev is invoked (Choice, Score, or Noul) and documents the architectural latency/cost gains.
Why delegate bounded decisions to Jev instead of general LLMs?
Generative LLMs excel at creative synthesis and dialogue, but are prone to latency and hallucination when making discrete tool dispatches, safety gates, or routing decisions. Jev evaluates bounded choices in a single forward pass within 200-400ms at minimal token expense.
How are projects vetted and verified for genuine Jev integration?
Every catalog entry undergoes fixed-commit source code review. The radar links directly to public repository files and documentation proving active Jev integration rather than unverified claims.
Why are project detail subpages configured with noindex?
In alignment with technical SEO best practices, the central radar and 17 dedicated category landing pages are fully indexed with rich metadata, while individual repo inspection cards are marked noindex to consolidate crawl equity and prevent thin-content sprawl.